Hugging Face's logo

illuin-conteb
/
modernbert-large-insent

Sentence Similarity
sentence-transformers
Safetensors
English
modernbert
feature-extraction
text-embeddings-inference
Model card Files
xet
Community
1
mlconti commited on
Commit
d2f8fa7
·
verified ·
1 Parent(s): e344d02

Upload folder using huggingface_hub

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. 1_Pooling/config.json +10 -0
  2. README.md +0 -0
  3. checkpoint-1000/1_Pooling/config.json +10 -0
  4. checkpoint-1000/README.md +0 -0
  5. checkpoint-1000/config.json +47 -0
  6. checkpoint-1000/config_sentence_transformers.json +10 -0
  7. checkpoint-1000/model.safetensors +3 -0
  8. checkpoint-1000/modules.json +20 -0
  9. checkpoint-1000/optimizer.pt +3 -0
  10. checkpoint-1000/rng_state_0.pth +3 -0
  11. checkpoint-1000/rng_state_1.pth +3 -0
  12. checkpoint-1000/rng_state_2.pth +3 -0
  13. checkpoint-1000/rng_state_3.pth +3 -0
  14. checkpoint-1000/scheduler.pt +3 -0
  15. checkpoint-1000/sentence_bert_config.json +4 -0
  16. checkpoint-1000/special_tokens_map.json +37 -0
  17. checkpoint-1000/tokenizer.json +0 -0
  18. checkpoint-1000/tokenizer_config.json +945 -0
  19. checkpoint-1000/trainer_state.json +1437 -0
  20. checkpoint-1000/training_args.bin +3 -0
  21. checkpoint-1234/1_Pooling/config.json +10 -0
  22. checkpoint-1234/README.md +0 -0
  23. checkpoint-1234/config.json +47 -0
  24. checkpoint-1234/config_sentence_transformers.json +10 -0
  25. checkpoint-1234/model.safetensors +3 -0
  26. checkpoint-1234/modules.json +20 -0
  27. checkpoint-1234/optimizer.pt +3 -0
  28. checkpoint-1234/rng_state_0.pth +3 -0
  29. checkpoint-1234/rng_state_1.pth +3 -0
  30. checkpoint-1234/rng_state_2.pth +3 -0
  31. checkpoint-1234/rng_state_3.pth +3 -0
  32. checkpoint-1234/scheduler.pt +3 -0
  33. checkpoint-1234/sentence_bert_config.json +4 -0
  34. checkpoint-1234/special_tokens_map.json +37 -0
  35. checkpoint-1234/tokenizer.json +0 -0
  36. checkpoint-1234/tokenizer_config.json +945 -0
  37. checkpoint-1234/trainer_state.json +1726 -0
  38. checkpoint-1234/training_args.bin +3 -0
  39. checkpoint-500/1_Pooling/config.json +10 -0
  40. checkpoint-500/README.md +0 -0
  41. checkpoint-500/config.json +47 -0
  42. checkpoint-500/config_sentence_transformers.json +10 -0
  43. checkpoint-500/model.safetensors +3 -0
  44. checkpoint-500/modules.json +20 -0
  45. checkpoint-500/optimizer.pt +3 -0
  46. checkpoint-500/rng_state_0.pth +3 -0
  47. checkpoint-500/rng_state_1.pth +3 -0
  48. checkpoint-500/rng_state_2.pth +3 -0
  49. checkpoint-500/rng_state_3.pth +3 -0
  50. checkpoint-500/scheduler.pt +3 -0
1_Pooling/config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "word_embedding_dimension": 1024,
3
+ "pooling_mode_cls_token": false,
4
+ "pooling_mode_mean_tokens": true,
5
+ "pooling_mode_max_tokens": false,
6
+ "pooling_mode_mean_sqrt_len_tokens": false,
7
+ "pooling_mode_weightedmean_tokens": false,
8
+ "pooling_mode_lasttoken": false,
9
+ "include_prompt": true
10
+ }
README.md ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-1000/1_Pooling/config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "word_embedding_dimension": 1024,
3
+ "pooling_mode_cls_token": false,
4
+ "pooling_mode_mean_tokens": true,
5
+ "pooling_mode_max_tokens": false,
6
+ "pooling_mode_mean_sqrt_len_tokens": false,
7
+ "pooling_mode_weightedmean_tokens": false,
8
+ "pooling_mode_lasttoken": false,
9
+ "include_prompt": true
10
+ }
checkpoint-1000/README.md ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-1000/config.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "./models/modernbert-embed-large",
3
+ "architectures": [
4
+ "ModernBertModel"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 50281,
9
+ "classifier_activation": "gelu",
10
+ "classifier_bias": false,
11
+ "classifier_dropout": 0.0,
12
+ "classifier_pooling": "mean",
13
+ "cls_token_id": 50281,
14
+ "decoder_bias": true,
15
+ "deterministic_flash_attn": false,
16
+ "embedding_dropout": 0.0,
17
+ "eos_token_id": 50282,
18
+ "global_attn_every_n_layers": 3,
19
+ "global_rope_theta": 160000.0,
20
+ "gradient_checkpointing": false,
21
+ "hidden_activation": "gelu",
22
+ "hidden_size": 1024,
23
+ "initializer_cutoff_factor": 2.0,
24
+ "initializer_range": 0.02,
25
+ "intermediate_size": 2624,
26
+ "layer_norm_eps": 1e-05,
27
+ "local_attention": 128,
28
+ "local_rope_theta": 10000.0,
29
+ "max_position_embeddings": 8192,
30
+ "mlp_bias": false,
31
+ "mlp_dropout": 0.0,
32
+ "model_type": "modernbert",
33
+ "norm_bias": false,
34
+ "norm_eps": 1e-05,
35
+ "num_attention_heads": 16,
36
+ "num_hidden_layers": 28,
37
+ "pad_token_id": 50283,
38
+ "position_embedding_type": "absolute",
39
+ "reference_compile": true,
40
+ "repad_logits_with_grad": false,
41
+ "sep_token_id": 50282,
42
+ "sparse_pred_ignore_index": -100,
43
+ "sparse_prediction": false,
44
+ "torch_dtype": "bfloat16",
45
+ "transformers_version": "4.48.1",
46
+ "vocab_size": 50368
47
+ }
checkpoint-1000/config_sentence_transformers.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "__version__": {
3
+ "sentence_transformers": "3.3.1",
4
+ "transformers": "4.48.1",
5
+ "pytorch": "2.5.1+cu118"
6
+ },
7
+ "prompts": {},
8
+ "default_prompt_name": null,
9
+ "similarity_fn_name": "cosine"
10
+ }
checkpoint-1000/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:befd2aa22a32e43f225d9101f1b5bd30351ef393a577b70219daf805413b4403
3
+ size 789580328
checkpoint-1000/modules.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [
2
+ {
3
+ "idx": 0,
4
+ "name": "0",
5
+ "path": "",
6
+ "type": "sentence_transformers.models.Transformer"
7
+ },
8
+ {
9
+ "idx": 1,
10
+ "name": "1",
11
+ "path": "1_Pooling",
12
+ "type": "sentence_transformers.models.Pooling"
13
+ },
14
+ {
15
+ "idx": 2,
16
+ "name": "2",
17
+ "path": "2_Normalize",
18
+ "type": "sentence_transformers.models.Normalize"
19
+ }
20
+ ]
checkpoint-1000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fc8f9cf65ecc52adc4b38dabff9bd37d423935c603812635d55eb2a74b43dfe9
3
+ size 1579269882
checkpoint-1000/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de22e8288d31a1e0ef0304e27e4b73375145a2a352b53a88122f8f100d3cbf23
3
+ size 14960
checkpoint-1000/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:765bc91fd8481923ad15932814b9ef7e41641cd38a760210ed13c3b92feee1a8
3
+ size 14960
checkpoint-1000/rng_state_2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc70fad49b9f2fc5798e70a5d014a7d24303bc62d9a6a6720832896c422e1cb1
3
+ size 14960
checkpoint-1000/rng_state_3.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:039f2ced681a9d057807e62a460c0ea44b6561716485c21229aa23f7e5e21a29
3
+ size 14960
checkpoint-1000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca864724fb3a6269d906759cfe8fe22fa45e5752b013e4be2e17312116913d18
3
+ size 1064
checkpoint-1000/sentence_bert_config.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "max_seq_length": 8192,
3
+ "do_lower_case": false
4
+ }
checkpoint-1000/special_tokens_map.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "mask_token": {
10
+ "content": "[MASK]",
11
+ "lstrip": true,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "[PAD]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "sep_token": {
24
+ "content": "[SEP]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "unk_token": {
31
+ "content": "[UNK]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ }
37
+ }
checkpoint-1000/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-1000/tokenizer_config.json ADDED
@@ -0,0 +1,945 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "|||IP_ADDRESS|||",
5
+ "lstrip": false,
6
+ "normalized": true,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": false
10
+ },
11
+ "1": {
12
+ "content": "<|padding|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "50254": {
20
+ "content": " ",
21
+ "lstrip": false,
22
+ "normalized": true,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": false
26
+ },
27
+ "50255": {
28
+ "content": " ",
29
+ "lstrip": false,
30
+ "normalized": true,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": false
34
+ },
35
+ "50256": {
36
+ "content": " ",
37
+ "lstrip": false,
38
+ "normalized": true,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": false
42
+ },
43
+ "50257": {
44
+ "content": " ",
45
+ "lstrip": false,
46
+ "normalized": true,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": false
50
+ },
51
+ "50258": {
52
+ "content": " ",
53
+ "lstrip": false,
54
+ "normalized": true,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": false
58
+ },
59
+ "50259": {
60
+ "content": " ",
61
+ "lstrip": false,
62
+ "normalized": true,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": false
66
+ },
67
+ "50260": {
68
+ "content": " ",
69
+ "lstrip": false,
70
+ "normalized": true,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": false
74
+ },
75
+ "50261": {
76
+ "content": " ",
77
+ "lstrip": false,
78
+ "normalized": true,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": false
82
+ },
83
+ "50262": {
84
+ "content": " ",
85
+ "lstrip": false,
86
+ "normalized": true,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": false
90
+ },
91
+ "50263": {
92
+ "content": " ",
93
+ "lstrip": false,
94
+ "normalized": true,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": false
98
+ },
99
+ "50264": {
100
+ "content": " ",
101
+ "lstrip": false,
102
+ "normalized": true,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": false
106
+ },
107
+ "50265": {
108
+ "content": " ",
109
+ "lstrip": false,
110
+ "normalized": true,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": false
114
+ },
115
+ "50266": {
116
+ "content": " ",
117
+ "lstrip": false,
118
+ "normalized": true,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": false
122
+ },
123
+ "50267": {
124
+ "content": " ",
125
+ "lstrip": false,
126
+ "normalized": true,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": false
130
+ },
131
+ "50268": {
132
+ "content": " ",
133
+ "lstrip": false,
134
+ "normalized": true,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": false
138
+ },
139
+ "50269": {
140
+ "content": " ",
141
+ "lstrip": false,
142
+ "normalized": true,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": false
146
+ },
147
+ "50270": {
148
+ "content": " ",
149
+ "lstrip": false,
150
+ "normalized": true,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": false
154
+ },
155
+ "50271": {
156
+ "content": " ",
157
+ "lstrip": false,
158
+ "normalized": true,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": false
162
+ },
163
+ "50272": {
164
+ "content": " ",
165
+ "lstrip": false,
166
+ "normalized": true,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": false
170
+ },
171
+ "50273": {
172
+ "content": " ",
173
+ "lstrip": false,
174
+ "normalized": true,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": false
178
+ },
179
+ "50274": {
180
+ "content": " ",
181
+ "lstrip": false,
182
+ "normalized": true,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": false
186
+ },
187
+ "50275": {
188
+ "content": " ",
189
+ "lstrip": false,
190
+ "normalized": true,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": false
194
+ },
195
+ "50276": {
196
+ "content": " ",
197
+ "lstrip": false,
198
+ "normalized": true,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": false
202
+ },
203
+ "50277": {
204
+ "content": "|||EMAIL_ADDRESS|||",
205
+ "lstrip": false,
206
+ "normalized": true,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": false
210
+ },
211
+ "50278": {
212
+ "content": "|||PHONE_NUMBER|||",
213
+ "lstrip": false,
214
+ "normalized": true,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": false
218
+ },
219
+ "50279": {
220
+ "content": "<|endoftext|>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "50280": {
228
+ "content": "[UNK]",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "50281": {
236
+ "content": "[CLS]",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "50282": {
244
+ "content": "[SEP]",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "50283": {
252
+ "content": "[PAD]",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "50284": {
260
+ "content": "[MASK]",
261
+ "lstrip": true,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "50285": {
268
+ "content": "[unused0]",
269
+ "lstrip": false,
270
+ "normalized": true,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": false
274
+ },
275
+ "50286": {
276
+ "content": "[unused1]",
277
+ "lstrip": false,
278
+ "normalized": true,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": false
282
+ },
283
+ "50287": {
284
+ "content": "[unused2]",
285
+ "lstrip": false,
286
+ "normalized": true,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": false
290
+ },
291
+ "50288": {
292
+ "content": "[unused3]",
293
+ "lstrip": false,
294
+ "normalized": true,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": false
298
+ },
299
+ "50289": {
300
+ "content": "[unused4]",
301
+ "lstrip": false,
302
+ "normalized": true,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": false
306
+ },
307
+ "50290": {
308
+ "content": "[unused5]",
309
+ "lstrip": false,
310
+ "normalized": true,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": false
314
+ },
315
+ "50291": {
316
+ "content": "[unused6]",
317
+ "lstrip": false,
318
+ "normalized": true,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": false
322
+ },
323
+ "50292": {
324
+ "content": "[unused7]",
325
+ "lstrip": false,
326
+ "normalized": true,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": false
330
+ },
331
+ "50293": {
332
+ "content": "[unused8]",
333
+ "lstrip": false,
334
+ "normalized": true,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": false
338
+ },
339
+ "50294": {
340
+ "content": "[unused9]",
341
+ "lstrip": false,
342
+ "normalized": true,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": false
346
+ },
347
+ "50295": {
348
+ "content": "[unused10]",
349
+ "lstrip": false,
350
+ "normalized": true,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": false
354
+ },
355
+ "50296": {
356
+ "content": "[unused11]",
357
+ "lstrip": false,
358
+ "normalized": true,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": false
362
+ },
363
+ "50297": {
364
+ "content": "[unused12]",
365
+ "lstrip": false,
366
+ "normalized": true,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": false
370
+ },
371
+ "50298": {
372
+ "content": "[unused13]",
373
+ "lstrip": false,
374
+ "normalized": true,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": false
378
+ },
379
+ "50299": {
380
+ "content": "[unused14]",
381
+ "lstrip": false,
382
+ "normalized": true,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": false
386
+ },
387
+ "50300": {
388
+ "content": "[unused15]",
389
+ "lstrip": false,
390
+ "normalized": true,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": false
394
+ },
395
+ "50301": {
396
+ "content": "[unused16]",
397
+ "lstrip": false,
398
+ "normalized": true,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": false
402
+ },
403
+ "50302": {
404
+ "content": "[unused17]",
405
+ "lstrip": false,
406
+ "normalized": true,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": false
410
+ },
411
+ "50303": {
412
+ "content": "[unused18]",
413
+ "lstrip": false,
414
+ "normalized": true,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": false
418
+ },
419
+ "50304": {
420
+ "content": "[unused19]",
421
+ "lstrip": false,
422
+ "normalized": true,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": false
426
+ },
427
+ "50305": {
428
+ "content": "[unused20]",
429
+ "lstrip": false,
430
+ "normalized": true,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": false
434
+ },
435
+ "50306": {
436
+ "content": "[unused21]",
437
+ "lstrip": false,
438
+ "normalized": true,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": false
442
+ },
443
+ "50307": {
444
+ "content": "[unused22]",
445
+ "lstrip": false,
446
+ "normalized": true,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": false
450
+ },
451
+ "50308": {
452
+ "content": "[unused23]",
453
+ "lstrip": false,
454
+ "normalized": true,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": false
458
+ },
459
+ "50309": {
460
+ "content": "[unused24]",
461
+ "lstrip": false,
462
+ "normalized": true,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": false
466
+ },
467
+ "50310": {
468
+ "content": "[unused25]",
469
+ "lstrip": false,
470
+ "normalized": true,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": false
474
+ },
475
+ "50311": {
476
+ "content": "[unused26]",
477
+ "lstrip": false,
478
+ "normalized": true,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": false
482
+ },
483
+ "50312": {
484
+ "content": "[unused27]",
485
+ "lstrip": false,
486
+ "normalized": true,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": false
490
+ },
491
+ "50313": {
492
+ "content": "[unused28]",
493
+ "lstrip": false,
494
+ "normalized": true,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": false
498
+ },
499
+ "50314": {
500
+ "content": "[unused29]",
501
+ "lstrip": false,
502
+ "normalized": true,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": false
506
+ },
507
+ "50315": {
508
+ "content": "[unused30]",
509
+ "lstrip": false,
510
+ "normalized": true,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": false
514
+ },
515
+ "50316": {
516
+ "content": "[unused31]",
517
+ "lstrip": false,
518
+ "normalized": true,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": false
522
+ },
523
+ "50317": {
524
+ "content": "[unused32]",
525
+ "lstrip": false,
526
+ "normalized": true,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": false
530
+ },
531
+ "50318": {
532
+ "content": "[unused33]",
533
+ "lstrip": false,
534
+ "normalized": true,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": false
538
+ },
539
+ "50319": {
540
+ "content": "[unused34]",
541
+ "lstrip": false,
542
+ "normalized": true,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": false
546
+ },
547
+ "50320": {
548
+ "content": "[unused35]",
549
+ "lstrip": false,
550
+ "normalized": true,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": false
554
+ },
555
+ "50321": {
556
+ "content": "[unused36]",
557
+ "lstrip": false,
558
+ "normalized": true,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": false
562
+ },
563
+ "50322": {
564
+ "content": "[unused37]",
565
+ "lstrip": false,
566
+ "normalized": true,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": false
570
+ },
571
+ "50323": {
572
+ "content": "[unused38]",
573
+ "lstrip": false,
574
+ "normalized": true,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": false
578
+ },
579
+ "50324": {
580
+ "content": "[unused39]",
581
+ "lstrip": false,
582
+ "normalized": true,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": false
586
+ },
587
+ "50325": {
588
+ "content": "[unused40]",
589
+ "lstrip": false,
590
+ "normalized": true,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": false
594
+ },
595
+ "50326": {
596
+ "content": "[unused41]",
597
+ "lstrip": false,
598
+ "normalized": true,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": false
602
+ },
603
+ "50327": {
604
+ "content": "[unused42]",
605
+ "lstrip": false,
606
+ "normalized": true,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": false
610
+ },
611
+ "50328": {
612
+ "content": "[unused43]",
613
+ "lstrip": false,
614
+ "normalized": true,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": false
618
+ },
619
+ "50329": {
620
+ "content": "[unused44]",
621
+ "lstrip": false,
622
+ "normalized": true,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": false
626
+ },
627
+ "50330": {
628
+ "content": "[unused45]",
629
+ "lstrip": false,
630
+ "normalized": true,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": false
634
+ },
635
+ "50331": {
636
+ "content": "[unused46]",
637
+ "lstrip": false,
638
+ "normalized": true,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": false
642
+ },
643
+ "50332": {
644
+ "content": "[unused47]",
645
+ "lstrip": false,
646
+ "normalized": true,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": false
650
+ },
651
+ "50333": {
652
+ "content": "[unused48]",
653
+ "lstrip": false,
654
+ "normalized": true,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": false
658
+ },
659
+ "50334": {
660
+ "content": "[unused49]",
661
+ "lstrip": false,
662
+ "normalized": true,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": false
666
+ },
667
+ "50335": {
668
+ "content": "[unused50]",
669
+ "lstrip": false,
670
+ "normalized": true,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": false
674
+ },
675
+ "50336": {
676
+ "content": "[unused51]",
677
+ "lstrip": false,
678
+ "normalized": true,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": false
682
+ },
683
+ "50337": {
684
+ "content": "[unused52]",
685
+ "lstrip": false,
686
+ "normalized": true,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": false
690
+ },
691
+ "50338": {
692
+ "content": "[unused53]",
693
+ "lstrip": false,
694
+ "normalized": true,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": false
698
+ },
699
+ "50339": {
700
+ "content": "[unused54]",
701
+ "lstrip": false,
702
+ "normalized": true,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": false
706
+ },
707
+ "50340": {
708
+ "content": "[unused55]",
709
+ "lstrip": false,
710
+ "normalized": true,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": false
714
+ },
715
+ "50341": {
716
+ "content": "[unused56]",
717
+ "lstrip": false,
718
+ "normalized": true,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": false
722
+ },
723
+ "50342": {
724
+ "content": "[unused57]",
725
+ "lstrip": false,
726
+ "normalized": true,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": false
730
+ },
731
+ "50343": {
732
+ "content": "[unused58]",
733
+ "lstrip": false,
734
+ "normalized": true,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": false
738
+ },
739
+ "50344": {
740
+ "content": "[unused59]",
741
+ "lstrip": false,
742
+ "normalized": true,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": false
746
+ },
747
+ "50345": {
748
+ "content": "[unused60]",
749
+ "lstrip": false,
750
+ "normalized": true,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": false
754
+ },
755
+ "50346": {
756
+ "content": "[unused61]",
757
+ "lstrip": false,
758
+ "normalized": true,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": false
762
+ },
763
+ "50347": {
764
+ "content": "[unused62]",
765
+ "lstrip": false,
766
+ "normalized": true,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": false
770
+ },
771
+ "50348": {
772
+ "content": "[unused63]",
773
+ "lstrip": false,
774
+ "normalized": true,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": false
778
+ },
779
+ "50349": {
780
+ "content": "[unused64]",
781
+ "lstrip": false,
782
+ "normalized": true,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": false
786
+ },
787
+ "50350": {
788
+ "content": "[unused65]",
789
+ "lstrip": false,
790
+ "normalized": true,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": false
794
+ },
795
+ "50351": {
796
+ "content": "[unused66]",
797
+ "lstrip": false,
798
+ "normalized": true,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": false
802
+ },
803
+ "50352": {
804
+ "content": "[unused67]",
805
+ "lstrip": false,
806
+ "normalized": true,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": false
810
+ },
811
+ "50353": {
812
+ "content": "[unused68]",
813
+ "lstrip": false,
814
+ "normalized": true,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": false
818
+ },
819
+ "50354": {
820
+ "content": "[unused69]",
821
+ "lstrip": false,
822
+ "normalized": true,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": false
826
+ },
827
+ "50355": {
828
+ "content": "[unused70]",
829
+ "lstrip": false,
830
+ "normalized": true,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": false
834
+ },
835
+ "50356": {
836
+ "content": "[unused71]",
837
+ "lstrip": false,
838
+ "normalized": true,
839
+ "rstrip": false,
840
+ "single_word": false,
841
+ "special": false
842
+ },
843
+ "50357": {
844
+ "content": "[unused72]",
845
+ "lstrip": false,
846
+ "normalized": true,
847
+ "rstrip": false,
848
+ "single_word": false,
849
+ "special": false
850
+ },
851
+ "50358": {
852
+ "content": "[unused73]",
853
+ "lstrip": false,
854
+ "normalized": true,
855
+ "rstrip": false,
856
+ "single_word": false,
857
+ "special": false
858
+ },
859
+ "50359": {
860
+ "content": "[unused74]",
861
+ "lstrip": false,
862
+ "normalized": true,
863
+ "rstrip": false,
864
+ "single_word": false,
865
+ "special": false
866
+ },
867
+ "50360": {
868
+ "content": "[unused75]",
869
+ "lstrip": false,
870
+ "normalized": true,
871
+ "rstrip": false,
872
+ "single_word": false,
873
+ "special": false
874
+ },
875
+ "50361": {
876
+ "content": "[unused76]",
877
+ "lstrip": false,
878
+ "normalized": true,
879
+ "rstrip": false,
880
+ "single_word": false,
881
+ "special": false
882
+ },
883
+ "50362": {
884
+ "content": "[unused77]",
885
+ "lstrip": false,
886
+ "normalized": true,
887
+ "rstrip": false,
888
+ "single_word": false,
889
+ "special": false
890
+ },
891
+ "50363": {
892
+ "content": "[unused78]",
893
+ "lstrip": false,
894
+ "normalized": true,
895
+ "rstrip": false,
896
+ "single_word": false,
897
+ "special": false
898
+ },
899
+ "50364": {
900
+ "content": "[unused79]",
901
+ "lstrip": false,
902
+ "normalized": true,
903
+ "rstrip": false,
904
+ "single_word": false,
905
+ "special": false
906
+ },
907
+ "50365": {
908
+ "content": "[unused80]",
909
+ "lstrip": false,
910
+ "normalized": true,
911
+ "rstrip": false,
912
+ "single_word": false,
913
+ "special": false
914
+ },
915
+ "50366": {
916
+ "content": "[unused81]",
917
+ "lstrip": false,
918
+ "normalized": true,
919
+ "rstrip": false,
920
+ "single_word": false,
921
+ "special": false
922
+ },
923
+ "50367": {
924
+ "content": "[unused82]",
925
+ "lstrip": false,
926
+ "normalized": true,
927
+ "rstrip": false,
928
+ "single_word": false,
929
+ "special": false
930
+ }
931
+ },
932
+ "clean_up_tokenization_spaces": true,
933
+ "cls_token": "[CLS]",
934
+ "extra_special_tokens": {},
935
+ "mask_token": "[MASK]",
936
+ "model_input_names": [
937
+ "input_ids",
938
+ "attention_mask"
939
+ ],
940
+ "model_max_length": 8192,
941
+ "pad_token": "[PAD]",
942
+ "sep_token": "[SEP]",
943
+ "tokenizer_class": "PreTrainedTokenizerFast",
944
+ "unk_token": "[UNK]"
945
+ }
checkpoint-1000/trainer_state.json ADDED
@@ -0,0 +1,1437 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.620745542949757,
5
+ "eval_steps": 100,
6
+ "global_step": 1000,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0,
13
+ "eval_NanoBEIR_mean_cosine_accuracy@1": 0.5733333333333334,
14
+ "eval_NanoBEIR_mean_cosine_accuracy@5": 0.88,
15
+ "eval_NanoBEIR_mean_cosine_map@100": 0.6499700198395969,
16
+ "eval_NanoBEIR_mean_cosine_mrr@10": 0.7025343915343916,
17
+ "eval_NanoBEIR_mean_cosine_ndcg@1": 0.5733333333333334,
18
+ "eval_NanoBEIR_mean_cosine_ndcg@5": 0.6933983700329899,
19
+ "eval_NanoBEIR_mean_cosine_precision@1": 0.5733333333333334,
20
+ "eval_NanoBEIR_mean_cosine_precision@5": 0.21599999999999997,
21
+ "eval_NanoBEIR_mean_cosine_recall@1": 0.44222222222222224,
22
+ "eval_NanoBEIR_mean_cosine_recall@5": 0.8077777777777778,
23
+ "eval_NanoFEVER_cosine_accuracy@1": 0.66,
24
+ "eval_NanoFEVER_cosine_accuracy@5": 0.94,
25
+ "eval_NanoFEVER_cosine_map@100": 0.7456105053991163,
26
+ "eval_NanoFEVER_cosine_mrr@10": 0.7750000000000001,
27
+ "eval_NanoFEVER_cosine_ndcg@1": 0.66,
28
+ "eval_NanoFEVER_cosine_ndcg@5": 0.7909186074531693,
29
+ "eval_NanoFEVER_cosine_precision@1": 0.66,
30
+ "eval_NanoFEVER_cosine_precision@5": 0.19999999999999996,
31
+ "eval_NanoFEVER_cosine_recall@1": 0.6166666666666667,
32
+ "eval_NanoFEVER_cosine_recall@5": 0.9133333333333333,
33
+ "eval_NanoHotpotQA_cosine_accuracy@1": 0.7,
34
+ "eval_NanoHotpotQA_cosine_accuracy@5": 0.92,
35
+ "eval_NanoHotpotQA_cosine_map@100": 0.659131307951428,
36
+ "eval_NanoHotpotQA_cosine_mrr@10": 0.795,
37
+ "eval_NanoHotpotQA_cosine_ndcg@1": 0.7,
38
+ "eval_NanoHotpotQA_cosine_ndcg@5": 0.7005437199248264,
39
+ "eval_NanoHotpotQA_cosine_precision@1": 0.7,
40
+ "eval_NanoHotpotQA_cosine_precision@5": 0.292,
41
+ "eval_NanoHotpotQA_cosine_recall@1": 0.35,
42
+ "eval_NanoHotpotQA_cosine_recall@5": 0.73,
43
+ "eval_NanoMSMARCO_cosine_accuracy@1": 0.36,
44
+ "eval_NanoMSMARCO_cosine_accuracy@5": 0.78,
45
+ "eval_NanoMSMARCO_cosine_map@100": 0.5451682461682461,
46
+ "eval_NanoMSMARCO_cosine_mrr@10": 0.5376031746031745,
47
+ "eval_NanoMSMARCO_cosine_ndcg@1": 0.36,
48
+ "eval_NanoMSMARCO_cosine_ndcg@5": 0.5887327827209738,
49
+ "eval_NanoMSMARCO_cosine_precision@1": 0.36,
50
+ "eval_NanoMSMARCO_cosine_precision@5": 0.156,
51
+ "eval_NanoMSMARCO_cosine_recall@1": 0.36,
52
+ "eval_NanoMSMARCO_cosine_recall@5": 0.78,
53
+ "eval_mldr_loss": 98.74517822265625,
54
+ "eval_mldr_runtime": 49.7129,
55
+ "eval_mldr_samples_per_second": 10.058,
56
+ "eval_mldr_steps_per_second": 0.644,
57
+ "step": 0
58
+ },
59
+ {
60
+ "epoch": 0,
61
+ "eval_squad_loss": 4.950023174285889,
62
+ "eval_squad_runtime": 0.9354,
63
+ "eval_squad_samples_per_second": 51.314,
64
+ "eval_squad_steps_per_second": 3.207,
65
+ "step": 0
66
+ },
67
+ {
68
+ "epoch": 0,
69
+ "eval_narrative_qa_loss": 49.38987731933594,
70
+ "eval_narrative_qa_runtime": 1.0306,
71
+ "eval_narrative_qa_samples_per_second": 290.117,
72
+ "eval_narrative_qa_steps_per_second": 18.436,
73
+ "step": 0
74
+ },
75
+ {
76
+ "epoch": 0.01620745542949757,
77
+ "grad_norm": 1336.0,
78
+ "learning_rate": 9.090909090909091e-06,
79
+ "loss": 86.6132,
80
+ "step": 10
81
+ },
82
+ {
83
+ "epoch": 0.03241491085899514,
84
+ "grad_norm": 828.0,
85
+ "learning_rate": 1.8181818181818182e-05,
86
+ "loss": 83.7595,
87
+ "step": 20
88
+ },
89
+ {
90
+ "epoch": 0.04862236628849271,
91
+ "grad_norm": 388.0,
92
+ "learning_rate": 2.7272727272727273e-05,
93
+ "loss": 65.5413,
94
+ "step": 30
95
+ },
96
+ {
97
+ "epoch": 0.06482982171799027,
98
+ "grad_norm": 320.0,
99
+ "learning_rate": 3.6363636363636364e-05,
100
+ "loss": 40.6319,
101
+ "step": 40
102
+ },
103
+ {
104
+ "epoch": 0.08103727714748785,
105
+ "grad_norm": 296.0,
106
+ "learning_rate": 4.545454545454546e-05,
107
+ "loss": 26.2768,
108
+ "step": 50
109
+ },
110
+ {
111
+ "epoch": 0.09724473257698542,
112
+ "grad_norm": 290.0,
113
+ "learning_rate": 4.9997781212386585e-05,
114
+ "loss": 14.4879,
115
+ "step": 60
116
+ },
117
+ {
118
+ "epoch": 0.11345218800648298,
119
+ "grad_norm": 160.0,
120
+ "learning_rate": 4.9980033274458193e-05,
121
+ "loss": 9.4888,
122
+ "step": 70
123
+ },
124
+ {
125
+ "epoch": 0.12965964343598055,
126
+ "grad_norm": 212.0,
127
+ "learning_rate": 4.994454999929178e-05,
128
+ "loss": 8.831,
129
+ "step": 80
130
+ },
131
+ {
132
+ "epoch": 0.1458670988654781,
133
+ "grad_norm": 109.0,
134
+ "learning_rate": 4.98913565793218e-05,
135
+ "loss": 7.6776,
136
+ "step": 90
137
+ },
138
+ {
139
+ "epoch": 0.1620745542949757,
140
+ "grad_norm": 71.5,
141
+ "learning_rate": 4.982049078084071e-05,
142
+ "loss": 6.4716,
143
+ "step": 100
144
+ },
145
+ {
146
+ "epoch": 0.1620745542949757,
147
+ "eval_NanoBEIR_mean_cosine_accuracy@1": 0.32666666666666666,
148
+ "eval_NanoBEIR_mean_cosine_accuracy@5": 0.6333333333333333,
149
+ "eval_NanoBEIR_mean_cosine_map@100": 0.39934768753390587,
150
+ "eval_NanoBEIR_mean_cosine_mrr@10": 0.4495740740740741,
151
+ "eval_NanoBEIR_mean_cosine_ndcg@1": 0.32666666666666666,
152
+ "eval_NanoBEIR_mean_cosine_ndcg@5": 0.43241374431385005,
153
+ "eval_NanoBEIR_mean_cosine_precision@1": 0.32666666666666666,
154
+ "eval_NanoBEIR_mean_cosine_precision@5": 0.13466666666666668,
155
+ "eval_NanoBEIR_mean_cosine_recall@1": 0.25666666666666665,
156
+ "eval_NanoBEIR_mean_cosine_recall@5": 0.5466666666666667,
157
+ "eval_NanoFEVER_cosine_accuracy@1": 0.24,
158
+ "eval_NanoFEVER_cosine_accuracy@5": 0.66,
159
+ "eval_NanoFEVER_cosine_map@100": 0.3935747452453245,
160
+ "eval_NanoFEVER_cosine_mrr@10": 0.39322222222222225,
161
+ "eval_NanoFEVER_cosine_ndcg@1": 0.24,
162
+ "eval_NanoFEVER_cosine_ndcg@5": 0.4387408055008589,
163
+ "eval_NanoFEVER_cosine_precision@1": 0.24,
164
+ "eval_NanoFEVER_cosine_precision@5": 0.132,
165
+ "eval_NanoFEVER_cosine_recall@1": 0.24,
166
+ "eval_NanoFEVER_cosine_recall@5": 0.63,
167
+ "eval_NanoHotpotQA_cosine_accuracy@1": 0.42,
168
+ "eval_NanoHotpotQA_cosine_accuracy@5": 0.58,
169
+ "eval_NanoHotpotQA_cosine_map@100": 0.3274226457297244,
170
+ "eval_NanoHotpotQA_cosine_mrr@10": 0.4911666666666667,
171
+ "eval_NanoHotpotQA_cosine_ndcg@1": 0.42,
172
+ "eval_NanoHotpotQA_cosine_ndcg@5": 0.35120107956309937,
173
+ "eval_NanoHotpotQA_cosine_precision@1": 0.42,
174
+ "eval_NanoHotpotQA_cosine_precision@5": 0.14,
175
+ "eval_NanoHotpotQA_cosine_recall@1": 0.21,
176
+ "eval_NanoHotpotQA_cosine_recall@5": 0.35,
177
+ "eval_NanoMSMARCO_cosine_accuracy@1": 0.32,
178
+ "eval_NanoMSMARCO_cosine_accuracy@5": 0.66,
179
+ "eval_NanoMSMARCO_cosine_map@100": 0.47704567162666855,
180
+ "eval_NanoMSMARCO_cosine_mrr@10": 0.4643333333333334,
181
+ "eval_NanoMSMARCO_cosine_ndcg@1": 0.32,
182
+ "eval_NanoMSMARCO_cosine_ndcg@5": 0.5072993478775919,
183
+ "eval_NanoMSMARCO_cosine_precision@1": 0.32,
184
+ "eval_NanoMSMARCO_cosine_precision@5": 0.132,
185
+ "eval_NanoMSMARCO_cosine_recall@1": 0.32,
186
+ "eval_NanoMSMARCO_cosine_recall@5": 0.66,
187
+ "eval_mldr_loss": 4.950920581817627,
188
+ "eval_mldr_runtime": 14.3444,
189
+ "eval_mldr_samples_per_second": 34.857,
190
+ "eval_mldr_steps_per_second": 2.231,
191
+ "step": 100
192
+ },
193
+ {
194
+ "epoch": 0.1620745542949757,
195
+ "eval_squad_loss": 2.0146381855010986,
196
+ "eval_squad_runtime": 0.9385,
197
+ "eval_squad_samples_per_second": 51.146,
198
+ "eval_squad_steps_per_second": 3.197,
199
+ "step": 100
200
+ },
201
+ {
202
+ "epoch": 0.1620745542949757,
203
+ "eval_narrative_qa_loss": 4.486134052276611,
204
+ "eval_narrative_qa_runtime": 1.1506,
205
+ "eval_narrative_qa_samples_per_second": 259.856,
206
+ "eval_narrative_qa_steps_per_second": 16.513,
207
+ "step": 100
208
+ },
209
+ {
210
+ "epoch": 0.17828200972447325,
211
+ "grad_norm": 107.5,
212
+ "learning_rate": 4.973200291718561e-05,
213
+ "loss": 6.1959,
214
+ "step": 110
215
+ },
216
+ {
217
+ "epoch": 0.19448946515397084,
218
+ "grad_norm": 50.75,
219
+ "learning_rate": 4.962595581301673e-05,
220
+ "loss": 4.5491,
221
+ "step": 120
222
+ },
223
+ {
224
+ "epoch": 0.2106969205834684,
225
+ "grad_norm": 50.25,
226
+ "learning_rate": 4.95024247597132e-05,
227
+ "loss": 4.0871,
228
+ "step": 130
229
+ },
230
+ {
231
+ "epoch": 0.22690437601296595,
232
+ "grad_norm": 53.25,
233
+ "learning_rate": 4.936149746191758e-05,
234
+ "loss": 3.0861,
235
+ "step": 140
236
+ },
237
+ {
238
+ "epoch": 0.24311183144246354,
239
+ "grad_norm": 25.5,
240
+ "learning_rate": 4.920327397526731e-05,
241
+ "loss": 2.7792,
242
+ "step": 150
243
+ },
244
+ {
245
+ "epoch": 0.2593192868719611,
246
+ "grad_norm": 122.0,
247
+ "learning_rate": 4.9027866635357136e-05,
248
+ "loss": 2.2107,
249
+ "step": 160
250
+ },
251
+ {
252
+ "epoch": 0.2755267423014587,
253
+ "grad_norm": 410.0,
254
+ "learning_rate": 4.883539997798303e-05,
255
+ "loss": 1.6997,
256
+ "step": 170
257
+ },
258
+ {
259
+ "epoch": 0.2917341977309562,
260
+ "grad_norm": 66.0,
261
+ "learning_rate": 4.8626010650724204e-05,
262
+ "loss": 1.4911,
263
+ "step": 180
264
+ },
265
+ {
266
+ "epoch": 0.3079416531604538,
267
+ "grad_norm": 1072.0,
268
+ "learning_rate": 4.8399847315926e-05,
269
+ "loss": 1.6304,
270
+ "step": 190
271
+ },
272
+ {
273
+ "epoch": 0.3241491085899514,
274
+ "grad_norm": 16.5,
275
+ "learning_rate": 4.815707054515248e-05,
276
+ "loss": 1.5042,
277
+ "step": 200
278
+ },
279
+ {
280
+ "epoch": 0.3241491085899514,
281
+ "eval_NanoBEIR_mean_cosine_accuracy@1": 0.24666666666666667,
282
+ "eval_NanoBEIR_mean_cosine_accuracy@5": 0.4533333333333333,
283
+ "eval_NanoBEIR_mean_cosine_map@100": 0.2917657022707883,
284
+ "eval_NanoBEIR_mean_cosine_mrr@10": 0.3391984126984127,
285
+ "eval_NanoBEIR_mean_cosine_ndcg@1": 0.24666666666666667,
286
+ "eval_NanoBEIR_mean_cosine_ndcg@5": 0.3047832475255773,
287
+ "eval_NanoBEIR_mean_cosine_precision@1": 0.24666666666666667,
288
+ "eval_NanoBEIR_mean_cosine_precision@5": 0.09466666666666669,
289
+ "eval_NanoBEIR_mean_cosine_recall@1": 0.18333333333333335,
290
+ "eval_NanoBEIR_mean_cosine_recall@5": 0.37333333333333335,
291
+ "eval_NanoFEVER_cosine_accuracy@1": 0.08,
292
+ "eval_NanoFEVER_cosine_accuracy@5": 0.26,
293
+ "eval_NanoFEVER_cosine_map@100": 0.15831046306304816,
294
+ "eval_NanoFEVER_cosine_mrr@10": 0.1541904761904762,
295
+ "eval_NanoFEVER_cosine_ndcg@1": 0.08,
296
+ "eval_NanoFEVER_cosine_ndcg@5": 0.15530091408199076,
297
+ "eval_NanoFEVER_cosine_precision@1": 0.08,
298
+ "eval_NanoFEVER_cosine_precision@5": 0.052000000000000005,
299
+ "eval_NanoFEVER_cosine_recall@1": 0.07,
300
+ "eval_NanoFEVER_cosine_recall@5": 0.24,
301
+ "eval_NanoHotpotQA_cosine_accuracy@1": 0.36,
302
+ "eval_NanoHotpotQA_cosine_accuracy@5": 0.5,
303
+ "eval_NanoHotpotQA_cosine_map@100": 0.2657203181494037,
304
+ "eval_NanoHotpotQA_cosine_mrr@10": 0.4257142857142857,
305
+ "eval_NanoHotpotQA_cosine_ndcg@1": 0.36,
306
+ "eval_NanoHotpotQA_cosine_ndcg@5": 0.2891308855457201,
307
+ "eval_NanoHotpotQA_cosine_precision@1": 0.36,
308
+ "eval_NanoHotpotQA_cosine_precision@5": 0.11200000000000003,
309
+ "eval_NanoHotpotQA_cosine_recall@1": 0.18,
310
+ "eval_NanoHotpotQA_cosine_recall@5": 0.28,
311
+ "eval_NanoMSMARCO_cosine_accuracy@1": 0.3,
312
+ "eval_NanoMSMARCO_cosine_accuracy@5": 0.6,
313
+ "eval_NanoMSMARCO_cosine_map@100": 0.45126632559991314,
314
+ "eval_NanoMSMARCO_cosine_mrr@10": 0.4376904761904762,
315
+ "eval_NanoMSMARCO_cosine_ndcg@1": 0.3,
316
+ "eval_NanoMSMARCO_cosine_ndcg@5": 0.46991794294902106,
317
+ "eval_NanoMSMARCO_cosine_precision@1": 0.3,
318
+ "eval_NanoMSMARCO_cosine_precision@5": 0.12000000000000002,
319
+ "eval_NanoMSMARCO_cosine_recall@1": 0.3,
320
+ "eval_NanoMSMARCO_cosine_recall@5": 0.6,
321
+ "eval_mldr_loss": 1.3893917798995972,
322
+ "eval_mldr_runtime": 14.4056,
323
+ "eval_mldr_samples_per_second": 34.709,
324
+ "eval_mldr_steps_per_second": 2.221,
325
+ "step": 200
326
+ },
327
+ {
328
+ "epoch": 0.3241491085899514,
329
+ "eval_squad_loss": 0.7646868824958801,
330
+ "eval_squad_runtime": 1.072,
331
+ "eval_squad_samples_per_second": 44.776,
332
+ "eval_squad_steps_per_second": 2.799,
333
+ "step": 200
334
+ },
335
+ {
336
+ "epoch": 0.3241491085899514,
337
+ "eval_narrative_qa_loss": 2.59745192527771,
338
+ "eval_narrative_qa_runtime": 1.1589,
339
+ "eval_narrative_qa_samples_per_second": 257.994,
340
+ "eval_narrative_qa_steps_per_second": 16.394,
341
+ "step": 200
342
+ },
343
+ {
344
+ "epoch": 0.34035656401944897,
345
+ "grad_norm": 35.0,
346
+ "learning_rate": 4.7897852705183785e-05,
347
+ "loss": 1.6009,
348
+ "step": 210
349
+ },
350
+ {
351
+ "epoch": 0.3565640194489465,
352
+ "grad_norm": 1352.0,
353
+ "learning_rate": 4.7622377835639064e-05,
354
+ "loss": 1.5156,
355
+ "step": 220
356
+ },
357
+ {
358
+ "epoch": 0.3727714748784441,
359
+ "grad_norm": 704.0,
360
+ "learning_rate": 4.73308415183119e-05,
361
+ "loss": 1.5305,
362
+ "step": 230
363
+ },
364
+ {
365
+ "epoch": 0.3889789303079417,
366
+ "grad_norm": 824.0,
367
+ "learning_rate": 4.702345073831109e-05,
368
+ "loss": 1.6842,
369
+ "step": 240
370
+ },
371
+ {
372
+ "epoch": 0.4051863857374392,
373
+ "grad_norm": 21760.0,
374
+ "learning_rate": 4.6700423737105236e-05,
375
+ "loss": 1.2207,
376
+ "step": 250
377
+ },
378
+ {
379
+ "epoch": 0.4213938411669368,
380
+ "grad_norm": 3040.0,
381
+ "learning_rate": 4.63619898575755e-05,
382
+ "loss": 1.2634,
383
+ "step": 260
384
+ },
385
+ {
386
+ "epoch": 0.4376012965964344,
387
+ "grad_norm": 46.5,
388
+ "learning_rate": 4.600838938118672e-05,
389
+ "loss": 1.3175,
390
+ "step": 270
391
+ },
392
+ {
393
+ "epoch": 0.4538087520259319,
394
+ "grad_norm": 6112.0,
395
+ "learning_rate": 4.563987335739216e-05,
396
+ "loss": 1.3107,
397
+ "step": 280
398
+ },
399
+ {
400
+ "epoch": 0.4700162074554295,
401
+ "grad_norm": 2256.0,
402
+ "learning_rate": 4.525670342539332e-05,
403
+ "loss": 1.3163,
404
+ "step": 290
405
+ },
406
+ {
407
+ "epoch": 0.4862236628849271,
408
+ "grad_norm": 860.0,
409
+ "learning_rate": 4.485915162838122e-05,
410
+ "loss": 1.3703,
411
+ "step": 300
412
+ },
413
+ {
414
+ "epoch": 0.4862236628849271,
415
+ "eval_NanoBEIR_mean_cosine_accuracy@1": 0.18666666666666668,
416
+ "eval_NanoBEIR_mean_cosine_accuracy@5": 0.37333333333333335,
417
+ "eval_NanoBEIR_mean_cosine_map@100": 0.24055436231400043,
418
+ "eval_NanoBEIR_mean_cosine_mrr@10": 0.26788624338624334,
419
+ "eval_NanoBEIR_mean_cosine_ndcg@1": 0.18666666666666668,
420
+ "eval_NanoBEIR_mean_cosine_ndcg@5": 0.24938490224868604,
421
+ "eval_NanoBEIR_mean_cosine_precision@1": 0.18666666666666668,
422
+ "eval_NanoBEIR_mean_cosine_precision@5": 0.07733333333333335,
423
+ "eval_NanoBEIR_mean_cosine_recall@1": 0.15,
424
+ "eval_NanoBEIR_mean_cosine_recall@5": 0.31666666666666665,
425
+ "eval_NanoFEVER_cosine_accuracy@1": 0.06,
426
+ "eval_NanoFEVER_cosine_accuracy@5": 0.18,
427
+ "eval_NanoFEVER_cosine_map@100": 0.11320690658806287,
428
+ "eval_NanoFEVER_cosine_mrr@10": 0.11538888888888887,
429
+ "eval_NanoFEVER_cosine_ndcg@1": 0.06,
430
+ "eval_NanoFEVER_cosine_ndcg@5": 0.11246425246579403,
431
+ "eval_NanoFEVER_cosine_precision@1": 0.06,
432
+ "eval_NanoFEVER_cosine_precision@5": 0.036000000000000004,
433
+ "eval_NanoFEVER_cosine_recall@1": 0.05,
434
+ "eval_NanoFEVER_cosine_recall@5": 0.17,
435
+ "eval_NanoHotpotQA_cosine_accuracy@1": 0.2,
436
+ "eval_NanoHotpotQA_cosine_accuracy@5": 0.36,
437
+ "eval_NanoHotpotQA_cosine_map@100": 0.17264044237203358,
438
+ "eval_NanoHotpotQA_cosine_mrr@10": 0.26374603174603173,
439
+ "eval_NanoHotpotQA_cosine_ndcg@1": 0.2,
440
+ "eval_NanoHotpotQA_cosine_ndcg@5": 0.18589124040083965,
441
+ "eval_NanoHotpotQA_cosine_precision@1": 0.2,
442
+ "eval_NanoHotpotQA_cosine_precision@5": 0.08,
443
+ "eval_NanoHotpotQA_cosine_recall@1": 0.1,
444
+ "eval_NanoHotpotQA_cosine_recall@5": 0.2,
445
+ "eval_NanoMSMARCO_cosine_accuracy@1": 0.3,
446
+ "eval_NanoMSMARCO_cosine_accuracy@5": 0.58,
447
+ "eval_NanoMSMARCO_cosine_map@100": 0.4358157379819049,
448
+ "eval_NanoMSMARCO_cosine_mrr@10": 0.42452380952380947,
449
+ "eval_NanoMSMARCO_cosine_ndcg@1": 0.3,
450
+ "eval_NanoMSMARCO_cosine_ndcg@5": 0.44979921387942445,
451
+ "eval_NanoMSMARCO_cosine_precision@1": 0.3,
452
+ "eval_NanoMSMARCO_cosine_precision@5": 0.11600000000000002,
453
+ "eval_NanoMSMARCO_cosine_recall@1": 0.3,
454
+ "eval_NanoMSMARCO_cosine_recall@5": 0.58,
455
+ "eval_mldr_loss": 1.218342900276184,
456
+ "eval_mldr_runtime": 14.4679,
457
+ "eval_mldr_samples_per_second": 34.559,
458
+ "eval_mldr_steps_per_second": 2.212,
459
+ "step": 300
460
+ },
461
+ {
462
+ "epoch": 0.4862236628849271,
463
+ "eval_squad_loss": 1.0243560075759888,
464
+ "eval_squad_runtime": 0.9647,
465
+ "eval_squad_samples_per_second": 49.755,
466
+ "eval_squad_steps_per_second": 3.11,
467
+ "step": 300
468
+ },
469
+ {
470
+ "epoch": 0.4862236628849271,
471
+ "eval_narrative_qa_loss": 2.635084629058838,
472
+ "eval_narrative_qa_runtime": 1.1616,
473
+ "eval_narrative_qa_samples_per_second": 257.409,
474
+ "eval_narrative_qa_steps_per_second": 16.357,
475
+ "step": 300
476
+ },
477
+ {
478
+ "epoch": 0.5024311183144247,
479
+ "grad_norm": 39.25,
480
+ "learning_rate": 4.444750022039099e-05,
481
+ "loss": 1.2901,
482
+ "step": 310
483
+ },
484
+ {
485
+ "epoch": 0.5186385737439222,
486
+ "grad_norm": 260.0,
487
+ "learning_rate": 4.4022041465907036e-05,
488
+ "loss": 1.245,
489
+ "step": 320
490
+ },
491
+ {
492
+ "epoch": 0.5348460291734197,
493
+ "grad_norm": 2192.0,
494
+ "learning_rate": 4.358307743236092e-05,
495
+ "loss": 1.1749,
496
+ "step": 330
497
+ },
498
+ {
499
+ "epoch": 0.5510534846029174,
500
+ "grad_norm": 1064.0,
501
+ "learning_rate": 4.3130919775669374e-05,
502
+ "loss": 1.0522,
503
+ "step": 340
504
+ },
505
+ {
506
+ "epoch": 0.5672609400324149,
507
+ "grad_norm": 1120.0,
508
+ "learning_rate": 4.2665889518964684e-05,
509
+ "loss": 1.1319,
510
+ "step": 350
511
+ },
512
+ {
513
+ "epoch": 0.5834683954619124,
514
+ "grad_norm": 1552.0,
515
+ "learning_rate": 4.2188316824674504e-05,
516
+ "loss": 1.1986,
517
+ "step": 360
518
+ },
519
+ {
520
+ "epoch": 0.5996758508914101,
521
+ "grad_norm": 133.0,
522
+ "learning_rate": 4.169854076011292e-05,
523
+ "loss": 1.3508,
524
+ "step": 370
525
+ },
526
+ {
527
+ "epoch": 0.6158833063209076,
528
+ "grad_norm": 5408.0,
529
+ "learning_rate": 4.119690905674937e-05,
530
+ "loss": 1.3465,
531
+ "step": 380
532
+ },
533
+ {
534
+ "epoch": 0.6320907617504052,
535
+ "grad_norm": 1624.0,
536
+ "learning_rate": 4.068377786332593e-05,
537
+ "loss": 1.3062,
538
+ "step": 390
539
+ },
540
+ {
541
+ "epoch": 0.6482982171799028,
542
+ "grad_norm": 1192.0,
543
+ "learning_rate": 4.0159511492998746e-05,
544
+ "loss": 0.9974,
545
+ "step": 400
546
+ },
547
+ {
548
+ "epoch": 0.6482982171799028,
549
+ "eval_NanoBEIR_mean_cosine_accuracy@1": 0.20000000000000004,
550
+ "eval_NanoBEIR_mean_cosine_accuracy@5": 0.39333333333333337,
551
+ "eval_NanoBEIR_mean_cosine_map@100": 0.25566257669608067,
552
+ "eval_NanoBEIR_mean_cosine_mrr@10": 0.2828835978835979,
553
+ "eval_NanoBEIR_mean_cosine_ndcg@1": 0.20000000000000004,
554
+ "eval_NanoBEIR_mean_cosine_ndcg@5": 0.2711361604281084,
555
+ "eval_NanoBEIR_mean_cosine_precision@1": 0.20000000000000004,
556
+ "eval_NanoBEIR_mean_cosine_precision@5": 0.08266666666666668,
557
+ "eval_NanoBEIR_mean_cosine_recall@1": 0.16333333333333333,
558
+ "eval_NanoBEIR_mean_cosine_recall@5": 0.3433333333333333,
559
+ "eval_NanoFEVER_cosine_accuracy@1": 0.08,
560
+ "eval_NanoFEVER_cosine_accuracy@5": 0.2,
561
+ "eval_NanoFEVER_cosine_map@100": 0.12628338770667222,
562
+ "eval_NanoFEVER_cosine_mrr@10": 0.1275,
563
+ "eval_NanoFEVER_cosine_ndcg@1": 0.08,
564
+ "eval_NanoFEVER_cosine_ndcg@5": 0.1285946755597121,
565
+ "eval_NanoFEVER_cosine_precision@1": 0.08,
566
+ "eval_NanoFEVER_cosine_precision@5": 0.04,
567
+ "eval_NanoFEVER_cosine_recall@1": 0.07,
568
+ "eval_NanoFEVER_cosine_recall@5": 0.18,
569
+ "eval_NanoHotpotQA_cosine_accuracy@1": 0.2,
570
+ "eval_NanoHotpotQA_cosine_accuracy@5": 0.32,
571
+ "eval_NanoHotpotQA_cosine_map@100": 0.17161850356661693,
572
+ "eval_NanoHotpotQA_cosine_mrr@10": 0.26146031746031745,
573
+ "eval_NanoHotpotQA_cosine_ndcg@1": 0.2,
574
+ "eval_NanoHotpotQA_cosine_ndcg@5": 0.18168469434151963,
575
+ "eval_NanoHotpotQA_cosine_precision@1": 0.2,
576
+ "eval_NanoHotpotQA_cosine_precision@5": 0.07600000000000001,
577
+ "eval_NanoHotpotQA_cosine_recall@1": 0.1,
578
+ "eval_NanoHotpotQA_cosine_recall@5": 0.19,
579
+ "eval_NanoMSMARCO_cosine_accuracy@1": 0.32,
580
+ "eval_NanoMSMARCO_cosine_accuracy@5": 0.66,
581
+ "eval_NanoMSMARCO_cosine_map@100": 0.4690858388149529,
582
+ "eval_NanoMSMARCO_cosine_mrr@10": 0.45969047619047615,
583
+ "eval_NanoMSMARCO_cosine_ndcg@1": 0.32,
584
+ "eval_NanoMSMARCO_cosine_ndcg@5": 0.5031291113830936,
585
+ "eval_NanoMSMARCO_cosine_precision@1": 0.32,
586
+ "eval_NanoMSMARCO_cosine_precision@5": 0.132,
587
+ "eval_NanoMSMARCO_cosine_recall@1": 0.32,
588
+ "eval_NanoMSMARCO_cosine_recall@5": 0.66,
589
+ "eval_mldr_loss": 1.7250500917434692,
590
+ "eval_mldr_runtime": 14.4371,
591
+ "eval_mldr_samples_per_second": 34.633,
592
+ "eval_mldr_steps_per_second": 2.217,
593
+ "step": 400
594
+ },
595
+ {
596
+ "epoch": 0.6482982171799028,
597
+ "eval_squad_loss": 0.8224272131919861,
598
+ "eval_squad_runtime": 0.9831,
599
+ "eval_squad_samples_per_second": 48.823,
600
+ "eval_squad_steps_per_second": 3.051,
601
+ "step": 400
602
+ },
603
+ {
604
+ "epoch": 0.6482982171799028,
605
+ "eval_narrative_qa_loss": 2.191936492919922,
606
+ "eval_narrative_qa_runtime": 1.1776,
607
+ "eval_narrative_qa_samples_per_second": 253.914,
608
+ "eval_narrative_qa_steps_per_second": 16.135,
609
+ "step": 400
610
+ },
611
+ {
612
+ "epoch": 0.6645056726094003,
613
+ "grad_norm": 796.0,
614
+ "learning_rate": 3.962448216468275e-05,
615
+ "loss": 3.2988,
616
+ "step": 410
617
+ },
618
+ {
619
+ "epoch": 0.6807131280388979,
620
+ "grad_norm": 9216.0,
621
+ "learning_rate": 3.9079069738783484e-05,
622
+ "loss": 1.3305,
623
+ "step": 420
624
+ },
625
+ {
626
+ "epoch": 0.6969205834683955,
627
+ "grad_norm": 227.0,
628
+ "learning_rate": 3.852366144750358e-05,
629
+ "loss": 1.2771,
630
+ "step": 430
631
+ },
632
+ {
633
+ "epoch": 0.713128038897893,
634
+ "grad_norm": 1456.0,
635
+ "learning_rate": 3.7958651619915495e-05,
636
+ "loss": 1.0724,
637
+ "step": 440
638
+ },
639
+ {
640
+ "epoch": 0.7293354943273906,
641
+ "grad_norm": 704.0,
642
+ "learning_rate": 3.738444140199549e-05,
643
+ "loss": 1.2473,
644
+ "step": 450
645
+ },
646
+ {
647
+ "epoch": 0.7455429497568882,
648
+ "grad_norm": 4608.0,
649
+ "learning_rate": 3.680143847181783e-05,
650
+ "loss": 1.4045,
651
+ "step": 460
652
+ },
653
+ {
654
+ "epoch": 0.7617504051863857,
655
+ "grad_norm": 8384.0,
656
+ "learning_rate": 3.621005675011127e-05,
657
+ "loss": 1.6167,
658
+ "step": 470
659
+ },
660
+ {
661
+ "epoch": 0.7779578606158833,
662
+ "grad_norm": 10752.0,
663
+ "learning_rate": 3.5610716106383426e-05,
664
+ "loss": 1.427,
665
+ "step": 480
666
+ },
667
+ {
668
+ "epoch": 0.7941653160453809,
669
+ "grad_norm": 32512.0,
670
+ "learning_rate": 3.500384206082155e-05,
671
+ "loss": 1.256,
672
+ "step": 490
673
+ },
674
+ {
675
+ "epoch": 0.8103727714748784,
676
+ "grad_norm": 2080.0,
677
+ "learning_rate": 3.438986548218155e-05,
678
+ "loss": 1.7336,
679
+ "step": 500
680
+ },
681
+ {
682
+ "epoch": 0.8103727714748784,
683
+ "eval_NanoBEIR_mean_cosine_accuracy@1": 0.22666666666666668,
684
+ "eval_NanoBEIR_mean_cosine_accuracy@5": 0.35333333333333333,
685
+ "eval_NanoBEIR_mean_cosine_map@100": 0.25285734426656203,
686
+ "eval_NanoBEIR_mean_cosine_mrr@10": 0.28679100529100526,
687
+ "eval_NanoBEIR_mean_cosine_ndcg@1": 0.22666666666666668,
688
+ "eval_NanoBEIR_mean_cosine_ndcg@5": 0.26096692405722594,
689
+ "eval_NanoBEIR_mean_cosine_precision@1": 0.22666666666666668,
690
+ "eval_NanoBEIR_mean_cosine_precision@5": 0.07600000000000001,
691
+ "eval_NanoBEIR_mean_cosine_recall@1": 0.17666666666666667,
692
+ "eval_NanoBEIR_mean_cosine_recall@5": 0.31,
693
+ "eval_NanoFEVER_cosine_accuracy@1": 0.08,
694
+ "eval_NanoFEVER_cosine_accuracy@5": 0.18,
695
+ "eval_NanoFEVER_cosine_map@100": 0.11514089868666741,
696
+ "eval_NanoFEVER_cosine_mrr@10": 0.11641269841269843,
697
+ "eval_NanoFEVER_cosine_ndcg@1": 0.08,
698
+ "eval_NanoFEVER_cosine_ndcg@5": 0.11458961164975079,
699
+ "eval_NanoFEVER_cosine_precision@1": 0.08,
700
+ "eval_NanoFEVER_cosine_precision@5": 0.036000000000000004,
701
+ "eval_NanoFEVER_cosine_recall@1": 0.07,
702
+ "eval_NanoFEVER_cosine_recall@5": 0.16,
703
+ "eval_NanoHotpotQA_cosine_accuracy@1": 0.28,
704
+ "eval_NanoHotpotQA_cosine_accuracy@5": 0.3,
705
+ "eval_NanoHotpotQA_cosine_map@100": 0.1921273663105645,
706
+ "eval_NanoHotpotQA_cosine_mrr@10": 0.3077380952380952,
707
+ "eval_NanoHotpotQA_cosine_ndcg@1": 0.28,
708
+ "eval_NanoHotpotQA_cosine_ndcg@5": 0.202243938877232,
709
+ "eval_NanoHotpotQA_cosine_precision@1": 0.28,
710
+ "eval_NanoHotpotQA_cosine_precision@5": 0.07600000000000001,
711
+ "eval_NanoHotpotQA_cosine_recall@1": 0.14,
712
+ "eval_NanoHotpotQA_cosine_recall@5": 0.19,
713
+ "eval_NanoMSMARCO_cosine_accuracy@1": 0.32,
714
+ "eval_NanoMSMARCO_cosine_accuracy@5": 0.58,
715
+ "eval_NanoMSMARCO_cosine_map@100": 0.4513037678024542,
716
+ "eval_NanoMSMARCO_cosine_mrr@10": 0.4362222222222223,
717
+ "eval_NanoMSMARCO_cosine_ndcg@1": 0.32,
718
+ "eval_NanoMSMARCO_cosine_ndcg@5": 0.4660672216446949,
719
+ "eval_NanoMSMARCO_cosine_precision@1": 0.32,
720
+ "eval_NanoMSMARCO_cosine_precision@5": 0.11600000000000002,
721
+ "eval_NanoMSMARCO_cosine_recall@1": 0.32,
722
+ "eval_NanoMSMARCO_cosine_recall@5": 0.58,
723
+ "eval_mldr_loss": 1.2118109464645386,
724
+ "eval_mldr_runtime": 14.4727,
725
+ "eval_mldr_samples_per_second": 34.548,
726
+ "eval_mldr_steps_per_second": 2.211,
727
+ "step": 500
728
+ },
729
+ {
730
+ "epoch": 0.8103727714748784,
731
+ "eval_squad_loss": 0.669793426990509,
732
+ "eval_squad_runtime": 0.9528,
733
+ "eval_squad_samples_per_second": 50.377,
734
+ "eval_squad_steps_per_second": 3.149,
735
+ "step": 500
736
+ },
737
+ {
738
+ "epoch": 0.8103727714748784,
739
+ "eval_narrative_qa_loss": 2.0540804862976074,
740
+ "eval_narrative_qa_runtime": 1.1722,
741
+ "eval_narrative_qa_samples_per_second": 255.077,
742
+ "eval_narrative_qa_steps_per_second": 16.209,
743
+ "step": 500
744
+ },
745
+ {
746
+ "epoch": 0.826580226904376,
747
+ "grad_norm": 5792.0,
748
+ "learning_rate": 3.3769222281879495e-05,
749
+ "loss": 0.9241,
750
+ "step": 510
751
+ },
752
+ {
753
+ "epoch": 0.8427876823338736,
754
+ "grad_norm": 1080.0,
755
+ "learning_rate": 3.314235310450306e-05,
756
+ "loss": 1.2186,
757
+ "step": 520
758
+ },
759
+ {
760
+ "epoch": 0.8589951377633711,
761
+ "grad_norm": 1264.0,
762
+ "learning_rate": 3.250970301496237e-05,
763
+ "loss": 1.3873,
764
+ "step": 530
765
+ },
766
+ {
767
+ "epoch": 0.8752025931928687,
768
+ "grad_norm": 308.0,
769
+ "learning_rate": 3.187172118250266e-05,
770
+ "loss": 1.299,
771
+ "step": 540
772
+ },
773
+ {
774
+ "epoch": 0.8914100486223663,
775
+ "grad_norm": 5568.0,
776
+ "learning_rate": 3.122886056180284e-05,
777
+ "loss": 1.4101,
778
+ "step": 550
779
+ },
780
+ {
781
+ "epoch": 0.9076175040518638,
782
+ "grad_norm": 1480.0,
783
+ "learning_rate": 3.0581577571386426e-05,
784
+ "loss": 1.047,
785
+ "step": 560
786
+ },
787
+ {
788
+ "epoch": 0.9238249594813615,
789
+ "grad_norm": 34.0,
790
+ "learning_rate": 2.9930331769573365e-05,
791
+ "loss": 1.1558,
792
+ "step": 570
793
+ },
794
+ {
795
+ "epoch": 0.940032414910859,
796
+ "grad_norm": 4640.0,
797
+ "learning_rate": 2.9275585528202516e-05,
798
+ "loss": 1.1769,
799
+ "step": 580
800
+ },
801
+ {
802
+ "epoch": 0.9562398703403565,
803
+ "grad_norm": 191.0,
804
+ "learning_rate": 2.8617803704356672e-05,
805
+ "loss": 1.1054,
806
+ "step": 590
807
+ },
808
+ {
809
+ "epoch": 0.9724473257698542,
810
+ "grad_norm": 167.0,
811
+ "learning_rate": 2.7957453310323073e-05,
812
+ "loss": 3.6745,
813
+ "step": 600
814
+ },
815
+ {
816
+ "epoch": 0.9724473257698542,
817
+ "eval_NanoBEIR_mean_cosine_accuracy@1": 0.20666666666666667,
818
+ "eval_NanoBEIR_mean_cosine_accuracy@5": 0.36000000000000004,
819
+ "eval_NanoBEIR_mean_cosine_map@100": 0.24725005259175806,
820
+ "eval_NanoBEIR_mean_cosine_mrr@10": 0.2764206349206349,
821
+ "eval_NanoBEIR_mean_cosine_ndcg@1": 0.20666666666666667,
822
+ "eval_NanoBEIR_mean_cosine_ndcg@5": 0.2557813556128824,
823
+ "eval_NanoBEIR_mean_cosine_precision@1": 0.20666666666666667,
824
+ "eval_NanoBEIR_mean_cosine_precision@5": 0.076,
825
+ "eval_NanoBEIR_mean_cosine_recall@1": 0.16666666666666666,
826
+ "eval_NanoBEIR_mean_cosine_recall@5": 0.31,
827
+ "eval_NanoFEVER_cosine_accuracy@1": 0.1,
828
+ "eval_NanoFEVER_cosine_accuracy@5": 0.12,
829
+ "eval_NanoFEVER_cosine_map@100": 0.12500495211409104,
830
+ "eval_NanoFEVER_cosine_mrr@10": 0.12576984126984128,
831
+ "eval_NanoFEVER_cosine_ndcg@1": 0.1,
832
+ "eval_NanoFEVER_cosine_ndcg@5": 0.10488153892673832,
833
+ "eval_NanoFEVER_cosine_precision@1": 0.1,
834
+ "eval_NanoFEVER_cosine_precision@5": 0.024000000000000004,
835
+ "eval_NanoFEVER_cosine_recall@1": 0.09,
836
+ "eval_NanoFEVER_cosine_recall@5": 0.11,
837
+ "eval_NanoHotpotQA_cosine_accuracy@1": 0.22,
838
+ "eval_NanoHotpotQA_cosine_accuracy@5": 0.34,
839
+ "eval_NanoHotpotQA_cosine_map@100": 0.17072760263191902,
840
+ "eval_NanoHotpotQA_cosine_mrr@10": 0.2686904761904762,
841
+ "eval_NanoHotpotQA_cosine_ndcg@1": 0.22,
842
+ "eval_NanoHotpotQA_cosine_ndcg@5": 0.19019906156669042,
843
+ "eval_NanoHotpotQA_cosine_precision@1": 0.22,
844
+ "eval_NanoHotpotQA_cosine_precision@5": 0.08,
845
+ "eval_NanoHotpotQA_cosine_recall@1": 0.11,
846
+ "eval_NanoHotpotQA_cosine_recall@5": 0.2,
847
+ "eval_NanoMSMARCO_cosine_accuracy@1": 0.3,
848
+ "eval_NanoMSMARCO_cosine_accuracy@5": 0.62,
849
+ "eval_NanoMSMARCO_cosine_map@100": 0.44601760302926413,
850
+ "eval_NanoMSMARCO_cosine_mrr@10": 0.4348015873015873,
851
+ "eval_NanoMSMARCO_cosine_ndcg@1": 0.3,
852
+ "eval_NanoMSMARCO_cosine_ndcg@5": 0.4722634663452185,
853
+ "eval_NanoMSMARCO_cosine_precision@1": 0.3,
854
+ "eval_NanoMSMARCO_cosine_precision@5": 0.124,
855
+ "eval_NanoMSMARCO_cosine_recall@1": 0.3,
856
+ "eval_NanoMSMARCO_cosine_recall@5": 0.62,
857
+ "eval_mldr_loss": 1.1025381088256836,
858
+ "eval_mldr_runtime": 14.5605,
859
+ "eval_mldr_samples_per_second": 34.339,
860
+ "eval_mldr_steps_per_second": 2.198,
861
+ "step": 600
862
+ },
863
+ {
864
+ "epoch": 0.9724473257698542,
865
+ "eval_squad_loss": 0.7168652415275574,
866
+ "eval_squad_runtime": 0.8907,
867
+ "eval_squad_samples_per_second": 53.891,
868
+ "eval_squad_steps_per_second": 3.368,
869
+ "step": 600
870
+ },
871
+ {
872
+ "epoch": 0.9724473257698542,
873
+ "eval_narrative_qa_loss": 1.757150411605835,
874
+ "eval_narrative_qa_runtime": 1.1289,
875
+ "eval_narrative_qa_samples_per_second": 264.853,
876
+ "eval_narrative_qa_steps_per_second": 16.83,
877
+ "step": 600
878
+ },
879
+ {
880
+ "epoch": 0.9886547811993517,
881
+ "grad_norm": 414.0,
882
+ "learning_rate": 2.7295003182023793e-05,
883
+ "loss": 1.2095,
884
+ "step": 610
885
+ },
886
+ {
887
+ "epoch": 1.0048622366288493,
888
+ "grad_norm": 760.0,
889
+ "learning_rate": 2.663092364615134e-05,
890
+ "loss": 1.0888,
891
+ "step": 620
892
+ },
893
+ {
894
+ "epoch": 1.0210696920583469,
895
+ "grad_norm": 884.0,
896
+ "learning_rate": 2.596568618624588e-05,
897
+ "loss": 1.1728,
898
+ "step": 630
899
+ },
900
+ {
901
+ "epoch": 1.0372771474878444,
902
+ "grad_norm": 1568.0,
903
+ "learning_rate": 2.529976310795108e-05,
904
+ "loss": 1.2033,
905
+ "step": 640
906
+ },
907
+ {
908
+ "epoch": 1.053484602917342,
909
+ "grad_norm": 716.0,
910
+ "learning_rate": 2.4633627203686322e-05,
911
+ "loss": 1.0108,
912
+ "step": 650
913
+ },
914
+ {
915
+ "epoch": 1.0696920583468394,
916
+ "grad_norm": 50.5,
917
+ "learning_rate": 2.3967751416973304e-05,
918
+ "loss": 0.9941,
919
+ "step": 660
920
+ },
921
+ {
922
+ "epoch": 1.0858995137763372,
923
+ "grad_norm": 39.5,
924
+ "learning_rate": 2.3302608506655286e-05,
925
+ "loss": 1.1392,
926
+ "step": 670
927
+ },
928
+ {
929
+ "epoch": 1.1021069692058347,
930
+ "grad_norm": 1000.0,
931
+ "learning_rate": 2.2638670711247605e-05,
932
+ "loss": 1.083,
933
+ "step": 680
934
+ },
935
+ {
936
+ "epoch": 1.1183144246353323,
937
+ "grad_norm": 7456.0,
938
+ "learning_rate": 2.197640941365743e-05,
939
+ "loss": 1.0115,
940
+ "step": 690
941
+ },
942
+ {
943
+ "epoch": 1.1345218800648298,
944
+ "grad_norm": 2944.0,
945
+ "learning_rate": 2.131629480651116e-05,
946
+ "loss": 1.2825,
947
+ "step": 700
948
+ },
949
+ {
950
+ "epoch": 1.1345218800648298,
951
+ "eval_NanoBEIR_mean_cosine_accuracy@1": 0.17333333333333334,
952
+ "eval_NanoBEIR_mean_cosine_accuracy@5": 0.34,
953
+ "eval_NanoBEIR_mean_cosine_map@100": 0.2227183429409336,
954
+ "eval_NanoBEIR_mean_cosine_mrr@10": 0.25063756613756616,
955
+ "eval_NanoBEIR_mean_cosine_ndcg@1": 0.17333333333333334,
956
+ "eval_NanoBEIR_mean_cosine_ndcg@5": 0.23117905501265376,
957
+ "eval_NanoBEIR_mean_cosine_precision@1": 0.17333333333333334,
958
+ "eval_NanoBEIR_mean_cosine_precision@5": 0.07066666666666667,
959
+ "eval_NanoBEIR_mean_cosine_recall@1": 0.14,
960
+ "eval_NanoBEIR_mean_cosine_recall@5": 0.29000000000000004,
961
+ "eval_NanoFEVER_cosine_accuracy@1": 0.06,
962
+ "eval_NanoFEVER_cosine_accuracy@5": 0.14,
963
+ "eval_NanoFEVER_cosine_map@100": 0.10226378102099443,
964
+ "eval_NanoFEVER_cosine_mrr@10": 0.107,
965
+ "eval_NanoFEVER_cosine_ndcg@1": 0.06,
966
+ "eval_NanoFEVER_cosine_ndcg@5": 0.09611366515963533,
967
+ "eval_NanoFEVER_cosine_precision@1": 0.06,
968
+ "eval_NanoFEVER_cosine_precision@5": 0.027999999999999997,
969
+ "eval_NanoFEVER_cosine_recall@1": 0.05,
970
+ "eval_NanoFEVER_cosine_recall@5": 0.13,
971
+ "eval_NanoHotpotQA_cosine_accuracy@1": 0.18,
972
+ "eval_NanoHotpotQA_cosine_accuracy@5": 0.32,
973
+ "eval_NanoHotpotQA_cosine_map@100": 0.1431808584557489,
974
+ "eval_NanoHotpotQA_cosine_mrr@10": 0.2346666666666667,
975
+ "eval_NanoHotpotQA_cosine_ndcg@1": 0.18,
976
+ "eval_NanoHotpotQA_cosine_ndcg@5": 0.16151062083926612,
977
+ "eval_NanoHotpotQA_cosine_precision@1": 0.18,
978
+ "eval_NanoHotpotQA_cosine_precision@5": 0.07200000000000001,
979
+ "eval_NanoHotpotQA_cosine_recall@1": 0.09,
980
+ "eval_NanoHotpotQA_cosine_recall@5": 0.18,
981
+ "eval_NanoMSMARCO_cosine_accuracy@1": 0.28,
982
+ "eval_NanoMSMARCO_cosine_accuracy@5": 0.56,
983
+ "eval_NanoMSMARCO_cosine_map@100": 0.4227103893460575,
984
+ "eval_NanoMSMARCO_cosine_mrr@10": 0.4102460317460318,
985
+ "eval_NanoMSMARCO_cosine_ndcg@1": 0.28,
986
+ "eval_NanoMSMARCO_cosine_ndcg@5": 0.4359128790390598,
987
+ "eval_NanoMSMARCO_cosine_precision@1": 0.28,
988
+ "eval_NanoMSMARCO_cosine_precision@5": 0.11200000000000002,
989
+ "eval_NanoMSMARCO_cosine_recall@1": 0.28,
990
+ "eval_NanoMSMARCO_cosine_recall@5": 0.56,
991
+ "eval_mldr_loss": 1.04865562915802,
992
+ "eval_mldr_runtime": 14.5246,
993
+ "eval_mldr_samples_per_second": 34.424,
994
+ "eval_mldr_steps_per_second": 2.203,
995
+ "step": 700
996
+ },
997
+ {
998
+ "epoch": 1.1345218800648298,
999
+ "eval_squad_loss": 0.7077043652534485,
1000
+ "eval_squad_runtime": 0.907,
1001
+ "eval_squad_samples_per_second": 52.924,
1002
+ "eval_squad_steps_per_second": 3.308,
1003
+ "step": 700
1004
+ },
1005
+ {
1006
+ "epoch": 1.1345218800648298,
1007
+ "eval_narrative_qa_loss": 1.7767502069473267,
1008
+ "eval_narrative_qa_runtime": 1.1658,
1009
+ "eval_narrative_qa_samples_per_second": 256.487,
1010
+ "eval_narrative_qa_steps_per_second": 16.298,
1011
+ "step": 700
1012
+ },
1013
+ {
1014
+ "epoch": 1.1507293354943273,
1015
+ "grad_norm": 1976.0,
1016
+ "learning_rate": 2.0658795558326743e-05,
1017
+ "loss": 1.1286,
1018
+ "step": 710
1019
+ },
1020
+ {
1021
+ "epoch": 1.1669367909238249,
1022
+ "grad_norm": 1640.0,
1023
+ "learning_rate": 2.000437848076822e-05,
1024
+ "loss": 1.174,
1025
+ "step": 720
1026
+ },
1027
+ {
1028
+ "epoch": 1.1831442463533226,
1029
+ "grad_norm": 3776.0,
1030
+ "learning_rate": 1.935350819721849e-05,
1031
+ "loss": 1.124,
1032
+ "step": 730
1033
+ },
1034
+ {
1035
+ "epoch": 1.1993517017828201,
1036
+ "grad_norm": 5568.0,
1037
+ "learning_rate": 1.870664681290575e-05,
1038
+ "loss": 0.9694,
1039
+ "step": 740
1040
+ },
1041
+ {
1042
+ "epoch": 1.2155591572123177,
1043
+ "grad_norm": 532.0,
1044
+ "learning_rate": 1.8064253586817816e-05,
1045
+ "loss": 1.165,
1046
+ "step": 750
1047
+ },
1048
+ {
1049
+ "epoch": 1.2317666126418152,
1050
+ "grad_norm": 928.0,
1051
+ "learning_rate": 1.7426784605637153e-05,
1052
+ "loss": 1.1989,
1053
+ "step": 760
1054
+ },
1055
+ {
1056
+ "epoch": 1.2479740680713127,
1057
+ "grad_norm": 560.0,
1058
+ "learning_rate": 1.6794692459928223e-05,
1059
+ "loss": 0.9966,
1060
+ "step": 770
1061
+ },
1062
+ {
1063
+ "epoch": 1.2641815235008105,
1064
+ "grad_norm": 123.5,
1065
+ "learning_rate": 1.6168425922807008e-05,
1066
+ "loss": 0.9768,
1067
+ "step": 780
1068
+ },
1069
+ {
1070
+ "epoch": 1.280388978930308,
1071
+ "grad_norm": 884.0,
1072
+ "learning_rate": 1.5548429631320806e-05,
1073
+ "loss": 1.1039,
1074
+ "step": 790
1075
+ },
1076
+ {
1077
+ "epoch": 1.2965964343598055,
1078
+ "grad_norm": 15.75,
1079
+ "learning_rate": 1.4935143770764601e-05,
1080
+ "loss": 2.7281,
1081
+ "step": 800
1082
+ },
1083
+ {
1084
+ "epoch": 1.2965964343598055,
1085
+ "eval_NanoBEIR_mean_cosine_accuracy@1": 0.17333333333333334,
1086
+ "eval_NanoBEIR_mean_cosine_accuracy@5": 0.35333333333333333,
1087
+ "eval_NanoBEIR_mean_cosine_map@100": 0.2232392549386716,
1088
+ "eval_NanoBEIR_mean_cosine_mrr@10": 0.24966402116402117,
1089
+ "eval_NanoBEIR_mean_cosine_ndcg@1": 0.17333333333333334,
1090
+ "eval_NanoBEIR_mean_cosine_ndcg@5": 0.23771617121243702,
1091
+ "eval_NanoBEIR_mean_cosine_precision@1": 0.17333333333333334,
1092
+ "eval_NanoBEIR_mean_cosine_precision@5": 0.07333333333333333,
1093
+ "eval_NanoBEIR_mean_cosine_recall@1": 0.1366666666666667,
1094
+ "eval_NanoBEIR_mean_cosine_recall@5": 0.31,
1095
+ "eval_NanoFEVER_cosine_accuracy@1": 0.06,
1096
+ "eval_NanoFEVER_cosine_accuracy@5": 0.16,
1097
+ "eval_NanoFEVER_cosine_map@100": 0.1100930297556344,
1098
+ "eval_NanoFEVER_cosine_mrr@10": 0.11335714285714285,
1099
+ "eval_NanoFEVER_cosine_ndcg@1": 0.06,
1100
+ "eval_NanoFEVER_cosine_ndcg@5": 0.10785578521428746,
1101
+ "eval_NanoFEVER_cosine_precision@1": 0.06,
1102
+ "eval_NanoFEVER_cosine_precision@5": 0.032,
1103
+ "eval_NanoFEVER_cosine_recall@1": 0.05,
1104
+ "eval_NanoFEVER_cosine_recall@5": 0.15,
1105
+ "eval_NanoHotpotQA_cosine_accuracy@1": 0.2,
1106
+ "eval_NanoHotpotQA_cosine_accuracy@5": 0.28,
1107
+ "eval_NanoHotpotQA_cosine_map@100": 0.14784815274029572,
1108
+ "eval_NanoHotpotQA_cosine_mrr@10": 0.2350555555555556,
1109
+ "eval_NanoHotpotQA_cosine_ndcg@1": 0.2,
1110
+ "eval_NanoHotpotQA_cosine_ndcg@5": 0.16017374485985264,
1111
+ "eval_NanoHotpotQA_cosine_precision@1": 0.2,
1112
+ "eval_NanoHotpotQA_cosine_precision@5": 0.064,
1113
+ "eval_NanoHotpotQA_cosine_recall@1": 0.1,
1114
+ "eval_NanoHotpotQA_cosine_recall@5": 0.16,
1115
+ "eval_NanoMSMARCO_cosine_accuracy@1": 0.26,
1116
+ "eval_NanoMSMARCO_cosine_accuracy@5": 0.62,
1117
+ "eval_NanoMSMARCO_cosine_map@100": 0.4117765823200847,
1118
+ "eval_NanoMSMARCO_cosine_mrr@10": 0.40057936507936504,
1119
+ "eval_NanoMSMARCO_cosine_ndcg@1": 0.26,
1120
+ "eval_NanoMSMARCO_cosine_ndcg@5": 0.445118983563171,
1121
+ "eval_NanoMSMARCO_cosine_precision@1": 0.26,
1122
+ "eval_NanoMSMARCO_cosine_precision@5": 0.124,
1123
+ "eval_NanoMSMARCO_cosine_recall@1": 0.26,
1124
+ "eval_NanoMSMARCO_cosine_recall@5": 0.62,
1125
+ "eval_mldr_loss": 1.0107322931289673,
1126
+ "eval_mldr_runtime": 14.5338,
1127
+ "eval_mldr_samples_per_second": 34.403,
1128
+ "eval_mldr_steps_per_second": 2.202,
1129
+ "step": 800
1130
+ },
1131
+ {
1132
+ "epoch": 1.2965964343598055,
1133
+ "eval_squad_loss": 0.6025272607803345,
1134
+ "eval_squad_runtime": 0.8024,
1135
+ "eval_squad_samples_per_second": 59.822,
1136
+ "eval_squad_steps_per_second": 3.739,
1137
+ "step": 800
1138
+ },
1139
+ {
1140
+ "epoch": 1.2965964343598055,
1141
+ "eval_narrative_qa_loss": 1.7681714296340942,
1142
+ "eval_narrative_qa_runtime": 1.1303,
1143
+ "eval_narrative_qa_samples_per_second": 264.533,
1144
+ "eval_narrative_qa_steps_per_second": 16.81,
1145
+ "step": 800
1146
+ },
1147
+ {
1148
+ "epoch": 1.312803889789303,
1149
+ "grad_norm": 4288.0,
1150
+ "learning_rate": 1.4329003762158106e-05,
1151
+ "loss": 1.2271,
1152
+ "step": 810
1153
+ },
1154
+ {
1155
+ "epoch": 1.3290113452188006,
1156
+ "grad_norm": 11840.0,
1157
+ "learning_rate": 1.3730439953105243e-05,
1158
+ "loss": 1.0453,
1159
+ "step": 820
1160
+ },
1161
+ {
1162
+ "epoch": 1.3452188006482984,
1163
+ "grad_norm": 1440.0,
1164
+ "learning_rate": 1.3139877312255799e-05,
1165
+ "loss": 1.106,
1166
+ "step": 830
1167
+ },
1168
+ {
1169
+ "epoch": 1.3614262560777957,
1170
+ "grad_norm": 440.0,
1171
+ "learning_rate": 1.2557735127585917e-05,
1172
+ "loss": 1.0065,
1173
+ "step": 840
1174
+ },
1175
+ {
1176
+ "epoch": 1.3776337115072934,
1177
+ "grad_norm": 616.0,
1178
+ "learning_rate": 1.1984426708711804e-05,
1179
+ "loss": 1.124,
1180
+ "step": 850
1181
+ },
1182
+ {
1183
+ "epoch": 1.393841166936791,
1184
+ "grad_norm": 12.5,
1185
+ "learning_rate": 1.1420359093447966e-05,
1186
+ "loss": 1.3403,
1187
+ "step": 860
1188
+ },
1189
+ {
1190
+ "epoch": 1.4100486223662885,
1191
+ "grad_norm": 1280.0,
1192
+ "learning_rate": 1.0865932758818258e-05,
1193
+ "loss": 1.1274,
1194
+ "step": 870
1195
+ },
1196
+ {
1197
+ "epoch": 1.426256077795786,
1198
+ "grad_norm": 186.0,
1199
+ "learning_rate": 1.0321541336725027e-05,
1200
+ "loss": 1.1335,
1201
+ "step": 880
1202
+ },
1203
+ {
1204
+ "epoch": 1.4424635332252835,
1205
+ "grad_norm": 6656.0,
1206
+ "learning_rate": 9.787571334478101e-06,
1207
+ "loss": 1.0805,
1208
+ "step": 890
1209
+ },
1210
+ {
1211
+ "epoch": 1.4586709886547813,
1212
+ "grad_norm": 73.5,
1213
+ "learning_rate": 9.26440186038211e-06,
1214
+ "loss": 1.1117,
1215
+ "step": 900
1216
+ },
1217
+ {
1218
+ "epoch": 1.4586709886547813,
1219
+ "eval_NanoBEIR_mean_cosine_accuracy@1": 0.2066666666666667,
1220
+ "eval_NanoBEIR_mean_cosine_accuracy@5": 0.3466666666666667,
1221
+ "eval_NanoBEIR_mean_cosine_map@100": 0.24109707671460848,
1222
+ "eval_NanoBEIR_mean_cosine_mrr@10": 0.27005291005291004,
1223
+ "eval_NanoBEIR_mean_cosine_ndcg@1": 0.2066666666666667,
1224
+ "eval_NanoBEIR_mean_cosine_ndcg@5": 0.24663303266901904,
1225
+ "eval_NanoBEIR_mean_cosine_precision@1": 0.2066666666666667,
1226
+ "eval_NanoBEIR_mean_cosine_precision@5": 0.07200000000000001,
1227
+ "eval_NanoBEIR_mean_cosine_recall@1": 0.17,
1228
+ "eval_NanoBEIR_mean_cosine_recall@5": 0.29666666666666663,
1229
+ "eval_NanoFEVER_cosine_accuracy@1": 0.08,
1230
+ "eval_NanoFEVER_cosine_accuracy@5": 0.14,
1231
+ "eval_NanoFEVER_cosine_map@100": 0.10717352446028915,
1232
+ "eval_NanoFEVER_cosine_mrr@10": 0.1099126984126984,
1233
+ "eval_NanoFEVER_cosine_ndcg@1": 0.08,
1234
+ "eval_NanoFEVER_cosine_ndcg@5": 0.10123212623289701,
1235
+ "eval_NanoFEVER_cosine_precision@1": 0.08,
1236
+ "eval_NanoFEVER_cosine_precision@5": 0.028000000000000004,
1237
+ "eval_NanoFEVER_cosine_recall@1": 0.07,
1238
+ "eval_NanoFEVER_cosine_recall@5": 0.13,
1239
+ "eval_NanoHotpotQA_cosine_accuracy@1": 0.2,
1240
+ "eval_NanoHotpotQA_cosine_accuracy@5": 0.32,
1241
+ "eval_NanoHotpotQA_cosine_map@100": 0.15637152907438528,
1242
+ "eval_NanoHotpotQA_cosine_mrr@10": 0.2523888888888889,
1243
+ "eval_NanoHotpotQA_cosine_ndcg@1": 0.2,
1244
+ "eval_NanoHotpotQA_cosine_ndcg@5": 0.17287282180469699,
1245
+ "eval_NanoHotpotQA_cosine_precision@1": 0.2,
1246
+ "eval_NanoHotpotQA_cosine_precision@5": 0.07200000000000001,
1247
+ "eval_NanoHotpotQA_cosine_recall@1": 0.1,
1248
+ "eval_NanoHotpotQA_cosine_recall@5": 0.18,
1249
+ "eval_NanoMSMARCO_cosine_accuracy@1": 0.34,
1250
+ "eval_NanoMSMARCO_cosine_accuracy@5": 0.58,
1251
+ "eval_NanoMSMARCO_cosine_map@100": 0.45974617660915107,
1252
+ "eval_NanoMSMARCO_cosine_mrr@10": 0.44785714285714284,
1253
+ "eval_NanoMSMARCO_cosine_ndcg@1": 0.34,
1254
+ "eval_NanoMSMARCO_cosine_ndcg@5": 0.4657941499694631,
1255
+ "eval_NanoMSMARCO_cosine_precision@1": 0.34,
1256
+ "eval_NanoMSMARCO_cosine_precision@5": 0.11600000000000002,
1257
+ "eval_NanoMSMARCO_cosine_recall@1": 0.34,
1258
+ "eval_NanoMSMARCO_cosine_recall@5": 0.58,
1259
+ "eval_mldr_loss": 1.006673812866211,
1260
+ "eval_mldr_runtime": 14.487,
1261
+ "eval_mldr_samples_per_second": 34.514,
1262
+ "eval_mldr_steps_per_second": 2.209,
1263
+ "step": 900
1264
+ },
1265
+ {
1266
+ "epoch": 1.4586709886547813,
1267
+ "eval_squad_loss": 0.7755841612815857,
1268
+ "eval_squad_runtime": 0.8044,
1269
+ "eval_squad_samples_per_second": 59.675,
1270
+ "eval_squad_steps_per_second": 3.73,
1271
+ "step": 900
1272
+ },
1273
+ {
1274
+ "epoch": 1.4586709886547813,
1275
+ "eval_narrative_qa_loss": 1.7425211668014526,
1276
+ "eval_narrative_qa_runtime": 1.1372,
1277
+ "eval_narrative_qa_samples_per_second": 262.924,
1278
+ "eval_narrative_qa_steps_per_second": 16.708,
1279
+ "step": 900
1280
+ },
1281
+ {
1282
+ "epoch": 1.4748784440842788,
1283
+ "grad_norm": 712.0,
1284
+ "learning_rate": 8.752404354577052e-06,
1285
+ "loss": 1.0897,
1286
+ "step": 910
1287
+ },
1288
+ {
1289
+ "epoch": 1.4910858995137763,
1290
+ "grad_norm": 1200.0,
1291
+ "learning_rate": 8.251942325322903e-06,
1292
+ "loss": 0.9964,
1293
+ "step": 920
1294
+ },
1295
+ {
1296
+ "epoch": 1.5072933549432739,
1297
+ "grad_norm": 2016.0,
1298
+ "learning_rate": 7.763371090915932e-06,
1299
+ "loss": 0.954,
1300
+ "step": 930
1301
+ },
1302
+ {
1303
+ "epoch": 1.5235008103727714,
1304
+ "grad_norm": 4512.0,
1305
+ "learning_rate": 7.287037527419604e-06,
1306
+ "loss": 1.3415,
1307
+ "step": 940
1308
+ },
1309
+ {
1310
+ "epoch": 1.5397082658022692,
1311
+ "grad_norm": 438.0,
1312
+ "learning_rate": 6.823279822389278e-06,
1313
+ "loss": 0.9926,
1314
+ "step": 950
1315
+ },
1316
+ {
1317
+ "epoch": 1.5559157212317665,
1318
+ "grad_norm": 158.0,
1319
+ "learning_rate": 6.372427234765688e-06,
1320
+ "loss": 1.1362,
1321
+ "step": 960
1322
+ },
1323
+ {
1324
+ "epoch": 1.5721231766612642,
1325
+ "grad_norm": 163.0,
1326
+ "learning_rate": 5.934799861107507e-06,
1327
+ "loss": 1.1178,
1328
+ "step": 970
1329
+ },
1330
+ {
1331
+ "epoch": 1.5883306320907618,
1332
+ "grad_norm": 1216.0,
1333
+ "learning_rate": 5.5107084083289576e-06,
1334
+ "loss": 0.8676,
1335
+ "step": 980
1336
+ },
1337
+ {
1338
+ "epoch": 1.6045380875202593,
1339
+ "grad_norm": 37632.0,
1340
+ "learning_rate": 5.1004539731040245e-06,
1341
+ "loss": 1.1794,
1342
+ "step": 990
1343
+ },
1344
+ {
1345
+ "epoch": 1.620745542949757,
1346
+ "grad_norm": 268.0,
1347
+ "learning_rate": 4.704327828093641e-06,
1348
+ "loss": 1.0575,
1349
+ "step": 1000
1350
+ },
1351
+ {
1352
+ "epoch": 1.620745542949757,
1353
+ "eval_NanoBEIR_mean_cosine_accuracy@1": 0.18666666666666668,
1354
+ "eval_NanoBEIR_mean_cosine_accuracy@5": 0.3333333333333333,
1355
+ "eval_NanoBEIR_mean_cosine_map@100": 0.23251229334833623,
1356
+ "eval_NanoBEIR_mean_cosine_mrr@10": 0.250457671957672,
1357
+ "eval_NanoBEIR_mean_cosine_ndcg@1": 0.18666666666666668,
1358
+ "eval_NanoBEIR_mean_cosine_ndcg@5": 0.23607659211604262,
1359
+ "eval_NanoBEIR_mean_cosine_precision@1": 0.18666666666666668,
1360
+ "eval_NanoBEIR_mean_cosine_precision@5": 0.06933333333333334,
1361
+ "eval_NanoBEIR_mean_cosine_recall@1": 0.15666666666666668,
1362
+ "eval_NanoBEIR_mean_cosine_recall@5": 0.29,
1363
+ "eval_NanoFEVER_cosine_accuracy@1": 0.08,
1364
+ "eval_NanoFEVER_cosine_accuracy@5": 0.14,
1365
+ "eval_NanoFEVER_cosine_map@100": 0.10995542705065009,
1366
+ "eval_NanoFEVER_cosine_mrr@10": 0.11060317460317462,
1367
+ "eval_NanoFEVER_cosine_ndcg@1": 0.08,
1368
+ "eval_NanoFEVER_cosine_ndcg@5": 0.10261859507142916,
1369
+ "eval_NanoFEVER_cosine_precision@1": 0.08,
1370
+ "eval_NanoFEVER_cosine_precision@5": 0.027999999999999997,
1371
+ "eval_NanoFEVER_cosine_recall@1": 0.07,
1372
+ "eval_NanoFEVER_cosine_recall@5": 0.13,
1373
+ "eval_NanoHotpotQA_cosine_accuracy@1": 0.16,
1374
+ "eval_NanoHotpotQA_cosine_accuracy@5": 0.28,
1375
+ "eval_NanoHotpotQA_cosine_map@100": 0.14864943925499563,
1376
+ "eval_NanoHotpotQA_cosine_mrr@10": 0.21274603174603177,
1377
+ "eval_NanoHotpotQA_cosine_ndcg@1": 0.16,
1378
+ "eval_NanoHotpotQA_cosine_ndcg@5": 0.15294562020041982,
1379
+ "eval_NanoHotpotQA_cosine_precision@1": 0.16,
1380
+ "eval_NanoHotpotQA_cosine_precision@5": 0.064,
1381
+ "eval_NanoHotpotQA_cosine_recall@1": 0.08,
1382
+ "eval_NanoHotpotQA_cosine_recall@5": 0.16,
1383
+ "eval_NanoMSMARCO_cosine_accuracy@1": 0.32,
1384
+ "eval_NanoMSMARCO_cosine_accuracy@5": 0.58,
1385
+ "eval_NanoMSMARCO_cosine_map@100": 0.4389320137393629,
1386
+ "eval_NanoMSMARCO_cosine_mrr@10": 0.42802380952380953,
1387
+ "eval_NanoMSMARCO_cosine_ndcg@1": 0.32,
1388
+ "eval_NanoMSMARCO_cosine_ndcg@5": 0.4526655610762789,
1389
+ "eval_NanoMSMARCO_cosine_precision@1": 0.32,
1390
+ "eval_NanoMSMARCO_cosine_precision@5": 0.11600000000000002,
1391
+ "eval_NanoMSMARCO_cosine_recall@1": 0.32,
1392
+ "eval_NanoMSMARCO_cosine_recall@5": 0.58,
1393
+ "eval_mldr_loss": 1.0088629722595215,
1394
+ "eval_mldr_runtime": 14.5077,
1395
+ "eval_mldr_samples_per_second": 34.464,
1396
+ "eval_mldr_steps_per_second": 2.206,
1397
+ "step": 1000
1398
+ },
1399
+ {
1400
+ "epoch": 1.620745542949757,
1401
+ "eval_squad_loss": 0.6442683339118958,
1402
+ "eval_squad_runtime": 0.8625,
1403
+ "eval_squad_samples_per_second": 55.652,
1404
+ "eval_squad_steps_per_second": 3.478,
1405
+ "step": 1000
1406
+ },
1407
+ {
1408
+ "epoch": 1.620745542949757,
1409
+ "eval_narrative_qa_loss": 1.7451977729797363,
1410
+ "eval_narrative_qa_runtime": 1.1443,
1411
+ "eval_narrative_qa_samples_per_second": 261.298,
1412
+ "eval_narrative_qa_steps_per_second": 16.604,
1413
+ "step": 1000
1414
+ }
1415
+ ],
1416
+ "logging_steps": 10,
1417
+ "max_steps": 1234,
1418
+ "num_input_tokens_seen": 0,
1419
+ "num_train_epochs": 2,
1420
+ "save_steps": 500,
1421
+ "stateful_callbacks": {
1422
+ "TrainerControl": {
1423
+ "args": {
1424
+ "should_epoch_stop": false,
1425
+ "should_evaluate": false,
1426
+ "should_log": false,
1427
+ "should_save": true,
1428
+ "should_training_stop": false
1429
+ },
1430
+ "attributes": {}
1431
+ }
1432
+ },
1433
+ "total_flos": 0.0,
1434
+ "train_batch_size": 4,
1435
+ "trial_name": null,
1436
+ "trial_params": null
1437
+ }
checkpoint-1000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e33f3c9977bb1dfdea6e80445e3a56ac46fa17e22c8e01527826c894784b6fb3
3
+ size 5560
checkpoint-1234/1_Pooling/config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "word_embedding_dimension": 1024,
3
+ "pooling_mode_cls_token": false,
4
+ "pooling_mode_mean_tokens": true,
5
+ "pooling_mode_max_tokens": false,
6
+ "pooling_mode_mean_sqrt_len_tokens": false,
7
+ "pooling_mode_weightedmean_tokens": false,
8
+ "pooling_mode_lasttoken": false,
9
+ "include_prompt": true
10
+ }
checkpoint-1234/README.md ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-1234/config.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "./models/modernbert-embed-large",
3
+ "architectures": [
4
+ "ModernBertModel"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 50281,
9
+ "classifier_activation": "gelu",
10
+ "classifier_bias": false,
11
+ "classifier_dropout": 0.0,
12
+ "classifier_pooling": "mean",
13
+ "cls_token_id": 50281,
14
+ "decoder_bias": true,
15
+ "deterministic_flash_attn": false,
16
+ "embedding_dropout": 0.0,
17
+ "eos_token_id": 50282,
18
+ "global_attn_every_n_layers": 3,
19
+ "global_rope_theta": 160000.0,
20
+ "gradient_checkpointing": false,
21
+ "hidden_activation": "gelu",
22
+ "hidden_size": 1024,
23
+ "initializer_cutoff_factor": 2.0,
24
+ "initializer_range": 0.02,
25
+ "intermediate_size": 2624,
26
+ "layer_norm_eps": 1e-05,
27
+ "local_attention": 128,
28
+ "local_rope_theta": 10000.0,
29
+ "max_position_embeddings": 8192,
30
+ "mlp_bias": false,
31
+ "mlp_dropout": 0.0,
32
+ "model_type": "modernbert",
33
+ "norm_bias": false,
34
+ "norm_eps": 1e-05,
35
+ "num_attention_heads": 16,
36
+ "num_hidden_layers": 28,
37
+ "pad_token_id": 50283,
38
+ "position_embedding_type": "absolute",
39
+ "reference_compile": true,
40
+ "repad_logits_with_grad": false,
41
+ "sep_token_id": 50282,
42
+ "sparse_pred_ignore_index": -100,
43
+ "sparse_prediction": false,
44
+ "torch_dtype": "bfloat16",
45
+ "transformers_version": "4.48.1",
46
+ "vocab_size": 50368
47
+ }
checkpoint-1234/config_sentence_transformers.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "__version__": {
3
+ "sentence_transformers": "3.3.1",
4
+ "transformers": "4.48.1",
5
+ "pytorch": "2.5.1+cu118"
6
+ },
7
+ "prompts": {},
8
+ "default_prompt_name": null,
9
+ "similarity_fn_name": "cosine"
10
+ }
checkpoint-1234/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7918c887ad3d7e6f54568e7a8fdd89edb5be8ea7d6ea3befeab228d20a1c3643
3
+ size 789580328
checkpoint-1234/modules.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [
2
+ {
3
+ "idx": 0,
4
+ "name": "0",
5
+ "path": "",
6
+ "type": "sentence_transformers.models.Transformer"
7
+ },
8
+ {
9
+ "idx": 1,
10
+ "name": "1",
11
+ "path": "1_Pooling",
12
+ "type": "sentence_transformers.models.Pooling"
13
+ },
14
+ {
15
+ "idx": 2,
16
+ "name": "2",
17
+ "path": "2_Normalize",
18
+ "type": "sentence_transformers.models.Normalize"
19
+ }
20
+ ]
checkpoint-1234/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0bb94e5f4bc011e1e4531941f1f4326252fb54b95d54fe1af21fdd28f0510f5c
3
+ size 1579269882
checkpoint-1234/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f074344b31d16dc370dea8a2426a2407d8b23220d9411dcdd8e8ae2d23803652
3
+ size 14960
checkpoint-1234/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a77ccee331ed4bd1798c711d77698c8aa42dba3810e921b867b2a01ad2fb872
3
+ size 14960
checkpoint-1234/rng_state_2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e645a65077530629dd86be9ed51233d9869ade31568c042416a52e4d95fba5b2
3
+ size 14960
checkpoint-1234/rng_state_3.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:78a3cb9d59ad46c739417a3244e3e072b6162066b40ab29901bf15895562dec7
3
+ size 14960
checkpoint-1234/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b03363b9639db230c6013af813fcc26492dd6525dff19a28a8275f52228be5ba
3
+ size 1064
checkpoint-1234/sentence_bert_config.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "max_seq_length": 8192,
3
+ "do_lower_case": false
4
+ }
checkpoint-1234/special_tokens_map.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": {
3
+ "content": "[CLS]",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "mask_token": {
10
+ "content": "[MASK]",
11
+ "lstrip": true,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "[PAD]",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "sep_token": {
24
+ "content": "[SEP]",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "unk_token": {
31
+ "content": "[UNK]",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ }
37
+ }
checkpoint-1234/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-1234/tokenizer_config.json ADDED
@@ -0,0 +1,945 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "|||IP_ADDRESS|||",
5
+ "lstrip": false,
6
+ "normalized": true,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": false
10
+ },
11
+ "1": {
12
+ "content": "<|padding|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "50254": {
20
+ "content": " ",
21
+ "lstrip": false,
22
+ "normalized": true,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": false
26
+ },
27
+ "50255": {
28
+ "content": " ",
29
+ "lstrip": false,
30
+ "normalized": true,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": false
34
+ },
35
+ "50256": {
36
+ "content": " ",
37
+ "lstrip": false,
38
+ "normalized": true,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": false
42
+ },
43
+ "50257": {
44
+ "content": " ",
45
+ "lstrip": false,
46
+ "normalized": true,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": false
50
+ },
51
+ "50258": {
52
+ "content": " ",
53
+ "lstrip": false,
54
+ "normalized": true,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": false
58
+ },
59
+ "50259": {
60
+ "content": " ",
61
+ "lstrip": false,
62
+ "normalized": true,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": false
66
+ },
67
+ "50260": {
68
+ "content": " ",
69
+ "lstrip": false,
70
+ "normalized": true,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": false
74
+ },
75
+ "50261": {
76
+ "content": " ",
77
+ "lstrip": false,
78
+ "normalized": true,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": false
82
+ },
83
+ "50262": {
84
+ "content": " ",
85
+ "lstrip": false,
86
+ "normalized": true,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": false
90
+ },
91
+ "50263": {
92
+ "content": " ",
93
+ "lstrip": false,
94
+ "normalized": true,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": false
98
+ },
99
+ "50264": {
100
+ "content": " ",
101
+ "lstrip": false,
102
+ "normalized": true,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": false
106
+ },
107
+ "50265": {
108
+ "content": " ",
109
+ "lstrip": false,
110
+ "normalized": true,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": false
114
+ },
115
+ "50266": {
116
+ "content": " ",
117
+ "lstrip": false,
118
+ "normalized": true,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": false
122
+ },
123
+ "50267": {
124
+ "content": " ",
125
+ "lstrip": false,
126
+ "normalized": true,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": false
130
+ },
131
+ "50268": {
132
+ "content": " ",
133
+ "lstrip": false,
134
+ "normalized": true,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": false
138
+ },
139
+ "50269": {
140
+ "content": " ",
141
+ "lstrip": false,
142
+ "normalized": true,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": false
146
+ },
147
+ "50270": {
148
+ "content": " ",
149
+ "lstrip": false,
150
+ "normalized": true,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": false
154
+ },
155
+ "50271": {
156
+ "content": " ",
157
+ "lstrip": false,
158
+ "normalized": true,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": false
162
+ },
163
+ "50272": {
164
+ "content": " ",
165
+ "lstrip": false,
166
+ "normalized": true,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": false
170
+ },
171
+ "50273": {
172
+ "content": " ",
173
+ "lstrip": false,
174
+ "normalized": true,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": false
178
+ },
179
+ "50274": {
180
+ "content": " ",
181
+ "lstrip": false,
182
+ "normalized": true,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": false
186
+ },
187
+ "50275": {
188
+ "content": " ",
189
+ "lstrip": false,
190
+ "normalized": true,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": false
194
+ },
195
+ "50276": {
196
+ "content": " ",
197
+ "lstrip": false,
198
+ "normalized": true,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": false
202
+ },
203
+ "50277": {
204
+ "content": "|||EMAIL_ADDRESS|||",
205
+ "lstrip": false,
206
+ "normalized": true,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": false
210
+ },
211
+ "50278": {
212
+ "content": "|||PHONE_NUMBER|||",
213
+ "lstrip": false,
214
+ "normalized": true,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": false
218
+ },
219
+ "50279": {
220
+ "content": "<|endoftext|>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "50280": {
228
+ "content": "[UNK]",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "50281": {
236
+ "content": "[CLS]",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "50282": {
244
+ "content": "[SEP]",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "50283": {
252
+ "content": "[PAD]",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "50284": {
260
+ "content": "[MASK]",
261
+ "lstrip": true,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "50285": {
268
+ "content": "[unused0]",
269
+ "lstrip": false,
270
+ "normalized": true,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": false
274
+ },
275
+ "50286": {
276
+ "content": "[unused1]",
277
+ "lstrip": false,
278
+ "normalized": true,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": false
282
+ },
283
+ "50287": {
284
+ "content": "[unused2]",
285
+ "lstrip": false,
286
+ "normalized": true,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": false
290
+ },
291
+ "50288": {
292
+ "content": "[unused3]",
293
+ "lstrip": false,
294
+ "normalized": true,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": false
298
+ },
299
+ "50289": {
300
+ "content": "[unused4]",
301
+ "lstrip": false,
302
+ "normalized": true,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": false
306
+ },
307
+ "50290": {
308
+ "content": "[unused5]",
309
+ "lstrip": false,
310
+ "normalized": true,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": false
314
+ },
315
+ "50291": {
316
+ "content": "[unused6]",
317
+ "lstrip": false,
318
+ "normalized": true,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": false
322
+ },
323
+ "50292": {
324
+ "content": "[unused7]",
325
+ "lstrip": false,
326
+ "normalized": true,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": false
330
+ },
331
+ "50293": {
332
+ "content": "[unused8]",
333
+ "lstrip": false,
334
+ "normalized": true,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": false
338
+ },
339
+ "50294": {
340
+ "content": "[unused9]",
341
+ "lstrip": false,
342
+ "normalized": true,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": false
346
+ },
347
+ "50295": {
348
+ "content": "[unused10]",
349
+ "lstrip": false,
350
+ "normalized": true,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": false
354
+ },
355
+ "50296": {
356
+ "content": "[unused11]",
357
+ "lstrip": false,
358
+ "normalized": true,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": false
362
+ },
363
+ "50297": {
364
+ "content": "[unused12]",
365
+ "lstrip": false,
366
+ "normalized": true,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": false
370
+ },
371
+ "50298": {
372
+ "content": "[unused13]",
373
+ "lstrip": false,
374
+ "normalized": true,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": false
378
+ },
379
+ "50299": {
380
+ "content": "[unused14]",
381
+ "lstrip": false,
382
+ "normalized": true,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": false
386
+ },
387
+ "50300": {
388
+ "content": "[unused15]",
389
+ "lstrip": false,
390
+ "normalized": true,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": false
394
+ },
395
+ "50301": {
396
+ "content": "[unused16]",
397
+ "lstrip": false,
398
+ "normalized": true,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": false
402
+ },
403
+ "50302": {
404
+ "content": "[unused17]",
405
+ "lstrip": false,
406
+ "normalized": true,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": false
410
+ },
411
+ "50303": {
412
+ "content": "[unused18]",
413
+ "lstrip": false,
414
+ "normalized": true,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": false
418
+ },
419
+ "50304": {
420
+ "content": "[unused19]",
421
+ "lstrip": false,
422
+ "normalized": true,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": false
426
+ },
427
+ "50305": {
428
+ "content": "[unused20]",
429
+ "lstrip": false,
430
+ "normalized": true,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": false
434
+ },
435
+ "50306": {
436
+ "content": "[unused21]",
437
+ "lstrip": false,
438
+ "normalized": true,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": false
442
+ },
443
+ "50307": {
444
+ "content": "[unused22]",
445
+ "lstrip": false,
446
+ "normalized": true,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": false
450
+ },
451
+ "50308": {
452
+ "content": "[unused23]",
453
+ "lstrip": false,
454
+ "normalized": true,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": false
458
+ },
459
+ "50309": {
460
+ "content": "[unused24]",
461
+ "lstrip": false,
462
+ "normalized": true,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": false
466
+ },
467
+ "50310": {
468
+ "content": "[unused25]",
469
+ "lstrip": false,
470
+ "normalized": true,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": false
474
+ },
475
+ "50311": {
476
+ "content": "[unused26]",
477
+ "lstrip": false,
478
+ "normalized": true,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": false
482
+ },
483
+ "50312": {
484
+ "content": "[unused27]",
485
+ "lstrip": false,
486
+ "normalized": true,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": false
490
+ },
491
+ "50313": {
492
+ "content": "[unused28]",
493
+ "lstrip": false,
494
+ "normalized": true,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": false
498
+ },
499
+ "50314": {
500
+ "content": "[unused29]",
501
+ "lstrip": false,
502
+ "normalized": true,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": false
506
+ },
507
+ "50315": {
508
+ "content": "[unused30]",
509
+ "lstrip": false,
510
+ "normalized": true,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": false
514
+ },
515
+ "50316": {
516
+ "content": "[unused31]",
517
+ "lstrip": false,
518
+ "normalized": true,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": false
522
+ },
523
+ "50317": {
524
+ "content": "[unused32]",
525
+ "lstrip": false,
526
+ "normalized": true,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": false
530
+ },
531
+ "50318": {
532
+ "content": "[unused33]",
533
+ "lstrip": false,
534
+ "normalized": true,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": false
538
+ },
539
+ "50319": {
540
+ "content": "[unused34]",
541
+ "lstrip": false,
542
+ "normalized": true,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": false
546
+ },
547
+ "50320": {
548
+ "content": "[unused35]",
549
+ "lstrip": false,
550
+ "normalized": true,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": false
554
+ },
555
+ "50321": {
556
+ "content": "[unused36]",
557
+ "lstrip": false,
558
+ "normalized": true,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": false
562
+ },
563
+ "50322": {
564
+ "content": "[unused37]",
565
+ "lstrip": false,
566
+ "normalized": true,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": false
570
+ },
571
+ "50323": {
572
+ "content": "[unused38]",
573
+ "lstrip": false,
574
+ "normalized": true,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": false
578
+ },
579
+ "50324": {
580
+ "content": "[unused39]",
581
+ "lstrip": false,
582
+ "normalized": true,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": false
586
+ },
587
+ "50325": {
588
+ "content": "[unused40]",
589
+ "lstrip": false,
590
+ "normalized": true,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": false
594
+ },
595
+ "50326": {
596
+ "content": "[unused41]",
597
+ "lstrip": false,
598
+ "normalized": true,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": false
602
+ },
603
+ "50327": {
604
+ "content": "[unused42]",
605
+ "lstrip": false,
606
+ "normalized": true,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": false
610
+ },
611
+ "50328": {
612
+ "content": "[unused43]",
613
+ "lstrip": false,
614
+ "normalized": true,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": false
618
+ },
619
+ "50329": {
620
+ "content": "[unused44]",
621
+ "lstrip": false,
622
+ "normalized": true,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": false
626
+ },
627
+ "50330": {
628
+ "content": "[unused45]",
629
+ "lstrip": false,
630
+ "normalized": true,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": false
634
+ },
635
+ "50331": {
636
+ "content": "[unused46]",
637
+ "lstrip": false,
638
+ "normalized": true,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": false
642
+ },
643
+ "50332": {
644
+ "content": "[unused47]",
645
+ "lstrip": false,
646
+ "normalized": true,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": false
650
+ },
651
+ "50333": {
652
+ "content": "[unused48]",
653
+ "lstrip": false,
654
+ "normalized": true,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": false
658
+ },
659
+ "50334": {
660
+ "content": "[unused49]",
661
+ "lstrip": false,
662
+ "normalized": true,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": false
666
+ },
667
+ "50335": {
668
+ "content": "[unused50]",
669
+ "lstrip": false,
670
+ "normalized": true,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": false
674
+ },
675
+ "50336": {
676
+ "content": "[unused51]",
677
+ "lstrip": false,
678
+ "normalized": true,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": false
682
+ },
683
+ "50337": {
684
+ "content": "[unused52]",
685
+ "lstrip": false,
686
+ "normalized": true,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": false
690
+ },
691
+ "50338": {
692
+ "content": "[unused53]",
693
+ "lstrip": false,
694
+ "normalized": true,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": false
698
+ },
699
+ "50339": {
700
+ "content": "[unused54]",
701
+ "lstrip": false,
702
+ "normalized": true,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": false
706
+ },
707
+ "50340": {
708
+ "content": "[unused55]",
709
+ "lstrip": false,
710
+ "normalized": true,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": false
714
+ },
715
+ "50341": {
716
+ "content": "[unused56]",
717
+ "lstrip": false,
718
+ "normalized": true,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": false
722
+ },
723
+ "50342": {
724
+ "content": "[unused57]",
725
+ "lstrip": false,
726
+ "normalized": true,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": false
730
+ },
731
+ "50343": {
732
+ "content": "[unused58]",
733
+ "lstrip": false,
734
+ "normalized": true,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": false
738
+ },
739
+ "50344": {
740
+ "content": "[unused59]",
741
+ "lstrip": false,
742
+ "normalized": true,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": false
746
+ },
747
+ "50345": {
748
+ "content": "[unused60]",
749
+ "lstrip": false,
750
+ "normalized": true,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": false
754
+ },
755
+ "50346": {
756
+ "content": "[unused61]",
757
+ "lstrip": false,
758
+ "normalized": true,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": false
762
+ },
763
+ "50347": {
764
+ "content": "[unused62]",
765
+ "lstrip": false,
766
+ "normalized": true,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": false
770
+ },
771
+ "50348": {
772
+ "content": "[unused63]",
773
+ "lstrip": false,
774
+ "normalized": true,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": false
778
+ },
779
+ "50349": {
780
+ "content": "[unused64]",
781
+ "lstrip": false,
782
+ "normalized": true,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": false
786
+ },
787
+ "50350": {
788
+ "content": "[unused65]",
789
+ "lstrip": false,
790
+ "normalized": true,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": false
794
+ },
795
+ "50351": {
796
+ "content": "[unused66]",
797
+ "lstrip": false,
798
+ "normalized": true,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": false
802
+ },
803
+ "50352": {
804
+ "content": "[unused67]",
805
+ "lstrip": false,
806
+ "normalized": true,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": false
810
+ },
811
+ "50353": {
812
+ "content": "[unused68]",
813
+ "lstrip": false,
814
+ "normalized": true,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": false
818
+ },
819
+ "50354": {
820
+ "content": "[unused69]",
821
+ "lstrip": false,
822
+ "normalized": true,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": false
826
+ },
827
+ "50355": {
828
+ "content": "[unused70]",
829
+ "lstrip": false,
830
+ "normalized": true,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": false
834
+ },
835
+ "50356": {
836
+ "content": "[unused71]",
837
+ "lstrip": false,
838
+ "normalized": true,
839
+ "rstrip": false,
840
+ "single_word": false,
841
+ "special": false
842
+ },
843
+ "50357": {
844
+ "content": "[unused72]",
845
+ "lstrip": false,
846
+ "normalized": true,
847
+ "rstrip": false,
848
+ "single_word": false,
849
+ "special": false
850
+ },
851
+ "50358": {
852
+ "content": "[unused73]",
853
+ "lstrip": false,
854
+ "normalized": true,
855
+ "rstrip": false,
856
+ "single_word": false,
857
+ "special": false
858
+ },
859
+ "50359": {
860
+ "content": "[unused74]",
861
+ "lstrip": false,
862
+ "normalized": true,
863
+ "rstrip": false,
864
+ "single_word": false,
865
+ "special": false
866
+ },
867
+ "50360": {
868
+ "content": "[unused75]",
869
+ "lstrip": false,
870
+ "normalized": true,
871
+ "rstrip": false,
872
+ "single_word": false,
873
+ "special": false
874
+ },
875
+ "50361": {
876
+ "content": "[unused76]",
877
+ "lstrip": false,
878
+ "normalized": true,
879
+ "rstrip": false,
880
+ "single_word": false,
881
+ "special": false
882
+ },
883
+ "50362": {
884
+ "content": "[unused77]",
885
+ "lstrip": false,
886
+ "normalized": true,
887
+ "rstrip": false,
888
+ "single_word": false,
889
+ "special": false
890
+ },
891
+ "50363": {
892
+ "content": "[unused78]",
893
+ "lstrip": false,
894
+ "normalized": true,
895
+ "rstrip": false,
896
+ "single_word": false,
897
+ "special": false
898
+ },
899
+ "50364": {
900
+ "content": "[unused79]",
901
+ "lstrip": false,
902
+ "normalized": true,
903
+ "rstrip": false,
904
+ "single_word": false,
905
+ "special": false
906
+ },
907
+ "50365": {
908
+ "content": "[unused80]",
909
+ "lstrip": false,
910
+ "normalized": true,
911
+ "rstrip": false,
912
+ "single_word": false,
913
+ "special": false
914
+ },
915
+ "50366": {
916
+ "content": "[unused81]",
917
+ "lstrip": false,
918
+ "normalized": true,
919
+ "rstrip": false,
920
+ "single_word": false,
921
+ "special": false
922
+ },
923
+ "50367": {
924
+ "content": "[unused82]",
925
+ "lstrip": false,
926
+ "normalized": true,
927
+ "rstrip": false,
928
+ "single_word": false,
929
+ "special": false
930
+ }
931
+ },
932
+ "clean_up_tokenization_spaces": true,
933
+ "cls_token": "[CLS]",
934
+ "extra_special_tokens": {},
935
+ "mask_token": "[MASK]",
936
+ "model_input_names": [
937
+ "input_ids",
938
+ "attention_mask"
939
+ ],
940
+ "model_max_length": 8192,
941
+ "pad_token": "[PAD]",
942
+ "sep_token": "[SEP]",
943
+ "tokenizer_class": "PreTrainedTokenizerFast",
944
+ "unk_token": "[UNK]"
945
+ }
checkpoint-1234/trainer_state.json ADDED
@@ -0,0 +1,1726 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.0,
5
+ "eval_steps": 100,
6
+ "global_step": 1234,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0,
13
+ "eval_NanoBEIR_mean_cosine_accuracy@1": 0.5733333333333334,
14
+ "eval_NanoBEIR_mean_cosine_accuracy@5": 0.88,
15
+ "eval_NanoBEIR_mean_cosine_map@100": 0.6499700198395969,
16
+ "eval_NanoBEIR_mean_cosine_mrr@10": 0.7025343915343916,
17
+ "eval_NanoBEIR_mean_cosine_ndcg@1": 0.5733333333333334,
18
+ "eval_NanoBEIR_mean_cosine_ndcg@5": 0.6933983700329899,
19
+ "eval_NanoBEIR_mean_cosine_precision@1": 0.5733333333333334,
20
+ "eval_NanoBEIR_mean_cosine_precision@5": 0.21599999999999997,
21
+ "eval_NanoBEIR_mean_cosine_recall@1": 0.44222222222222224,
22
+ "eval_NanoBEIR_mean_cosine_recall@5": 0.8077777777777778,
23
+ "eval_NanoFEVER_cosine_accuracy@1": 0.66,
24
+ "eval_NanoFEVER_cosine_accuracy@5": 0.94,
25
+ "eval_NanoFEVER_cosine_map@100": 0.7456105053991163,
26
+ "eval_NanoFEVER_cosine_mrr@10": 0.7750000000000001,
27
+ "eval_NanoFEVER_cosine_ndcg@1": 0.66,
28
+ "eval_NanoFEVER_cosine_ndcg@5": 0.7909186074531693,
29
+ "eval_NanoFEVER_cosine_precision@1": 0.66,
30
+ "eval_NanoFEVER_cosine_precision@5": 0.19999999999999996,
31
+ "eval_NanoFEVER_cosine_recall@1": 0.6166666666666667,
32
+ "eval_NanoFEVER_cosine_recall@5": 0.9133333333333333,
33
+ "eval_NanoHotpotQA_cosine_accuracy@1": 0.7,
34
+ "eval_NanoHotpotQA_cosine_accuracy@5": 0.92,
35
+ "eval_NanoHotpotQA_cosine_map@100": 0.659131307951428,
36
+ "eval_NanoHotpotQA_cosine_mrr@10": 0.795,
37
+ "eval_NanoHotpotQA_cosine_ndcg@1": 0.7,
38
+ "eval_NanoHotpotQA_cosine_ndcg@5": 0.7005437199248264,
39
+ "eval_NanoHotpotQA_cosine_precision@1": 0.7,
40
+ "eval_NanoHotpotQA_cosine_precision@5": 0.292,
41
+ "eval_NanoHotpotQA_cosine_recall@1": 0.35,
42
+ "eval_NanoHotpotQA_cosine_recall@5": 0.73,
43
+ "eval_NanoMSMARCO_cosine_accuracy@1": 0.36,
44
+ "eval_NanoMSMARCO_cosine_accuracy@5": 0.78,
45
+ "eval_NanoMSMARCO_cosine_map@100": 0.5451682461682461,
46
+ "eval_NanoMSMARCO_cosine_mrr@10": 0.5376031746031745,
47
+ "eval_NanoMSMARCO_cosine_ndcg@1": 0.36,
48
+ "eval_NanoMSMARCO_cosine_ndcg@5": 0.5887327827209738,
49
+ "eval_NanoMSMARCO_cosine_precision@1": 0.36,
50
+ "eval_NanoMSMARCO_cosine_precision@5": 0.156,
51
+ "eval_NanoMSMARCO_cosine_recall@1": 0.36,
52
+ "eval_NanoMSMARCO_cosine_recall@5": 0.78,
53
+ "eval_mldr_loss": 98.74517822265625,
54
+ "eval_mldr_runtime": 49.7129,
55
+ "eval_mldr_samples_per_second": 10.058,
56
+ "eval_mldr_steps_per_second": 0.644,
57
+ "step": 0
58
+ },
59
+ {
60
+ "epoch": 0,
61
+ "eval_squad_loss": 4.950023174285889,
62
+ "eval_squad_runtime": 0.9354,
63
+ "eval_squad_samples_per_second": 51.314,
64
+ "eval_squad_steps_per_second": 3.207,
65
+ "step": 0
66
+ },
67
+ {
68
+ "epoch": 0,
69
+ "eval_narrative_qa_loss": 49.38987731933594,
70
+ "eval_narrative_qa_runtime": 1.0306,
71
+ "eval_narrative_qa_samples_per_second": 290.117,
72
+ "eval_narrative_qa_steps_per_second": 18.436,
73
+ "step": 0
74
+ },
75
+ {
76
+ "epoch": 0.01620745542949757,
77
+ "grad_norm": 1336.0,
78
+ "learning_rate": 9.090909090909091e-06,
79
+ "loss": 86.6132,
80
+ "step": 10
81
+ },
82
+ {
83
+ "epoch": 0.03241491085899514,
84
+ "grad_norm": 828.0,
85
+ "learning_rate": 1.8181818181818182e-05,
86
+ "loss": 83.7595,
87
+ "step": 20
88
+ },
89
+ {
90
+ "epoch": 0.04862236628849271,
91
+ "grad_norm": 388.0,
92
+ "learning_rate": 2.7272727272727273e-05,
93
+ "loss": 65.5413,
94
+ "step": 30
95
+ },
96
+ {
97
+ "epoch": 0.06482982171799027,
98
+ "grad_norm": 320.0,
99
+ "learning_rate": 3.6363636363636364e-05,
100
+ "loss": 40.6319,
101
+ "step": 40
102
+ },
103
+ {
104
+ "epoch": 0.08103727714748785,
105
+ "grad_norm": 296.0,
106
+ "learning_rate": 4.545454545454546e-05,
107
+ "loss": 26.2768,
108
+ "step": 50
109
+ },
110
+ {
111
+ "epoch": 0.09724473257698542,
112
+ "grad_norm": 290.0,
113
+ "learning_rate": 4.9997781212386585e-05,
114
+ "loss": 14.4879,
115
+ "step": 60
116
+ },
117
+ {
118
+ "epoch": 0.11345218800648298,
119
+ "grad_norm": 160.0,
120
+ "learning_rate": 4.9980033274458193e-05,
121
+ "loss": 9.4888,
122
+ "step": 70
123
+ },
124
+ {
125
+ "epoch": 0.12965964343598055,
126
+ "grad_norm": 212.0,
127
+ "learning_rate": 4.994454999929178e-05,
128
+ "loss": 8.831,
129
+ "step": 80
130
+ },
131
+ {
132
+ "epoch": 0.1458670988654781,
133
+ "grad_norm": 109.0,
134
+ "learning_rate": 4.98913565793218e-05,
135
+ "loss": 7.6776,
136
+ "step": 90
137
+ },
138
+ {
139
+ "epoch": 0.1620745542949757,
140
+ "grad_norm": 71.5,
141
+ "learning_rate": 4.982049078084071e-05,
142
+ "loss": 6.4716,
143
+ "step": 100
144
+ },
145
+ {
146
+ "epoch": 0.1620745542949757,
147
+ "eval_NanoBEIR_mean_cosine_accuracy@1": 0.32666666666666666,
148
+ "eval_NanoBEIR_mean_cosine_accuracy@5": 0.6333333333333333,
149
+ "eval_NanoBEIR_mean_cosine_map@100": 0.39934768753390587,
150
+ "eval_NanoBEIR_mean_cosine_mrr@10": 0.4495740740740741,
151
+ "eval_NanoBEIR_mean_cosine_ndcg@1": 0.32666666666666666,
152
+ "eval_NanoBEIR_mean_cosine_ndcg@5": 0.43241374431385005,
153
+ "eval_NanoBEIR_mean_cosine_precision@1": 0.32666666666666666,
154
+ "eval_NanoBEIR_mean_cosine_precision@5": 0.13466666666666668,
155
+ "eval_NanoBEIR_mean_cosine_recall@1": 0.25666666666666665,
156
+ "eval_NanoBEIR_mean_cosine_recall@5": 0.5466666666666667,
157
+ "eval_NanoFEVER_cosine_accuracy@1": 0.24,
158
+ "eval_NanoFEVER_cosine_accuracy@5": 0.66,
159
+ "eval_NanoFEVER_cosine_map@100": 0.3935747452453245,
160
+ "eval_NanoFEVER_cosine_mrr@10": 0.39322222222222225,
161
+ "eval_NanoFEVER_cosine_ndcg@1": 0.24,
162
+ "eval_NanoFEVER_cosine_ndcg@5": 0.4387408055008589,
163
+ "eval_NanoFEVER_cosine_precision@1": 0.24,
164
+ "eval_NanoFEVER_cosine_precision@5": 0.132,
165
+ "eval_NanoFEVER_cosine_recall@1": 0.24,
166
+ "eval_NanoFEVER_cosine_recall@5": 0.63,
167
+ "eval_NanoHotpotQA_cosine_accuracy@1": 0.42,
168
+ "eval_NanoHotpotQA_cosine_accuracy@5": 0.58,
169
+ "eval_NanoHotpotQA_cosine_map@100": 0.3274226457297244,
170
+ "eval_NanoHotpotQA_cosine_mrr@10": 0.4911666666666667,
171
+ "eval_NanoHotpotQA_cosine_ndcg@1": 0.42,
172
+ "eval_NanoHotpotQA_cosine_ndcg@5": 0.35120107956309937,
173
+ "eval_NanoHotpotQA_cosine_precision@1": 0.42,
174
+ "eval_NanoHotpotQA_cosine_precision@5": 0.14,
175
+ "eval_NanoHotpotQA_cosine_recall@1": 0.21,
176
+ "eval_NanoHotpotQA_cosine_recall@5": 0.35,
177
+ "eval_NanoMSMARCO_cosine_accuracy@1": 0.32,
178
+ "eval_NanoMSMARCO_cosine_accuracy@5": 0.66,
179
+ "eval_NanoMSMARCO_cosine_map@100": 0.47704567162666855,
180
+ "eval_NanoMSMARCO_cosine_mrr@10": 0.4643333333333334,
181
+ "eval_NanoMSMARCO_cosine_ndcg@1": 0.32,
182
+ "eval_NanoMSMARCO_cosine_ndcg@5": 0.5072993478775919,
183
+ "eval_NanoMSMARCO_cosine_precision@1": 0.32,
184
+ "eval_NanoMSMARCO_cosine_precision@5": 0.132,
185
+ "eval_NanoMSMARCO_cosine_recall@1": 0.32,
186
+ "eval_NanoMSMARCO_cosine_recall@5": 0.66,
187
+ "eval_mldr_loss": 4.950920581817627,
188
+ "eval_mldr_runtime": 14.3444,
189
+ "eval_mldr_samples_per_second": 34.857,
190
+ "eval_mldr_steps_per_second": 2.231,
191
+ "step": 100
192
+ },
193
+ {
194
+ "epoch": 0.1620745542949757,
195
+ "eval_squad_loss": 2.0146381855010986,
196
+ "eval_squad_runtime": 0.9385,
197
+ "eval_squad_samples_per_second": 51.146,
198
+ "eval_squad_steps_per_second": 3.197,
199
+ "step": 100
200
+ },
201
+ {
202
+ "epoch": 0.1620745542949757,
203
+ "eval_narrative_qa_loss": 4.486134052276611,
204
+ "eval_narrative_qa_runtime": 1.1506,
205
+ "eval_narrative_qa_samples_per_second": 259.856,
206
+ "eval_narrative_qa_steps_per_second": 16.513,
207
+ "step": 100
208
+ },
209
+ {
210
+ "epoch": 0.17828200972447325,
211
+ "grad_norm": 107.5,
212
+ "learning_rate": 4.973200291718561e-05,
213
+ "loss": 6.1959,
214
+ "step": 110
215
+ },
216
+ {
217
+ "epoch": 0.19448946515397084,
218
+ "grad_norm": 50.75,
219
+ "learning_rate": 4.962595581301673e-05,
220
+ "loss": 4.5491,
221
+ "step": 120
222
+ },
223
+ {
224
+ "epoch": 0.2106969205834684,
225
+ "grad_norm": 50.25,
226
+ "learning_rate": 4.95024247597132e-05,
227
+ "loss": 4.0871,
228
+ "step": 130
229
+ },
230
+ {
231
+ "epoch": 0.22690437601296595,
232
+ "grad_norm": 53.25,
233
+ "learning_rate": 4.936149746191758e-05,
234
+ "loss": 3.0861,
235
+ "step": 140
236
+ },
237
+ {
238
+ "epoch": 0.24311183144246354,
239
+ "grad_norm": 25.5,
240
+ "learning_rate": 4.920327397526731e-05,
241
+ "loss": 2.7792,
242
+ "step": 150
243
+ },
244
+ {
245
+ "epoch": 0.2593192868719611,
246
+ "grad_norm": 122.0,
247
+ "learning_rate": 4.9027866635357136e-05,
248
+ "loss": 2.2107,
249
+ "step": 160
250
+ },
251
+ {
252
+ "epoch": 0.2755267423014587,
253
+ "grad_norm": 410.0,
254
+ "learning_rate": 4.883539997798303e-05,
255
+ "loss": 1.6997,
256
+ "step": 170
257
+ },
258
+ {
259
+ "epoch": 0.2917341977309562,
260
+ "grad_norm": 66.0,
261
+ "learning_rate": 4.8626010650724204e-05,
262
+ "loss": 1.4911,
263
+ "step": 180
264
+ },
265
+ {
266
+ "epoch": 0.3079416531604538,
267
+ "grad_norm": 1072.0,
268
+ "learning_rate": 4.8399847315926e-05,
269
+ "loss": 1.6304,
270
+ "step": 190
271
+ },
272
+ {
273
+ "epoch": 0.3241491085899514,
274
+ "grad_norm": 16.5,
275
+ "learning_rate": 4.815707054515248e-05,
276
+ "loss": 1.5042,
277
+ "step": 200
278
+ },
279
+ {
280
+ "epoch": 0.3241491085899514,
281
+ "eval_NanoBEIR_mean_cosine_accuracy@1": 0.24666666666666667,
282
+ "eval_NanoBEIR_mean_cosine_accuracy@5": 0.4533333333333333,
283
+ "eval_NanoBEIR_mean_cosine_map@100": 0.2917657022707883,
284
+ "eval_NanoBEIR_mean_cosine_mrr@10": 0.3391984126984127,
285
+ "eval_NanoBEIR_mean_cosine_ndcg@1": 0.24666666666666667,
286
+ "eval_NanoBEIR_mean_cosine_ndcg@5": 0.3047832475255773,
287
+ "eval_NanoBEIR_mean_cosine_precision@1": 0.24666666666666667,
288
+ "eval_NanoBEIR_mean_cosine_precision@5": 0.09466666666666669,
289
+ "eval_NanoBEIR_mean_cosine_recall@1": 0.18333333333333335,
290
+ "eval_NanoBEIR_mean_cosine_recall@5": 0.37333333333333335,
291
+ "eval_NanoFEVER_cosine_accuracy@1": 0.08,
292
+ "eval_NanoFEVER_cosine_accuracy@5": 0.26,
293
+ "eval_NanoFEVER_cosine_map@100": 0.15831046306304816,
294
+ "eval_NanoFEVER_cosine_mrr@10": 0.1541904761904762,
295
+ "eval_NanoFEVER_cosine_ndcg@1": 0.08,
296
+ "eval_NanoFEVER_cosine_ndcg@5": 0.15530091408199076,
297
+ "eval_NanoFEVER_cosine_precision@1": 0.08,
298
+ "eval_NanoFEVER_cosine_precision@5": 0.052000000000000005,
299
+ "eval_NanoFEVER_cosine_recall@1": 0.07,
300
+ "eval_NanoFEVER_cosine_recall@5": 0.24,
301
+ "eval_NanoHotpotQA_cosine_accuracy@1": 0.36,
302
+ "eval_NanoHotpotQA_cosine_accuracy@5": 0.5,
303
+ "eval_NanoHotpotQA_cosine_map@100": 0.2657203181494037,
304
+ "eval_NanoHotpotQA_cosine_mrr@10": 0.4257142857142857,
305
+ "eval_NanoHotpotQA_cosine_ndcg@1": 0.36,
306
+ "eval_NanoHotpotQA_cosine_ndcg@5": 0.2891308855457201,
307
+ "eval_NanoHotpotQA_cosine_precision@1": 0.36,
308
+ "eval_NanoHotpotQA_cosine_precision@5": 0.11200000000000003,
309
+ "eval_NanoHotpotQA_cosine_recall@1": 0.18,
310
+ "eval_NanoHotpotQA_cosine_recall@5": 0.28,
311
+ "eval_NanoMSMARCO_cosine_accuracy@1": 0.3,
312
+ "eval_NanoMSMARCO_cosine_accuracy@5": 0.6,
313
+ "eval_NanoMSMARCO_cosine_map@100": 0.45126632559991314,
314
+ "eval_NanoMSMARCO_cosine_mrr@10": 0.4376904761904762,
315
+ "eval_NanoMSMARCO_cosine_ndcg@1": 0.3,
316
+ "eval_NanoMSMARCO_cosine_ndcg@5": 0.46991794294902106,
317
+ "eval_NanoMSMARCO_cosine_precision@1": 0.3,
318
+ "eval_NanoMSMARCO_cosine_precision@5": 0.12000000000000002,
319
+ "eval_NanoMSMARCO_cosine_recall@1": 0.3,
320
+ "eval_NanoMSMARCO_cosine_recall@5": 0.6,
321
+ "eval_mldr_loss": 1.3893917798995972,
322
+ "eval_mldr_runtime": 14.4056,
323
+ "eval_mldr_samples_per_second": 34.709,
324
+ "eval_mldr_steps_per_second": 2.221,
325
+ "step": 200
326
+ },
327
+ {
328
+ "epoch": 0.3241491085899514,
329
+ "eval_squad_loss": 0.7646868824958801,
330
+ "eval_squad_runtime": 1.072,
331
+ "eval_squad_samples_per_second": 44.776,
332
+ "eval_squad_steps_per_second": 2.799,
333
+ "step": 200
334
+ },
335
+ {
336
+ "epoch": 0.3241491085899514,
337
+ "eval_narrative_qa_loss": 2.59745192527771,
338
+ "eval_narrative_qa_runtime": 1.1589,
339
+ "eval_narrative_qa_samples_per_second": 257.994,
340
+ "eval_narrative_qa_steps_per_second": 16.394,
341
+ "step": 200
342
+ },
343
+ {
344
+ "epoch": 0.34035656401944897,
345
+ "grad_norm": 35.0,
346
+ "learning_rate": 4.7897852705183785e-05,
347
+ "loss": 1.6009,
348
+ "step": 210
349
+ },
350
+ {
351
+ "epoch": 0.3565640194489465,
352
+ "grad_norm": 1352.0,
353
+ "learning_rate": 4.7622377835639064e-05,
354
+ "loss": 1.5156,
355
+ "step": 220
356
+ },
357
+ {
358
+ "epoch": 0.3727714748784441,
359
+ "grad_norm": 704.0,
360
+ "learning_rate": 4.73308415183119e-05,
361
+ "loss": 1.5305,
362
+ "step": 230
363
+ },
364
+ {
365
+ "epoch": 0.3889789303079417,
366
+ "grad_norm": 824.0,
367
+ "learning_rate": 4.702345073831109e-05,
368
+ "loss": 1.6842,
369
+ "step": 240
370
+ },
371
+ {
372
+ "epoch": 0.4051863857374392,
373
+ "grad_norm": 21760.0,
374
+ "learning_rate": 4.6700423737105236e-05,
375
+ "loss": 1.2207,
376
+ "step": 250
377
+ },
378
+ {
379
+ "epoch": 0.4213938411669368,
380
+ "grad_norm": 3040.0,
381
+ "learning_rate": 4.63619898575755e-05,
382
+ "loss": 1.2634,
383
+ "step": 260
384
+ },
385
+ {
386
+ "epoch": 0.4376012965964344,
387
+ "grad_norm": 46.5,
388
+ "learning_rate": 4.600838938118672e-05,
389
+ "loss": 1.3175,
390
+ "step": 270
391
+ },
392
+ {
393
+ "epoch": 0.4538087520259319,
394
+ "grad_norm": 6112.0,
395
+ "learning_rate": 4.563987335739216e-05,
396
+ "loss": 1.3107,
397
+ "step": 280
398
+ },
399
+ {
400
+ "epoch": 0.4700162074554295,
401
+ "grad_norm": 2256.0,
402
+ "learning_rate": 4.525670342539332e-05,
403
+ "loss": 1.3163,
404
+ "step": 290
405
+ },
406
+ {
407
+ "epoch": 0.4862236628849271,
408
+ "grad_norm": 860.0,
409
+ "learning_rate": 4.485915162838122e-05,
410
+ "loss": 1.3703,
411
+ "step": 300
412
+ },
413
+ {
414
+ "epoch": 0.4862236628849271,
415
+ "eval_NanoBEIR_mean_cosine_accuracy@1": 0.18666666666666668,
416
+ "eval_NanoBEIR_mean_cosine_accuracy@5": 0.37333333333333335,
417
+ "eval_NanoBEIR_mean_cosine_map@100": 0.24055436231400043,
418
+ "eval_NanoBEIR_mean_cosine_mrr@10": 0.26788624338624334,
419
+ "eval_NanoBEIR_mean_cosine_ndcg@1": 0.18666666666666668,
420
+ "eval_NanoBEIR_mean_cosine_ndcg@5": 0.24938490224868604,
421
+ "eval_NanoBEIR_mean_cosine_precision@1": 0.18666666666666668,
422
+ "eval_NanoBEIR_mean_cosine_precision@5": 0.07733333333333335,
423
+ "eval_NanoBEIR_mean_cosine_recall@1": 0.15,
424
+ "eval_NanoBEIR_mean_cosine_recall@5": 0.31666666666666665,
425
+ "eval_NanoFEVER_cosine_accuracy@1": 0.06,
426
+ "eval_NanoFEVER_cosine_accuracy@5": 0.18,
427
+ "eval_NanoFEVER_cosine_map@100": 0.11320690658806287,
428
+ "eval_NanoFEVER_cosine_mrr@10": 0.11538888888888887,
429
+ "eval_NanoFEVER_cosine_ndcg@1": 0.06,
430
+ "eval_NanoFEVER_cosine_ndcg@5": 0.11246425246579403,
431
+ "eval_NanoFEVER_cosine_precision@1": 0.06,
432
+ "eval_NanoFEVER_cosine_precision@5": 0.036000000000000004,
433
+ "eval_NanoFEVER_cosine_recall@1": 0.05,
434
+ "eval_NanoFEVER_cosine_recall@5": 0.17,
435
+ "eval_NanoHotpotQA_cosine_accuracy@1": 0.2,
436
+ "eval_NanoHotpotQA_cosine_accuracy@5": 0.36,
437
+ "eval_NanoHotpotQA_cosine_map@100": 0.17264044237203358,
438
+ "eval_NanoHotpotQA_cosine_mrr@10": 0.26374603174603173,
439
+ "eval_NanoHotpotQA_cosine_ndcg@1": 0.2,
440
+ "eval_NanoHotpotQA_cosine_ndcg@5": 0.18589124040083965,
441
+ "eval_NanoHotpotQA_cosine_precision@1": 0.2,
442
+ "eval_NanoHotpotQA_cosine_precision@5": 0.08,
443
+ "eval_NanoHotpotQA_cosine_recall@1": 0.1,
444
+ "eval_NanoHotpotQA_cosine_recall@5": 0.2,
445
+ "eval_NanoMSMARCO_cosine_accuracy@1": 0.3,
446
+ "eval_NanoMSMARCO_cosine_accuracy@5": 0.58,
447
+ "eval_NanoMSMARCO_cosine_map@100": 0.4358157379819049,
448
+ "eval_NanoMSMARCO_cosine_mrr@10": 0.42452380952380947,
449
+ "eval_NanoMSMARCO_cosine_ndcg@1": 0.3,
450
+ "eval_NanoMSMARCO_cosine_ndcg@5": 0.44979921387942445,
451
+ "eval_NanoMSMARCO_cosine_precision@1": 0.3,
452
+ "eval_NanoMSMARCO_cosine_precision@5": 0.11600000000000002,
453
+ "eval_NanoMSMARCO_cosine_recall@1": 0.3,
454
+ "eval_NanoMSMARCO_cosine_recall@5": 0.58,
455
+ "eval_mldr_loss": 1.218342900276184,
456
+ "eval_mldr_runtime": 14.4679,
457
+ "eval_mldr_samples_per_second": 34.559,
458
+ "eval_mldr_steps_per_second": 2.212,
459
+ "step": 300
460
+ },
461
+ {
462
+ "epoch": 0.4862236628849271,
463
+ "eval_squad_loss": 1.0243560075759888,
464
+ "eval_squad_runtime": 0.9647,
465
+ "eval_squad_samples_per_second": 49.755,
466
+ "eval_squad_steps_per_second": 3.11,
467
+ "step": 300
468
+ },
469
+ {
470
+ "epoch": 0.4862236628849271,
471
+ "eval_narrative_qa_loss": 2.635084629058838,
472
+ "eval_narrative_qa_runtime": 1.1616,
473
+ "eval_narrative_qa_samples_per_second": 257.409,
474
+ "eval_narrative_qa_steps_per_second": 16.357,
475
+ "step": 300
476
+ },
477
+ {
478
+ "epoch": 0.5024311183144247,
479
+ "grad_norm": 39.25,
480
+ "learning_rate": 4.444750022039099e-05,
481
+ "loss": 1.2901,
482
+ "step": 310
483
+ },
484
+ {
485
+ "epoch": 0.5186385737439222,
486
+ "grad_norm": 260.0,
487
+ "learning_rate": 4.4022041465907036e-05,
488
+ "loss": 1.245,
489
+ "step": 320
490
+ },
491
+ {
492
+ "epoch": 0.5348460291734197,
493
+ "grad_norm": 2192.0,
494
+ "learning_rate": 4.358307743236092e-05,
495
+ "loss": 1.1749,
496
+ "step": 330
497
+ },
498
+ {
499
+ "epoch": 0.5510534846029174,
500
+ "grad_norm": 1064.0,
501
+ "learning_rate": 4.3130919775669374e-05,
502
+ "loss": 1.0522,
503
+ "step": 340
504
+ },
505
+ {
506
+ "epoch": 0.5672609400324149,
507
+ "grad_norm": 1120.0,
508
+ "learning_rate": 4.2665889518964684e-05,
509
+ "loss": 1.1319,
510
+ "step": 350
511
+ },
512
+ {
513
+ "epoch": 0.5834683954619124,
514
+ "grad_norm": 1552.0,
515
+ "learning_rate": 4.2188316824674504e-05,
516
+ "loss": 1.1986,
517
+ "step": 360
518
+ },
519
+ {
520
+ "epoch": 0.5996758508914101,
521
+ "grad_norm": 133.0,
522
+ "learning_rate": 4.169854076011292e-05,
523
+ "loss": 1.3508,
524
+ "step": 370
525
+ },
526
+ {
527
+ "epoch": 0.6158833063209076,
528
+ "grad_norm": 5408.0,
529
+ "learning_rate": 4.119690905674937e-05,
530
+ "loss": 1.3465,
531
+ "step": 380
532
+ },
533
+ {
534
+ "epoch": 0.6320907617504052,
535
+ "grad_norm": 1624.0,
536
+ "learning_rate": 4.068377786332593e-05,
537
+ "loss": 1.3062,
538
+ "step": 390
539
+ },
540
+ {
541
+ "epoch": 0.6482982171799028,
542
+ "grad_norm": 1192.0,
543
+ "learning_rate": 4.0159511492998746e-05,
544
+ "loss": 0.9974,
545
+ "step": 400
546
+ },
547
+ {
548
+ "epoch": 0.6482982171799028,
549
+ "eval_NanoBEIR_mean_cosine_accuracy@1": 0.20000000000000004,
550
+ "eval_NanoBEIR_mean_cosine_accuracy@5": 0.39333333333333337,
551
+ "eval_NanoBEIR_mean_cosine_map@100": 0.25566257669608067,
552
+ "eval_NanoBEIR_mean_cosine_mrr@10": 0.2828835978835979,
553
+ "eval_NanoBEIR_mean_cosine_ndcg@1": 0.20000000000000004,
554
+ "eval_NanoBEIR_mean_cosine_ndcg@5": 0.2711361604281084,
555
+ "eval_NanoBEIR_mean_cosine_precision@1": 0.20000000000000004,
556
+ "eval_NanoBEIR_mean_cosine_precision@5": 0.08266666666666668,
557
+ "eval_NanoBEIR_mean_cosine_recall@1": 0.16333333333333333,
558
+ "eval_NanoBEIR_mean_cosine_recall@5": 0.3433333333333333,
559
+ "eval_NanoFEVER_cosine_accuracy@1": 0.08,
560
+ "eval_NanoFEVER_cosine_accuracy@5": 0.2,
561
+ "eval_NanoFEVER_cosine_map@100": 0.12628338770667222,
562
+ "eval_NanoFEVER_cosine_mrr@10": 0.1275,
563
+ "eval_NanoFEVER_cosine_ndcg@1": 0.08,
564
+ "eval_NanoFEVER_cosine_ndcg@5": 0.1285946755597121,
565
+ "eval_NanoFEVER_cosine_precision@1": 0.08,
566
+ "eval_NanoFEVER_cosine_precision@5": 0.04,
567
+ "eval_NanoFEVER_cosine_recall@1": 0.07,
568
+ "eval_NanoFEVER_cosine_recall@5": 0.18,
569
+ "eval_NanoHotpotQA_cosine_accuracy@1": 0.2,
570
+ "eval_NanoHotpotQA_cosine_accuracy@5": 0.32,
571
+ "eval_NanoHotpotQA_cosine_map@100": 0.17161850356661693,
572
+ "eval_NanoHotpotQA_cosine_mrr@10": 0.26146031746031745,
573
+ "eval_NanoHotpotQA_cosine_ndcg@1": 0.2,
574
+ "eval_NanoHotpotQA_cosine_ndcg@5": 0.18168469434151963,
575
+ "eval_NanoHotpotQA_cosine_precision@1": 0.2,
576
+ "eval_NanoHotpotQA_cosine_precision@5": 0.07600000000000001,
577
+ "eval_NanoHotpotQA_cosine_recall@1": 0.1,
578
+ "eval_NanoHotpotQA_cosine_recall@5": 0.19,
579
+ "eval_NanoMSMARCO_cosine_accuracy@1": 0.32,
580
+ "eval_NanoMSMARCO_cosine_accuracy@5": 0.66,
581
+ "eval_NanoMSMARCO_cosine_map@100": 0.4690858388149529,
582
+ "eval_NanoMSMARCO_cosine_mrr@10": 0.45969047619047615,
583
+ "eval_NanoMSMARCO_cosine_ndcg@1": 0.32,
584
+ "eval_NanoMSMARCO_cosine_ndcg@5": 0.5031291113830936,
585
+ "eval_NanoMSMARCO_cosine_precision@1": 0.32,
586
+ "eval_NanoMSMARCO_cosine_precision@5": 0.132,
587
+ "eval_NanoMSMARCO_cosine_recall@1": 0.32,
588
+ "eval_NanoMSMARCO_cosine_recall@5": 0.66,
589
+ "eval_mldr_loss": 1.7250500917434692,
590
+ "eval_mldr_runtime": 14.4371,
591
+ "eval_mldr_samples_per_second": 34.633,
592
+ "eval_mldr_steps_per_second": 2.217,
593
+ "step": 400
594
+ },
595
+ {
596
+ "epoch": 0.6482982171799028,
597
+ "eval_squad_loss": 0.8224272131919861,
598
+ "eval_squad_runtime": 0.9831,
599
+ "eval_squad_samples_per_second": 48.823,
600
+ "eval_squad_steps_per_second": 3.051,
601
+ "step": 400
602
+ },
603
+ {
604
+ "epoch": 0.6482982171799028,
605
+ "eval_narrative_qa_loss": 2.191936492919922,
606
+ "eval_narrative_qa_runtime": 1.1776,
607
+ "eval_narrative_qa_samples_per_second": 253.914,
608
+ "eval_narrative_qa_steps_per_second": 16.135,
609
+ "step": 400
610
+ },
611
+ {
612
+ "epoch": 0.6645056726094003,
613
+ "grad_norm": 796.0,
614
+ "learning_rate": 3.962448216468275e-05,
615
+ "loss": 3.2988,
616
+ "step": 410
617
+ },
618
+ {
619
+ "epoch": 0.6807131280388979,
620
+ "grad_norm": 9216.0,
621
+ "learning_rate": 3.9079069738783484e-05,
622
+ "loss": 1.3305,
623
+ "step": 420
624
+ },
625
+ {
626
+ "epoch": 0.6969205834683955,
627
+ "grad_norm": 227.0,
628
+ "learning_rate": 3.852366144750358e-05,
629
+ "loss": 1.2771,
630
+ "step": 430
631
+ },
632
+ {
633
+ "epoch": 0.713128038897893,
634
+ "grad_norm": 1456.0,
635
+ "learning_rate": 3.7958651619915495e-05,
636
+ "loss": 1.0724,
637
+ "step": 440
638
+ },
639
+ {
640
+ "epoch": 0.7293354943273906,
641
+ "grad_norm": 704.0,
642
+ "learning_rate": 3.738444140199549e-05,
643
+ "loss": 1.2473,
644
+ "step": 450
645
+ },
646
+ {
647
+ "epoch": 0.7455429497568882,
648
+ "grad_norm": 4608.0,
649
+ "learning_rate": 3.680143847181783e-05,
650
+ "loss": 1.4045,
651
+ "step": 460
652
+ },
653
+ {
654
+ "epoch": 0.7617504051863857,
655
+ "grad_norm": 8384.0,
656
+ "learning_rate": 3.621005675011127e-05,
657
+ "loss": 1.6167,
658
+ "step": 470
659
+ },
660
+ {
661
+ "epoch": 0.7779578606158833,
662
+ "grad_norm": 10752.0,
663
+ "learning_rate": 3.5610716106383426e-05,
664
+ "loss": 1.427,
665
+ "step": 480
666
+ },
667
+ {
668
+ "epoch": 0.7941653160453809,
669
+ "grad_norm": 32512.0,
670
+ "learning_rate": 3.500384206082155e-05,
671
+ "loss": 1.256,
672
+ "step": 490
673
+ },
674
+ {
675
+ "epoch": 0.8103727714748784,
676
+ "grad_norm": 2080.0,
677
+ "learning_rate": 3.438986548218155e-05,
678
+ "loss": 1.7336,
679
+ "step": 500
680
+ },
681
+ {
682
+ "epoch": 0.8103727714748784,
683
+ "eval_NanoBEIR_mean_cosine_accuracy@1": 0.22666666666666668,
684
+ "eval_NanoBEIR_mean_cosine_accuracy@5": 0.35333333333333333,
685
+ "eval_NanoBEIR_mean_cosine_map@100": 0.25285734426656203,
686
+ "eval_NanoBEIR_mean_cosine_mrr@10": 0.28679100529100526,
687
+ "eval_NanoBEIR_mean_cosine_ndcg@1": 0.22666666666666668,
688
+ "eval_NanoBEIR_mean_cosine_ndcg@5": 0.26096692405722594,
689
+ "eval_NanoBEIR_mean_cosine_precision@1": 0.22666666666666668,
690
+ "eval_NanoBEIR_mean_cosine_precision@5": 0.07600000000000001,
691
+ "eval_NanoBEIR_mean_cosine_recall@1": 0.17666666666666667,
692
+ "eval_NanoBEIR_mean_cosine_recall@5": 0.31,
693
+ "eval_NanoFEVER_cosine_accuracy@1": 0.08,
694
+ "eval_NanoFEVER_cosine_accuracy@5": 0.18,
695
+ "eval_NanoFEVER_cosine_map@100": 0.11514089868666741,
696
+ "eval_NanoFEVER_cosine_mrr@10": 0.11641269841269843,
697
+ "eval_NanoFEVER_cosine_ndcg@1": 0.08,
698
+ "eval_NanoFEVER_cosine_ndcg@5": 0.11458961164975079,
699
+ "eval_NanoFEVER_cosine_precision@1": 0.08,
700
+ "eval_NanoFEVER_cosine_precision@5": 0.036000000000000004,
701
+ "eval_NanoFEVER_cosine_recall@1": 0.07,
702
+ "eval_NanoFEVER_cosine_recall@5": 0.16,
703
+ "eval_NanoHotpotQA_cosine_accuracy@1": 0.28,
704
+ "eval_NanoHotpotQA_cosine_accuracy@5": 0.3,
705
+ "eval_NanoHotpotQA_cosine_map@100": 0.1921273663105645,
706
+ "eval_NanoHotpotQA_cosine_mrr@10": 0.3077380952380952,
707
+ "eval_NanoHotpotQA_cosine_ndcg@1": 0.28,
708
+ "eval_NanoHotpotQA_cosine_ndcg@5": 0.202243938877232,
709
+ "eval_NanoHotpotQA_cosine_precision@1": 0.28,
710
+ "eval_NanoHotpotQA_cosine_precision@5": 0.07600000000000001,
711
+ "eval_NanoHotpotQA_cosine_recall@1": 0.14,
712
+ "eval_NanoHotpotQA_cosine_recall@5": 0.19,
713
+ "eval_NanoMSMARCO_cosine_accuracy@1": 0.32,
714
+ "eval_NanoMSMARCO_cosine_accuracy@5": 0.58,
715
+ "eval_NanoMSMARCO_cosine_map@100": 0.4513037678024542,
716
+ "eval_NanoMSMARCO_cosine_mrr@10": 0.4362222222222223,
717
+ "eval_NanoMSMARCO_cosine_ndcg@1": 0.32,
718
+ "eval_NanoMSMARCO_cosine_ndcg@5": 0.4660672216446949,
719
+ "eval_NanoMSMARCO_cosine_precision@1": 0.32,
720
+ "eval_NanoMSMARCO_cosine_precision@5": 0.11600000000000002,
721
+ "eval_NanoMSMARCO_cosine_recall@1": 0.32,
722
+ "eval_NanoMSMARCO_cosine_recall@5": 0.58,
723
+ "eval_mldr_loss": 1.2118109464645386,
724
+ "eval_mldr_runtime": 14.4727,
725
+ "eval_mldr_samples_per_second": 34.548,
726
+ "eval_mldr_steps_per_second": 2.211,
727
+ "step": 500
728
+ },
729
+ {
730
+ "epoch": 0.8103727714748784,
731
+ "eval_squad_loss": 0.669793426990509,
732
+ "eval_squad_runtime": 0.9528,
733
+ "eval_squad_samples_per_second": 50.377,
734
+ "eval_squad_steps_per_second": 3.149,
735
+ "step": 500
736
+ },
737
+ {
738
+ "epoch": 0.8103727714748784,
739
+ "eval_narrative_qa_loss": 2.0540804862976074,
740
+ "eval_narrative_qa_runtime": 1.1722,
741
+ "eval_narrative_qa_samples_per_second": 255.077,
742
+ "eval_narrative_qa_steps_per_second": 16.209,
743
+ "step": 500
744
+ },
745
+ {
746
+ "epoch": 0.826580226904376,
747
+ "grad_norm": 5792.0,
748
+ "learning_rate": 3.3769222281879495e-05,
749
+ "loss": 0.9241,
750
+ "step": 510
751
+ },
752
+ {
753
+ "epoch": 0.8427876823338736,
754
+ "grad_norm": 1080.0,
755
+ "learning_rate": 3.314235310450306e-05,
756
+ "loss": 1.2186,
757
+ "step": 520
758
+ },
759
+ {
760
+ "epoch": 0.8589951377633711,
761
+ "grad_norm": 1264.0,
762
+ "learning_rate": 3.250970301496237e-05,
763
+ "loss": 1.3873,
764
+ "step": 530
765
+ },
766
+ {
767
+ "epoch": 0.8752025931928687,
768
+ "grad_norm": 308.0,
769
+ "learning_rate": 3.187172118250266e-05,
770
+ "loss": 1.299,
771
+ "step": 540
772
+ },
773
+ {
774
+ "epoch": 0.8914100486223663,
775
+ "grad_norm": 5568.0,
776
+ "learning_rate": 3.122886056180284e-05,
777
+ "loss": 1.4101,
778
+ "step": 550
779
+ },
780
+ {
781
+ "epoch": 0.9076175040518638,
782
+ "grad_norm": 1480.0,
783
+ "learning_rate": 3.0581577571386426e-05,
784
+ "loss": 1.047,
785
+ "step": 560
786
+ },
787
+ {
788
+ "epoch": 0.9238249594813615,
789
+ "grad_norm": 34.0,
790
+ "learning_rate": 2.9930331769573365e-05,
791
+ "loss": 1.1558,
792
+ "step": 570
793
+ },
794
+ {
795
+ "epoch": 0.940032414910859,
796
+ "grad_norm": 4640.0,
797
+ "learning_rate": 2.9275585528202516e-05,
798
+ "loss": 1.1769,
799
+ "step": 580
800
+ },
801
+ {
802
+ "epoch": 0.9562398703403565,
803
+ "grad_norm": 191.0,
804
+ "learning_rate": 2.8617803704356672e-05,
805
+ "loss": 1.1054,
806
+ "step": 590
807
+ },
808
+ {
809
+ "epoch": 0.9724473257698542,
810
+ "grad_norm": 167.0,
811
+ "learning_rate": 2.7957453310323073e-05,
812
+ "loss": 3.6745,
813
+ "step": 600
814
+ },
815
+ {
816
+ "epoch": 0.9724473257698542,
817
+ "eval_NanoBEIR_mean_cosine_accuracy@1": 0.20666666666666667,
818
+ "eval_NanoBEIR_mean_cosine_accuracy@5": 0.36000000000000004,
819
+ "eval_NanoBEIR_mean_cosine_map@100": 0.24725005259175806,
820
+ "eval_NanoBEIR_mean_cosine_mrr@10": 0.2764206349206349,
821
+ "eval_NanoBEIR_mean_cosine_ndcg@1": 0.20666666666666667,
822
+ "eval_NanoBEIR_mean_cosine_ndcg@5": 0.2557813556128824,
823
+ "eval_NanoBEIR_mean_cosine_precision@1": 0.20666666666666667,
824
+ "eval_NanoBEIR_mean_cosine_precision@5": 0.076,
825
+ "eval_NanoBEIR_mean_cosine_recall@1": 0.16666666666666666,
826
+ "eval_NanoBEIR_mean_cosine_recall@5": 0.31,
827
+ "eval_NanoFEVER_cosine_accuracy@1": 0.1,
828
+ "eval_NanoFEVER_cosine_accuracy@5": 0.12,
829
+ "eval_NanoFEVER_cosine_map@100": 0.12500495211409104,
830
+ "eval_NanoFEVER_cosine_mrr@10": 0.12576984126984128,
831
+ "eval_NanoFEVER_cosine_ndcg@1": 0.1,
832
+ "eval_NanoFEVER_cosine_ndcg@5": 0.10488153892673832,
833
+ "eval_NanoFEVER_cosine_precision@1": 0.1,
834
+ "eval_NanoFEVER_cosine_precision@5": 0.024000000000000004,
835
+ "eval_NanoFEVER_cosine_recall@1": 0.09,
836
+ "eval_NanoFEVER_cosine_recall@5": 0.11,
837
+ "eval_NanoHotpotQA_cosine_accuracy@1": 0.22,
838
+ "eval_NanoHotpotQA_cosine_accuracy@5": 0.34,
839
+ "eval_NanoHotpotQA_cosine_map@100": 0.17072760263191902,
840
+ "eval_NanoHotpotQA_cosine_mrr@10": 0.2686904761904762,
841
+ "eval_NanoHotpotQA_cosine_ndcg@1": 0.22,
842
+ "eval_NanoHotpotQA_cosine_ndcg@5": 0.19019906156669042,
843
+ "eval_NanoHotpotQA_cosine_precision@1": 0.22,
844
+ "eval_NanoHotpotQA_cosine_precision@5": 0.08,
845
+ "eval_NanoHotpotQA_cosine_recall@1": 0.11,
846
+ "eval_NanoHotpotQA_cosine_recall@5": 0.2,
847
+ "eval_NanoMSMARCO_cosine_accuracy@1": 0.3,
848
+ "eval_NanoMSMARCO_cosine_accuracy@5": 0.62,
849
+ "eval_NanoMSMARCO_cosine_map@100": 0.44601760302926413,
850
+ "eval_NanoMSMARCO_cosine_mrr@10": 0.4348015873015873,
851
+ "eval_NanoMSMARCO_cosine_ndcg@1": 0.3,
852
+ "eval_NanoMSMARCO_cosine_ndcg@5": 0.4722634663452185,
853
+ "eval_NanoMSMARCO_cosine_precision@1": 0.3,
854
+ "eval_NanoMSMARCO_cosine_precision@5": 0.124,
855
+ "eval_NanoMSMARCO_cosine_recall@1": 0.3,
856
+ "eval_NanoMSMARCO_cosine_recall@5": 0.62,
857
+ "eval_mldr_loss": 1.1025381088256836,
858
+ "eval_mldr_runtime": 14.5605,
859
+ "eval_mldr_samples_per_second": 34.339,
860
+ "eval_mldr_steps_per_second": 2.198,
861
+ "step": 600
862
+ },
863
+ {
864
+ "epoch": 0.9724473257698542,
865
+ "eval_squad_loss": 0.7168652415275574,
866
+ "eval_squad_runtime": 0.8907,
867
+ "eval_squad_samples_per_second": 53.891,
868
+ "eval_squad_steps_per_second": 3.368,
869
+ "step": 600
870
+ },
871
+ {
872
+ "epoch": 0.9724473257698542,
873
+ "eval_narrative_qa_loss": 1.757150411605835,
874
+ "eval_narrative_qa_runtime": 1.1289,
875
+ "eval_narrative_qa_samples_per_second": 264.853,
876
+ "eval_narrative_qa_steps_per_second": 16.83,
877
+ "step": 600
878
+ },
879
+ {
880
+ "epoch": 0.9886547811993517,
881
+ "grad_norm": 414.0,
882
+ "learning_rate": 2.7295003182023793e-05,
883
+ "loss": 1.2095,
884
+ "step": 610
885
+ },
886
+ {
887
+ "epoch": 1.0048622366288493,
888
+ "grad_norm": 760.0,
889
+ "learning_rate": 2.663092364615134e-05,
890
+ "loss": 1.0888,
891
+ "step": 620
892
+ },
893
+ {
894
+ "epoch": 1.0210696920583469,
895
+ "grad_norm": 884.0,
896
+ "learning_rate": 2.596568618624588e-05,
897
+ "loss": 1.1728,
898
+ "step": 630
899
+ },
900
+ {
901
+ "epoch": 1.0372771474878444,
902
+ "grad_norm": 1568.0,
903
+ "learning_rate": 2.529976310795108e-05,
904
+ "loss": 1.2033,
905
+ "step": 640
906
+ },
907
+ {
908
+ "epoch": 1.053484602917342,
909
+ "grad_norm": 716.0,
910
+ "learning_rate": 2.4633627203686322e-05,
911
+ "loss": 1.0108,
912
+ "step": 650
913
+ },
914
+ {
915
+ "epoch": 1.0696920583468394,
916
+ "grad_norm": 50.5,
917
+ "learning_rate": 2.3967751416973304e-05,
918
+ "loss": 0.9941,
919
+ "step": 660
920
+ },
921
+ {
922
+ "epoch": 1.0858995137763372,
923
+ "grad_norm": 39.5,
924
+ "learning_rate": 2.3302608506655286e-05,
925
+ "loss": 1.1392,
926
+ "step": 670
927
+ },
928
+ {
929
+ "epoch": 1.1021069692058347,
930
+ "grad_norm": 1000.0,
931
+ "learning_rate": 2.2638670711247605e-05,
932
+ "loss": 1.083,
933
+ "step": 680
934
+ },
935
+ {
936
+ "epoch": 1.1183144246353323,
937
+ "grad_norm": 7456.0,
938
+ "learning_rate": 2.197640941365743e-05,
939
+ "loss": 1.0115,
940
+ "step": 690
941
+ },
942
+ {
943
+ "epoch": 1.1345218800648298,
944
+ "grad_norm": 2944.0,
945
+ "learning_rate": 2.131629480651116e-05,
946
+ "loss": 1.2825,
947
+ "step": 700
948
+ },
949
+ {
950
+ "epoch": 1.1345218800648298,
951
+ "eval_NanoBEIR_mean_cosine_accuracy@1": 0.17333333333333334,
952
+ "eval_NanoBEIR_mean_cosine_accuracy@5": 0.34,
953
+ "eval_NanoBEIR_mean_cosine_map@100": 0.2227183429409336,
954
+ "eval_NanoBEIR_mean_cosine_mrr@10": 0.25063756613756616,
955
+ "eval_NanoBEIR_mean_cosine_ndcg@1": 0.17333333333333334,
956
+ "eval_NanoBEIR_mean_cosine_ndcg@5": 0.23117905501265376,
957
+ "eval_NanoBEIR_mean_cosine_precision@1": 0.17333333333333334,
958
+ "eval_NanoBEIR_mean_cosine_precision@5": 0.07066666666666667,
959
+ "eval_NanoBEIR_mean_cosine_recall@1": 0.14,
960
+ "eval_NanoBEIR_mean_cosine_recall@5": 0.29000000000000004,
961
+ "eval_NanoFEVER_cosine_accuracy@1": 0.06,
962
+ "eval_NanoFEVER_cosine_accuracy@5": 0.14,
963
+ "eval_NanoFEVER_cosine_map@100": 0.10226378102099443,
964
+ "eval_NanoFEVER_cosine_mrr@10": 0.107,
965
+ "eval_NanoFEVER_cosine_ndcg@1": 0.06,
966
+ "eval_NanoFEVER_cosine_ndcg@5": 0.09611366515963533,
967
+ "eval_NanoFEVER_cosine_precision@1": 0.06,
968
+ "eval_NanoFEVER_cosine_precision@5": 0.027999999999999997,
969
+ "eval_NanoFEVER_cosine_recall@1": 0.05,
970
+ "eval_NanoFEVER_cosine_recall@5": 0.13,
971
+ "eval_NanoHotpotQA_cosine_accuracy@1": 0.18,
972
+ "eval_NanoHotpotQA_cosine_accuracy@5": 0.32,
973
+ "eval_NanoHotpotQA_cosine_map@100": 0.1431808584557489,
974
+ "eval_NanoHotpotQA_cosine_mrr@10": 0.2346666666666667,
975
+ "eval_NanoHotpotQA_cosine_ndcg@1": 0.18,
976
+ "eval_NanoHotpotQA_cosine_ndcg@5": 0.16151062083926612,
977
+ "eval_NanoHotpotQA_cosine_precision@1": 0.18,
978
+ "eval_NanoHotpotQA_cosine_precision@5": 0.07200000000000001,
979
+ "eval_NanoHotpotQA_cosine_recall@1": 0.09,
980
+ "eval_NanoHotpotQA_cosine_recall@5": 0.18,
981
+ "eval_NanoMSMARCO_cosine_accuracy@1": 0.28,
982
+ "eval_NanoMSMARCO_cosine_accuracy@5": 0.56,
983
+ "eval_NanoMSMARCO_cosine_map@100": 0.4227103893460575,
984
+ "eval_NanoMSMARCO_cosine_mrr@10": 0.4102460317460318,
985
+ "eval_NanoMSMARCO_cosine_ndcg@1": 0.28,
986
+ "eval_NanoMSMARCO_cosine_ndcg@5": 0.4359128790390598,
987
+ "eval_NanoMSMARCO_cosine_precision@1": 0.28,
988
+ "eval_NanoMSMARCO_cosine_precision@5": 0.11200000000000002,
989
+ "eval_NanoMSMARCO_cosine_recall@1": 0.28,
990
+ "eval_NanoMSMARCO_cosine_recall@5": 0.56,
991
+ "eval_mldr_loss": 1.04865562915802,
992
+ "eval_mldr_runtime": 14.5246,
993
+ "eval_mldr_samples_per_second": 34.424,
994
+ "eval_mldr_steps_per_second": 2.203,
995
+ "step": 700
996
+ },
997
+ {
998
+ "epoch": 1.1345218800648298,
999
+ "eval_squad_loss": 0.7077043652534485,
1000
+ "eval_squad_runtime": 0.907,
1001
+ "eval_squad_samples_per_second": 52.924,
1002
+ "eval_squad_steps_per_second": 3.308,
1003
+ "step": 700
1004
+ },
1005
+ {
1006
+ "epoch": 1.1345218800648298,
1007
+ "eval_narrative_qa_loss": 1.7767502069473267,
1008
+ "eval_narrative_qa_runtime": 1.1658,
1009
+ "eval_narrative_qa_samples_per_second": 256.487,
1010
+ "eval_narrative_qa_steps_per_second": 16.298,
1011
+ "step": 700
1012
+ },
1013
+ {
1014
+ "epoch": 1.1507293354943273,
1015
+ "grad_norm": 1976.0,
1016
+ "learning_rate": 2.0658795558326743e-05,
1017
+ "loss": 1.1286,
1018
+ "step": 710
1019
+ },
1020
+ {
1021
+ "epoch": 1.1669367909238249,
1022
+ "grad_norm": 1640.0,
1023
+ "learning_rate": 2.000437848076822e-05,
1024
+ "loss": 1.174,
1025
+ "step": 720
1026
+ },
1027
+ {
1028
+ "epoch": 1.1831442463533226,
1029
+ "grad_norm": 3776.0,
1030
+ "learning_rate": 1.935350819721849e-05,
1031
+ "loss": 1.124,
1032
+ "step": 730
1033
+ },
1034
+ {
1035
+ "epoch": 1.1993517017828201,
1036
+ "grad_norm": 5568.0,
1037
+ "learning_rate": 1.870664681290575e-05,
1038
+ "loss": 0.9694,
1039
+ "step": 740
1040
+ },
1041
+ {
1042
+ "epoch": 1.2155591572123177,
1043
+ "grad_norm": 532.0,
1044
+ "learning_rate": 1.8064253586817816e-05,
1045
+ "loss": 1.165,
1046
+ "step": 750
1047
+ },
1048
+ {
1049
+ "epoch": 1.2317666126418152,
1050
+ "grad_norm": 928.0,
1051
+ "learning_rate": 1.7426784605637153e-05,
1052
+ "loss": 1.1989,
1053
+ "step": 760
1054
+ },
1055
+ {
1056
+ "epoch": 1.2479740680713127,
1057
+ "grad_norm": 560.0,
1058
+ "learning_rate": 1.6794692459928223e-05,
1059
+ "loss": 0.9966,
1060
+ "step": 770
1061
+ },
1062
+ {
1063
+ "epoch": 1.2641815235008105,
1064
+ "grad_norm": 123.5,
1065
+ "learning_rate": 1.6168425922807008e-05,
1066
+ "loss": 0.9768,
1067
+ "step": 780
1068
+ },
1069
+ {
1070
+ "epoch": 1.280388978930308,
1071
+ "grad_norm": 884.0,
1072
+ "learning_rate": 1.5548429631320806e-05,
1073
+ "loss": 1.1039,
1074
+ "step": 790
1075
+ },
1076
+ {
1077
+ "epoch": 1.2965964343598055,
1078
+ "grad_norm": 15.75,
1079
+ "learning_rate": 1.4935143770764601e-05,
1080
+ "loss": 2.7281,
1081
+ "step": 800
1082
+ },
1083
+ {
1084
+ "epoch": 1.2965964343598055,
1085
+ "eval_NanoBEIR_mean_cosine_accuracy@1": 0.17333333333333334,
1086
+ "eval_NanoBEIR_mean_cosine_accuracy@5": 0.35333333333333333,
1087
+ "eval_NanoBEIR_mean_cosine_map@100": 0.2232392549386716,
1088
+ "eval_NanoBEIR_mean_cosine_mrr@10": 0.24966402116402117,
1089
+ "eval_NanoBEIR_mean_cosine_ndcg@1": 0.17333333333333334,
1090
+ "eval_NanoBEIR_mean_cosine_ndcg@5": 0.23771617121243702,
1091
+ "eval_NanoBEIR_mean_cosine_precision@1": 0.17333333333333334,
1092
+ "eval_NanoBEIR_mean_cosine_precision@5": 0.07333333333333333,
1093
+ "eval_NanoBEIR_mean_cosine_recall@1": 0.1366666666666667,
1094
+ "eval_NanoBEIR_mean_cosine_recall@5": 0.31,
1095
+ "eval_NanoFEVER_cosine_accuracy@1": 0.06,
1096
+ "eval_NanoFEVER_cosine_accuracy@5": 0.16,
1097
+ "eval_NanoFEVER_cosine_map@100": 0.1100930297556344,
1098
+ "eval_NanoFEVER_cosine_mrr@10": 0.11335714285714285,
1099
+ "eval_NanoFEVER_cosine_ndcg@1": 0.06,
1100
+ "eval_NanoFEVER_cosine_ndcg@5": 0.10785578521428746,
1101
+ "eval_NanoFEVER_cosine_precision@1": 0.06,
1102
+ "eval_NanoFEVER_cosine_precision@5": 0.032,
1103
+ "eval_NanoFEVER_cosine_recall@1": 0.05,
1104
+ "eval_NanoFEVER_cosine_recall@5": 0.15,
1105
+ "eval_NanoHotpotQA_cosine_accuracy@1": 0.2,
1106
+ "eval_NanoHotpotQA_cosine_accuracy@5": 0.28,
1107
+ "eval_NanoHotpotQA_cosine_map@100": 0.14784815274029572,
1108
+ "eval_NanoHotpotQA_cosine_mrr@10": 0.2350555555555556,
1109
+ "eval_NanoHotpotQA_cosine_ndcg@1": 0.2,
1110
+ "eval_NanoHotpotQA_cosine_ndcg@5": 0.16017374485985264,
1111
+ "eval_NanoHotpotQA_cosine_precision@1": 0.2,
1112
+ "eval_NanoHotpotQA_cosine_precision@5": 0.064,
1113
+ "eval_NanoHotpotQA_cosine_recall@1": 0.1,
1114
+ "eval_NanoHotpotQA_cosine_recall@5": 0.16,
1115
+ "eval_NanoMSMARCO_cosine_accuracy@1": 0.26,
1116
+ "eval_NanoMSMARCO_cosine_accuracy@5": 0.62,
1117
+ "eval_NanoMSMARCO_cosine_map@100": 0.4117765823200847,
1118
+ "eval_NanoMSMARCO_cosine_mrr@10": 0.40057936507936504,
1119
+ "eval_NanoMSMARCO_cosine_ndcg@1": 0.26,
1120
+ "eval_NanoMSMARCO_cosine_ndcg@5": 0.445118983563171,
1121
+ "eval_NanoMSMARCO_cosine_precision@1": 0.26,
1122
+ "eval_NanoMSMARCO_cosine_precision@5": 0.124,
1123
+ "eval_NanoMSMARCO_cosine_recall@1": 0.26,
1124
+ "eval_NanoMSMARCO_cosine_recall@5": 0.62,
1125
+ "eval_mldr_loss": 1.0107322931289673,
1126
+ "eval_mldr_runtime": 14.5338,
1127
+ "eval_mldr_samples_per_second": 34.403,
1128
+ "eval_mldr_steps_per_second": 2.202,
1129
+ "step": 800
1130
+ },
1131
+ {
1132
+ "epoch": 1.2965964343598055,
1133
+ "eval_squad_loss": 0.6025272607803345,
1134
+ "eval_squad_runtime": 0.8024,
1135
+ "eval_squad_samples_per_second": 59.822,
1136
+ "eval_squad_steps_per_second": 3.739,
1137
+ "step": 800
1138
+ },
1139
+ {
1140
+ "epoch": 1.2965964343598055,
1141
+ "eval_narrative_qa_loss": 1.7681714296340942,
1142
+ "eval_narrative_qa_runtime": 1.1303,
1143
+ "eval_narrative_qa_samples_per_second": 264.533,
1144
+ "eval_narrative_qa_steps_per_second": 16.81,
1145
+ "step": 800
1146
+ },
1147
+ {
1148
+ "epoch": 1.312803889789303,
1149
+ "grad_norm": 4288.0,
1150
+ "learning_rate": 1.4329003762158106e-05,
1151
+ "loss": 1.2271,
1152
+ "step": 810
1153
+ },
1154
+ {
1155
+ "epoch": 1.3290113452188006,
1156
+ "grad_norm": 11840.0,
1157
+ "learning_rate": 1.3730439953105243e-05,
1158
+ "loss": 1.0453,
1159
+ "step": 820
1160
+ },
1161
+ {
1162
+ "epoch": 1.3452188006482984,
1163
+ "grad_norm": 1440.0,
1164
+ "learning_rate": 1.3139877312255799e-05,
1165
+ "loss": 1.106,
1166
+ "step": 830
1167
+ },
1168
+ {
1169
+ "epoch": 1.3614262560777957,
1170
+ "grad_norm": 440.0,
1171
+ "learning_rate": 1.2557735127585917e-05,
1172
+ "loss": 1.0065,
1173
+ "step": 840
1174
+ },
1175
+ {
1176
+ "epoch": 1.3776337115072934,
1177
+ "grad_norm": 616.0,
1178
+ "learning_rate": 1.1984426708711804e-05,
1179
+ "loss": 1.124,
1180
+ "step": 850
1181
+ },
1182
+ {
1183
+ "epoch": 1.393841166936791,
1184
+ "grad_norm": 12.5,
1185
+ "learning_rate": 1.1420359093447966e-05,
1186
+ "loss": 1.3403,
1187
+ "step": 860
1188
+ },
1189
+ {
1190
+ "epoch": 1.4100486223662885,
1191
+ "grad_norm": 1280.0,
1192
+ "learning_rate": 1.0865932758818258e-05,
1193
+ "loss": 1.1274,
1194
+ "step": 870
1195
+ },
1196
+ {
1197
+ "epoch": 1.426256077795786,
1198
+ "grad_norm": 186.0,
1199
+ "learning_rate": 1.0321541336725027e-05,
1200
+ "loss": 1.1335,
1201
+ "step": 880
1202
+ },
1203
+ {
1204
+ "epoch": 1.4424635332252835,
1205
+ "grad_norm": 6656.0,
1206
+ "learning_rate": 9.787571334478101e-06,
1207
+ "loss": 1.0805,
1208
+ "step": 890
1209
+ },
1210
+ {
1211
+ "epoch": 1.4586709886547813,
1212
+ "grad_norm": 73.5,
1213
+ "learning_rate": 9.26440186038211e-06,
1214
+ "loss": 1.1117,
1215
+ "step": 900
1216
+ },
1217
+ {
1218
+ "epoch": 1.4586709886547813,
1219
+ "eval_NanoBEIR_mean_cosine_accuracy@1": 0.2066666666666667,
1220
+ "eval_NanoBEIR_mean_cosine_accuracy@5": 0.3466666666666667,
1221
+ "eval_NanoBEIR_mean_cosine_map@100": 0.24109707671460848,
1222
+ "eval_NanoBEIR_mean_cosine_mrr@10": 0.27005291005291004,
1223
+ "eval_NanoBEIR_mean_cosine_ndcg@1": 0.2066666666666667,
1224
+ "eval_NanoBEIR_mean_cosine_ndcg@5": 0.24663303266901904,
1225
+ "eval_NanoBEIR_mean_cosine_precision@1": 0.2066666666666667,
1226
+ "eval_NanoBEIR_mean_cosine_precision@5": 0.07200000000000001,
1227
+ "eval_NanoBEIR_mean_cosine_recall@1": 0.17,
1228
+ "eval_NanoBEIR_mean_cosine_recall@5": 0.29666666666666663,
1229
+ "eval_NanoFEVER_cosine_accuracy@1": 0.08,
1230
+ "eval_NanoFEVER_cosine_accuracy@5": 0.14,
1231
+ "eval_NanoFEVER_cosine_map@100": 0.10717352446028915,
1232
+ "eval_NanoFEVER_cosine_mrr@10": 0.1099126984126984,
1233
+ "eval_NanoFEVER_cosine_ndcg@1": 0.08,
1234
+ "eval_NanoFEVER_cosine_ndcg@5": 0.10123212623289701,
1235
+ "eval_NanoFEVER_cosine_precision@1": 0.08,
1236
+ "eval_NanoFEVER_cosine_precision@5": 0.028000000000000004,
1237
+ "eval_NanoFEVER_cosine_recall@1": 0.07,
1238
+ "eval_NanoFEVER_cosine_recall@5": 0.13,
1239
+ "eval_NanoHotpotQA_cosine_accuracy@1": 0.2,
1240
+ "eval_NanoHotpotQA_cosine_accuracy@5": 0.32,
1241
+ "eval_NanoHotpotQA_cosine_map@100": 0.15637152907438528,
1242
+ "eval_NanoHotpotQA_cosine_mrr@10": 0.2523888888888889,
1243
+ "eval_NanoHotpotQA_cosine_ndcg@1": 0.2,
1244
+ "eval_NanoHotpotQA_cosine_ndcg@5": 0.17287282180469699,
1245
+ "eval_NanoHotpotQA_cosine_precision@1": 0.2,
1246
+ "eval_NanoHotpotQA_cosine_precision@5": 0.07200000000000001,
1247
+ "eval_NanoHotpotQA_cosine_recall@1": 0.1,
1248
+ "eval_NanoHotpotQA_cosine_recall@5": 0.18,
1249
+ "eval_NanoMSMARCO_cosine_accuracy@1": 0.34,
1250
+ "eval_NanoMSMARCO_cosine_accuracy@5": 0.58,
1251
+ "eval_NanoMSMARCO_cosine_map@100": 0.45974617660915107,
1252
+ "eval_NanoMSMARCO_cosine_mrr@10": 0.44785714285714284,
1253
+ "eval_NanoMSMARCO_cosine_ndcg@1": 0.34,
1254
+ "eval_NanoMSMARCO_cosine_ndcg@5": 0.4657941499694631,
1255
+ "eval_NanoMSMARCO_cosine_precision@1": 0.34,
1256
+ "eval_NanoMSMARCO_cosine_precision@5": 0.11600000000000002,
1257
+ "eval_NanoMSMARCO_cosine_recall@1": 0.34,
1258
+ "eval_NanoMSMARCO_cosine_recall@5": 0.58,
1259
+ "eval_mldr_loss": 1.006673812866211,
1260
+ "eval_mldr_runtime": 14.487,
1261
+ "eval_mldr_samples_per_second": 34.514,
1262
+ "eval_mldr_steps_per_second": 2.209,
1263
+ "step": 900
1264
+ },
1265
+ {
1266
+ "epoch": 1.4586709886547813,
1267
+ "eval_squad_loss": 0.7755841612815857,
1268
+ "eval_squad_runtime": 0.8044,
1269
+ "eval_squad_samples_per_second": 59.675,
1270
+ "eval_squad_steps_per_second": 3.73,
1271
+ "step": 900
1272
+ },
1273
+ {
1274
+ "epoch": 1.4586709886547813,
1275
+ "eval_narrative_qa_loss": 1.7425211668014526,
1276
+ "eval_narrative_qa_runtime": 1.1372,
1277
+ "eval_narrative_qa_samples_per_second": 262.924,
1278
+ "eval_narrative_qa_steps_per_second": 16.708,
1279
+ "step": 900
1280
+ },
1281
+ {
1282
+ "epoch": 1.4748784440842788,
1283
+ "grad_norm": 712.0,
1284
+ "learning_rate": 8.752404354577052e-06,
1285
+ "loss": 1.0897,
1286
+ "step": 910
1287
+ },
1288
+ {
1289
+ "epoch": 1.4910858995137763,
1290
+ "grad_norm": 1200.0,
1291
+ "learning_rate": 8.251942325322903e-06,
1292
+ "loss": 0.9964,
1293
+ "step": 920
1294
+ },
1295
+ {
1296
+ "epoch": 1.5072933549432739,
1297
+ "grad_norm": 2016.0,
1298
+ "learning_rate": 7.763371090915932e-06,
1299
+ "loss": 0.954,
1300
+ "step": 930
1301
+ },
1302
+ {
1303
+ "epoch": 1.5235008103727714,
1304
+ "grad_norm": 4512.0,
1305
+ "learning_rate": 7.287037527419604e-06,
1306
+ "loss": 1.3415,
1307
+ "step": 940
1308
+ },
1309
+ {
1310
+ "epoch": 1.5397082658022692,
1311
+ "grad_norm": 438.0,
1312
+ "learning_rate": 6.823279822389278e-06,
1313
+ "loss": 0.9926,
1314
+ "step": 950
1315
+ },
1316
+ {
1317
+ "epoch": 1.5559157212317665,
1318
+ "grad_norm": 158.0,
1319
+ "learning_rate": 6.372427234765688e-06,
1320
+ "loss": 1.1362,
1321
+ "step": 960
1322
+ },
1323
+ {
1324
+ "epoch": 1.5721231766612642,
1325
+ "grad_norm": 163.0,
1326
+ "learning_rate": 5.934799861107507e-06,
1327
+ "loss": 1.1178,
1328
+ "step": 970
1329
+ },
1330
+ {
1331
+ "epoch": 1.5883306320907618,
1332
+ "grad_norm": 1216.0,
1333
+ "learning_rate": 5.5107084083289576e-06,
1334
+ "loss": 0.8676,
1335
+ "step": 980
1336
+ },
1337
+ {
1338
+ "epoch": 1.6045380875202593,
1339
+ "grad_norm": 37632.0,
1340
+ "learning_rate": 5.1004539731040245e-06,
1341
+ "loss": 1.1794,
1342
+ "step": 990
1343
+ },
1344
+ {
1345
+ "epoch": 1.620745542949757,
1346
+ "grad_norm": 268.0,
1347
+ "learning_rate": 4.704327828093641e-06,
1348
+ "loss": 1.0575,
1349
+ "step": 1000
1350
+ },
1351
+ {
1352
+ "epoch": 1.620745542949757,
1353
+ "eval_NanoBEIR_mean_cosine_accuracy@1": 0.18666666666666668,
1354
+ "eval_NanoBEIR_mean_cosine_accuracy@5": 0.3333333333333333,
1355
+ "eval_NanoBEIR_mean_cosine_map@100": 0.23251229334833623,
1356
+ "eval_NanoBEIR_mean_cosine_mrr@10": 0.250457671957672,
1357
+ "eval_NanoBEIR_mean_cosine_ndcg@1": 0.18666666666666668,
1358
+ "eval_NanoBEIR_mean_cosine_ndcg@5": 0.23607659211604262,
1359
+ "eval_NanoBEIR_mean_cosine_precision@1": 0.18666666666666668,
1360
+ "eval_NanoBEIR_mean_cosine_precision@5": 0.06933333333333334,
1361
+ "eval_NanoBEIR_mean_cosine_recall@1": 0.15666666666666668,
1362
+ "eval_NanoBEIR_mean_cosine_recall@5": 0.29,
1363
+ "eval_NanoFEVER_cosine_accuracy@1": 0.08,
1364
+ "eval_NanoFEVER_cosine_accuracy@5": 0.14,
1365
+ "eval_NanoFEVER_cosine_map@100": 0.10995542705065009,
1366
+ "eval_NanoFEVER_cosine_mrr@10": 0.11060317460317462,
1367
+ "eval_NanoFEVER_cosine_ndcg@1": 0.08,
1368
+ "eval_NanoFEVER_cosine_ndcg@5": 0.10261859507142916,
1369
+ "eval_NanoFEVER_cosine_precision@1": 0.08,
1370
+ "eval_NanoFEVER_cosine_precision@5": 0.027999999999999997,
1371
+ "eval_NanoFEVER_cosine_recall@1": 0.07,
1372
+ "eval_NanoFEVER_cosine_recall@5": 0.13,
1373
+ "eval_NanoHotpotQA_cosine_accuracy@1": 0.16,
1374
+ "eval_NanoHotpotQA_cosine_accuracy@5": 0.28,
1375
+ "eval_NanoHotpotQA_cosine_map@100": 0.14864943925499563,
1376
+ "eval_NanoHotpotQA_cosine_mrr@10": 0.21274603174603177,
1377
+ "eval_NanoHotpotQA_cosine_ndcg@1": 0.16,
1378
+ "eval_NanoHotpotQA_cosine_ndcg@5": 0.15294562020041982,
1379
+ "eval_NanoHotpotQA_cosine_precision@1": 0.16,
1380
+ "eval_NanoHotpotQA_cosine_precision@5": 0.064,
1381
+ "eval_NanoHotpotQA_cosine_recall@1": 0.08,
1382
+ "eval_NanoHotpotQA_cosine_recall@5": 0.16,
1383
+ "eval_NanoMSMARCO_cosine_accuracy@1": 0.32,
1384
+ "eval_NanoMSMARCO_cosine_accuracy@5": 0.58,
1385
+ "eval_NanoMSMARCO_cosine_map@100": 0.4389320137393629,
1386
+ "eval_NanoMSMARCO_cosine_mrr@10": 0.42802380952380953,
1387
+ "eval_NanoMSMARCO_cosine_ndcg@1": 0.32,
1388
+ "eval_NanoMSMARCO_cosine_ndcg@5": 0.4526655610762789,
1389
+ "eval_NanoMSMARCO_cosine_precision@1": 0.32,
1390
+ "eval_NanoMSMARCO_cosine_precision@5": 0.11600000000000002,
1391
+ "eval_NanoMSMARCO_cosine_recall@1": 0.32,
1392
+ "eval_NanoMSMARCO_cosine_recall@5": 0.58,
1393
+ "eval_mldr_loss": 1.0088629722595215,
1394
+ "eval_mldr_runtime": 14.5077,
1395
+ "eval_mldr_samples_per_second": 34.464,
1396
+ "eval_mldr_steps_per_second": 2.206,
1397
+ "step": 1000
1398
+ },
1399
+ {
1400
+ "epoch": 1.620745542949757,
1401
+ "eval_squad_loss": 0.6442683339118958,
1402
+ "eval_squad_runtime": 0.8625,
1403
+ "eval_squad_samples_per_second": 55.652,
1404
+ "eval_squad_steps_per_second": 3.478,
1405
+ "step": 1000
1406
+ },
1407
+ {
1408
+ "epoch": 1.620745542949757,
1409
+ "eval_narrative_qa_loss": 1.7451977729797363,
1410
+ "eval_narrative_qa_runtime": 1.1443,
1411
+ "eval_narrative_qa_samples_per_second": 261.298,
1412
+ "eval_narrative_qa_steps_per_second": 16.604,
1413
+ "step": 1000
1414
+ },
1415
+ {
1416
+ "epoch": 1.6369529983792543,
1417
+ "grad_norm": 382.0,
1418
+ "learning_rate": 4.322611215147784e-06,
1419
+ "loss": 1.1097,
1420
+ "step": 1010
1421
+ },
1422
+ {
1423
+ "epoch": 1.653160453808752,
1424
+ "grad_norm": 1012.0,
1425
+ "learning_rate": 3.955575145629237e-06,
1426
+ "loss": 1.125,
1427
+ "step": 1020
1428
+ },
1429
+ {
1430
+ "epoch": 1.6693679092382496,
1431
+ "grad_norm": 2688.0,
1432
+ "learning_rate": 3.603480208000781e-06,
1433
+ "loss": 1.1596,
1434
+ "step": 1030
1435
+ },
1436
+ {
1437
+ "epoch": 1.6855753646677472,
1438
+ "grad_norm": 880.0,
1439
+ "learning_rate": 3.266576382812489e-06,
1440
+ "loss": 1.0161,
1441
+ "step": 1040
1442
+ },
1443
+ {
1444
+ "epoch": 1.7017828200972447,
1445
+ "grad_norm": 3936.0,
1446
+ "learning_rate": 2.945102865220381e-06,
1447
+ "loss": 1.0132,
1448
+ "step": 1050
1449
+ },
1450
+ {
1451
+ "epoch": 1.7179902755267422,
1452
+ "grad_norm": 98.0,
1453
+ "learning_rate": 2.6392878951625263e-06,
1454
+ "loss": 1.073,
1455
+ "step": 1060
1456
+ },
1457
+ {
1458
+ "epoch": 1.73419773095624,
1459
+ "grad_norm": 4640.0,
1460
+ "learning_rate": 2.349348595313139e-06,
1461
+ "loss": 1.1178,
1462
+ "step": 1070
1463
+ },
1464
+ {
1465
+ "epoch": 1.7504051863857373,
1466
+ "grad_norm": 412.0,
1467
+ "learning_rate": 2.0754908169296953e-06,
1468
+ "loss": 0.9568,
1469
+ "step": 1080
1470
+ },
1471
+ {
1472
+ "epoch": 1.766612641815235,
1473
+ "grad_norm": 10176.0,
1474
+ "learning_rate": 1.817908993702555e-06,
1475
+ "loss": 0.9444,
1476
+ "step": 1090
1477
+ },
1478
+ {
1479
+ "epoch": 1.7828200972447326,
1480
+ "grad_norm": 11392.0,
1481
+ "learning_rate": 1.5767860037108284e-06,
1482
+ "loss": 1.1216,
1483
+ "step": 1100
1484
+ },
1485
+ {
1486
+ "epoch": 1.7828200972447326,
1487
+ "eval_NanoBEIR_mean_cosine_accuracy@1": 0.20000000000000004,
1488
+ "eval_NanoBEIR_mean_cosine_accuracy@5": 0.3466666666666667,
1489
+ "eval_NanoBEIR_mean_cosine_map@100": 0.24487122110018178,
1490
+ "eval_NanoBEIR_mean_cosine_mrr@10": 0.26410582010582007,
1491
+ "eval_NanoBEIR_mean_cosine_ndcg@1": 0.20000000000000004,
1492
+ "eval_NanoBEIR_mean_cosine_ndcg@5": 0.24908430500748113,
1493
+ "eval_NanoBEIR_mean_cosine_precision@1": 0.20000000000000004,
1494
+ "eval_NanoBEIR_mean_cosine_precision@5": 0.07200000000000001,
1495
+ "eval_NanoBEIR_mean_cosine_recall@1": 0.16666666666666666,
1496
+ "eval_NanoBEIR_mean_cosine_recall@5": 0.30333333333333334,
1497
+ "eval_NanoFEVER_cosine_accuracy@1": 0.08,
1498
+ "eval_NanoFEVER_cosine_accuracy@5": 0.16,
1499
+ "eval_NanoFEVER_cosine_map@100": 0.1179874269166529,
1500
+ "eval_NanoFEVER_cosine_mrr@10": 0.11407936507936509,
1501
+ "eval_NanoFEVER_cosine_ndcg@1": 0.08,
1502
+ "eval_NanoFEVER_cosine_ndcg@5": 0.11385072130432616,
1503
+ "eval_NanoFEVER_cosine_precision@1": 0.08,
1504
+ "eval_NanoFEVER_cosine_precision@5": 0.032,
1505
+ "eval_NanoFEVER_cosine_recall@1": 0.07,
1506
+ "eval_NanoFEVER_cosine_recall@5": 0.15,
1507
+ "eval_NanoHotpotQA_cosine_accuracy@1": 0.18,
1508
+ "eval_NanoHotpotQA_cosine_accuracy@5": 0.28,
1509
+ "eval_NanoHotpotQA_cosine_map@100": 0.14983234189813172,
1510
+ "eval_NanoHotpotQA_cosine_mrr@10": 0.22338095238095235,
1511
+ "eval_NanoHotpotQA_cosine_ndcg@1": 0.18,
1512
+ "eval_NanoHotpotQA_cosine_ndcg@5": 0.15586592369400193,
1513
+ "eval_NanoHotpotQA_cosine_precision@1": 0.18,
1514
+ "eval_NanoHotpotQA_cosine_precision@5": 0.064,
1515
+ "eval_NanoHotpotQA_cosine_recall@1": 0.09,
1516
+ "eval_NanoHotpotQA_cosine_recall@5": 0.16,
1517
+ "eval_NanoMSMARCO_cosine_accuracy@1": 0.34,
1518
+ "eval_NanoMSMARCO_cosine_accuracy@5": 0.6,
1519
+ "eval_NanoMSMARCO_cosine_map@100": 0.4667938944857608,
1520
+ "eval_NanoMSMARCO_cosine_mrr@10": 0.4548571428571428,
1521
+ "eval_NanoMSMARCO_cosine_ndcg@1": 0.34,
1522
+ "eval_NanoMSMARCO_cosine_ndcg@5": 0.47753627002411525,
1523
+ "eval_NanoMSMARCO_cosine_precision@1": 0.34,
1524
+ "eval_NanoMSMARCO_cosine_precision@5": 0.12000000000000002,
1525
+ "eval_NanoMSMARCO_cosine_recall@1": 0.34,
1526
+ "eval_NanoMSMARCO_cosine_recall@5": 0.6,
1527
+ "eval_mldr_loss": 1.0336848497390747,
1528
+ "eval_mldr_runtime": 14.5915,
1529
+ "eval_mldr_samples_per_second": 34.266,
1530
+ "eval_mldr_steps_per_second": 2.193,
1531
+ "step": 1100
1532
+ },
1533
+ {
1534
+ "epoch": 1.7828200972447326,
1535
+ "eval_squad_loss": 0.6948645114898682,
1536
+ "eval_squad_runtime": 0.8997,
1537
+ "eval_squad_samples_per_second": 53.351,
1538
+ "eval_squad_steps_per_second": 3.334,
1539
+ "step": 1100
1540
+ },
1541
+ {
1542
+ "epoch": 1.7828200972447326,
1543
+ "eval_narrative_qa_loss": 1.710744857788086,
1544
+ "eval_narrative_qa_runtime": 1.1493,
1545
+ "eval_narrative_qa_samples_per_second": 260.15,
1546
+ "eval_narrative_qa_steps_per_second": 16.531,
1547
+ "step": 1100
1548
+ },
1549
+ {
1550
+ "epoch": 1.79902755267423,
1551
+ "grad_norm": 19.75,
1552
+ "learning_rate": 1.3522930395825029e-06,
1553
+ "loss": 1.0427,
1554
+ "step": 1110
1555
+ },
1556
+ {
1557
+ "epoch": 1.8152350081037278,
1558
+ "grad_norm": 760.0,
1559
+ "learning_rate": 1.1445894869509865e-06,
1560
+ "loss": 0.9255,
1561
+ "step": 1120
1562
+ },
1563
+ {
1564
+ "epoch": 1.8314424635332252,
1565
+ "grad_norm": 564.0,
1566
+ "learning_rate": 9.538228112944665e-07,
1567
+ "loss": 1.0119,
1568
+ "step": 1130
1569
+ },
1570
+ {
1571
+ "epoch": 1.847649918962723,
1572
+ "grad_norm": 1448.0,
1573
+ "learning_rate": 7.801284532382214e-07,
1574
+ "loss": 1.0469,
1575
+ "step": 1140
1576
+ },
1577
+ {
1578
+ "epoch": 1.8638573743922204,
1579
+ "grad_norm": 956.0,
1580
+ "learning_rate": 6.236297323944679e-07,
1581
+ "loss": 1.0786,
1582
+ "step": 1150
1583
+ },
1584
+ {
1585
+ "epoch": 1.880064829821718,
1586
+ "grad_norm": 2040.0,
1587
+ "learning_rate": 4.844377598078209e-07,
1588
+ "loss": 0.9487,
1589
+ "step": 1160
1590
+ },
1591
+ {
1592
+ "epoch": 1.8962722852512157,
1593
+ "grad_norm": 892.0,
1594
+ "learning_rate": 3.626513590685998e-07,
1595
+ "loss": 0.9978,
1596
+ "step": 1170
1597
+ },
1598
+ {
1599
+ "epoch": 1.912479740680713,
1600
+ "grad_norm": 492.0,
1601
+ "learning_rate": 2.5835699615002764e-07,
1602
+ "loss": 0.8763,
1603
+ "step": 1180
1604
+ },
1605
+ {
1606
+ "epoch": 1.9286871961102108,
1607
+ "grad_norm": 1472.0,
1608
+ "learning_rate": 1.71628718019054e-07,
1609
+ "loss": 1.1807,
1610
+ "step": 1190
1611
+ },
1612
+ {
1613
+ "epoch": 1.9448946515397083,
1614
+ "grad_norm": 1944.0,
1615
+ "learning_rate": 1.0252810006446679e-07,
1616
+ "loss": 1.0942,
1617
+ "step": 1200
1618
+ },
1619
+ {
1620
+ "epoch": 1.9448946515397083,
1621
+ "eval_NanoBEIR_mean_cosine_accuracy@1": 0.14666666666666667,
1622
+ "eval_NanoBEIR_mean_cosine_accuracy@5": 0.3466666666666667,
1623
+ "eval_NanoBEIR_mean_cosine_map@100": 0.21268529762891542,
1624
+ "eval_NanoBEIR_mean_cosine_mrr@10": 0.23622486772486773,
1625
+ "eval_NanoBEIR_mean_cosine_ndcg@1": 0.14666666666666667,
1626
+ "eval_NanoBEIR_mean_cosine_ndcg@5": 0.22392149211074455,
1627
+ "eval_NanoBEIR_mean_cosine_precision@1": 0.14666666666666667,
1628
+ "eval_NanoBEIR_mean_cosine_precision@5": 0.07066666666666667,
1629
+ "eval_NanoBEIR_mean_cosine_recall@1": 0.12333333333333334,
1630
+ "eval_NanoBEIR_mean_cosine_recall@5": 0.3,
1631
+ "eval_NanoFEVER_cosine_accuracy@1": 0.06,
1632
+ "eval_NanoFEVER_cosine_accuracy@5": 0.18,
1633
+ "eval_NanoFEVER_cosine_map@100": 0.10919730647820787,
1634
+ "eval_NanoFEVER_cosine_mrr@10": 0.11404761904761906,
1635
+ "eval_NanoFEVER_cosine_ndcg@1": 0.06,
1636
+ "eval_NanoFEVER_cosine_ndcg@5": 0.11420637252044616,
1637
+ "eval_NanoFEVER_cosine_precision@1": 0.06,
1638
+ "eval_NanoFEVER_cosine_precision@5": 0.036000000000000004,
1639
+ "eval_NanoFEVER_cosine_recall@1": 0.05,
1640
+ "eval_NanoFEVER_cosine_recall@5": 0.17,
1641
+ "eval_NanoHotpotQA_cosine_accuracy@1": 0.12,
1642
+ "eval_NanoHotpotQA_cosine_accuracy@5": 0.28,
1643
+ "eval_NanoHotpotQA_cosine_map@100": 0.12244441327627578,
1644
+ "eval_NanoHotpotQA_cosine_mrr@10": 0.19749206349206347,
1645
+ "eval_NanoHotpotQA_cosine_ndcg@1": 0.12,
1646
+ "eval_NanoHotpotQA_cosine_ndcg@5": 0.12878970755477528,
1647
+ "eval_NanoHotpotQA_cosine_precision@1": 0.12,
1648
+ "eval_NanoHotpotQA_cosine_precision@5": 0.06000000000000001,
1649
+ "eval_NanoHotpotQA_cosine_recall@1": 0.06,
1650
+ "eval_NanoHotpotQA_cosine_recall@5": 0.15,
1651
+ "eval_NanoMSMARCO_cosine_accuracy@1": 0.26,
1652
+ "eval_NanoMSMARCO_cosine_accuracy@5": 0.58,
1653
+ "eval_NanoMSMARCO_cosine_map@100": 0.40641417313226263,
1654
+ "eval_NanoMSMARCO_cosine_mrr@10": 0.3971349206349206,
1655
+ "eval_NanoMSMARCO_cosine_ndcg@1": 0.26,
1656
+ "eval_NanoMSMARCO_cosine_ndcg@5": 0.4287683962570123,
1657
+ "eval_NanoMSMARCO_cosine_precision@1": 0.26,
1658
+ "eval_NanoMSMARCO_cosine_precision@5": 0.11600000000000002,
1659
+ "eval_NanoMSMARCO_cosine_recall@1": 0.26,
1660
+ "eval_NanoMSMARCO_cosine_recall@5": 0.58,
1661
+ "eval_mldr_loss": 0.9975912570953369,
1662
+ "eval_mldr_runtime": 14.5803,
1663
+ "eval_mldr_samples_per_second": 34.293,
1664
+ "eval_mldr_steps_per_second": 2.195,
1665
+ "step": 1200
1666
+ },
1667
+ {
1668
+ "epoch": 1.9448946515397083,
1669
+ "eval_squad_loss": 0.7459979057312012,
1670
+ "eval_squad_runtime": 0.9491,
1671
+ "eval_squad_samples_per_second": 50.572,
1672
+ "eval_squad_steps_per_second": 3.161,
1673
+ "step": 1200
1674
+ },
1675
+ {
1676
+ "epoch": 1.9448946515397083,
1677
+ "eval_narrative_qa_loss": 1.7257987260818481,
1678
+ "eval_narrative_qa_runtime": 1.1714,
1679
+ "eval_narrative_qa_samples_per_second": 255.243,
1680
+ "eval_narrative_qa_steps_per_second": 16.219,
1681
+ "step": 1200
1682
+ },
1683
+ {
1684
+ "epoch": 1.9611021069692058,
1685
+ "grad_norm": 6752.0,
1686
+ "learning_rate": 5.110420237955382e-08,
1687
+ "loss": 1.0164,
1688
+ "step": 1210
1689
+ },
1690
+ {
1691
+ "epoch": 1.9773095623987034,
1692
+ "grad_norm": 3360.0,
1693
+ "learning_rate": 1.7393534930393308e-08,
1694
+ "loss": 1.1927,
1695
+ "step": 1220
1696
+ },
1697
+ {
1698
+ "epoch": 1.993517017828201,
1699
+ "grad_norm": 812.0,
1700
+ "learning_rate": 1.4200316344942234e-09,
1701
+ "loss": 1.073,
1702
+ "step": 1230
1703
+ }
1704
+ ],
1705
+ "logging_steps": 10,
1706
+ "max_steps": 1234,
1707
+ "num_input_tokens_seen": 0,
1708
+ "num_train_epochs": 2,
1709
+ "save_steps": 500,
1710
+ "stateful_callbacks": {
1711
+ "TrainerControl": {
1712
+ "args": {
1713
+ "should_epoch_stop": false,
1714
+ "should_evaluate": false,
1715
+ "should_log": false,
1716
+ "should_save": true,
1717
+ "should_training_stop": true
1718
+ },
1719
+ "attributes": {}
1720
+ }
1721
+ },
1722
+ "total_flos": 0.0,
1723
+ "train_batch_size": 4,
1724
+ "trial_name": null,
1725
+ "trial_params": null
1726
+ }
checkpoint-1234/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e33f3c9977bb1dfdea6e80445e3a56ac46fa17e22c8e01527826c894784b6fb3
3
+ size 5560
checkpoint-500/1_Pooling/config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "word_embedding_dimension": 1024,
3
+ "pooling_mode_cls_token": false,
4
+ "pooling_mode_mean_tokens": true,
5
+ "pooling_mode_max_tokens": false,
6
+ "pooling_mode_mean_sqrt_len_tokens": false,
7
+ "pooling_mode_weightedmean_tokens": false,
8
+ "pooling_mode_lasttoken": false,
9
+ "include_prompt": true
10
+ }
checkpoint-500/README.md ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-500/config.json ADDED
@@ -0,0 +1,47 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "./models/modernbert-embed-large",
3
+ "architectures": [
4
+ "ModernBertModel"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 50281,
9
+ "classifier_activation": "gelu",
10
+ "classifier_bias": false,
11
+ "classifier_dropout": 0.0,
12
+ "classifier_pooling": "mean",
13
+ "cls_token_id": 50281,
14
+ "decoder_bias": true,
15
+ "deterministic_flash_attn": false,
16
+ "embedding_dropout": 0.0,
17
+ "eos_token_id": 50282,
18
+ "global_attn_every_n_layers": 3,
19
+ "global_rope_theta": 160000.0,
20
+ "gradient_checkpointing": false,
21
+ "hidden_activation": "gelu",
22
+ "hidden_size": 1024,
23
+ "initializer_cutoff_factor": 2.0,
24
+ "initializer_range": 0.02,
25
+ "intermediate_size": 2624,
26
+ "layer_norm_eps": 1e-05,
27
+ "local_attention": 128,
28
+ "local_rope_theta": 10000.0,
29
+ "max_position_embeddings": 8192,
30
+ "mlp_bias": false,
31
+ "mlp_dropout": 0.0,
32
+ "model_type": "modernbert",
33
+ "norm_bias": false,
34
+ "norm_eps": 1e-05,
35
+ "num_attention_heads": 16,
36
+ "num_hidden_layers": 28,
37
+ "pad_token_id": 50283,
38
+ "position_embedding_type": "absolute",
39
+ "reference_compile": true,
40
+ "repad_logits_with_grad": false,
41
+ "sep_token_id": 50282,
42
+ "sparse_pred_ignore_index": -100,
43
+ "sparse_prediction": false,
44
+ "torch_dtype": "bfloat16",
45
+ "transformers_version": "4.48.1",
46
+ "vocab_size": 50368
47
+ }
checkpoint-500/config_sentence_transformers.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "__version__": {
3
+ "sentence_transformers": "3.3.1",
4
+ "transformers": "4.48.1",
5
+ "pytorch": "2.5.1+cu118"
6
+ },
7
+ "prompts": {},
8
+ "default_prompt_name": null,
9
+ "similarity_fn_name": "cosine"
10
+ }
checkpoint-500/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:602ee8d4ca181ab742d391949c3a6feb027ed9275f52737833a8692e2b7c8a9a
3
+ size 789580328
checkpoint-500/modules.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [
2
+ {
3
+ "idx": 0,
4
+ "name": "0",
5
+ "path": "",
6
+ "type": "sentence_transformers.models.Transformer"
7
+ },
8
+ {
9
+ "idx": 1,
10
+ "name": "1",
11
+ "path": "1_Pooling",
12
+ "type": "sentence_transformers.models.Pooling"
13
+ },
14
+ {
15
+ "idx": 2,
16
+ "name": "2",
17
+ "path": "2_Normalize",
18
+ "type": "sentence_transformers.models.Normalize"
19
+ }
20
+ ]
checkpoint-500/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca387c5c236d3bae8b340878fa7ef91666d7ee32c36ea47e46dd1bcf346163bf
3
+ size 1579269882
checkpoint-500/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c23569d2761483a87b9e6fc833db135096d40180c13b62381a7851ab2839a8f0
3
+ size 14960
checkpoint-500/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2103da0e8ef16faf70d7e0f7cd1f2f51e8d1f8dbd8de8b79b1edd114eae68f15
3
+ size 14960
checkpoint-500/rng_state_2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b56712589d3d249f2b2c2ae7efc1a8b4f2a6e5524d7b03e8b6eb500efa86806
3
+ size 14960
checkpoint-500/rng_state_3.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0613df44991ed1247364614cb59d29421493ea0c45ee81f9b58aa37330bdd8c7
3
+ size 14960
checkpoint-500/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f3ad640ea6e2a4313e78f081136cdb95be173d2bbd174e406549e80c8ddf296
3
+ size 1064