Upload model finetuned on codet5p-220m using strategy src_fm_fc_ms_ff
Browse files- README.md +50 -3
- added_tokens.json +8 -0
- config.json +33 -0
- generation_config.json +8 -0
- merges.txt +0 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +59 -0
- tokenizer.json +0 -0
- tokenizer_config.json +113 -0
- trainer_state.json +1603 -0
- training_args.bin +3 -0
- vocab.json +0 -0
README.md
CHANGED
|
@@ -1,3 +1,50 @@
|
|
| 1 |
-
---
|
| 2 |
-
license:
|
| 3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: bsd-3-clause
|
| 3 |
+
base_model: Salesforce/codet5p-220m
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
+
model-index:
|
| 7 |
+
- name: finetuning_02_codet5p_src_fm_fc_ms_ff
|
| 8 |
+
results: []
|
| 9 |
+
---
|
| 10 |
+
|
| 11 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 12 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 13 |
+
|
| 14 |
+
# finetuning_02_codet5p_src_fm_fc_ms_ff
|
| 15 |
+
|
| 16 |
+
This model is a fine-tuned version of [Salesforce/codet5p-220m](https://huggingface.co/Salesforce/codet5p-220m) on an unknown dataset.
|
| 17 |
+
|
| 18 |
+
## Model description
|
| 19 |
+
|
| 20 |
+
More information needed
|
| 21 |
+
|
| 22 |
+
## Intended uses & limitations
|
| 23 |
+
|
| 24 |
+
More information needed
|
| 25 |
+
|
| 26 |
+
## Training and evaluation data
|
| 27 |
+
|
| 28 |
+
More information needed
|
| 29 |
+
|
| 30 |
+
## Training procedure
|
| 31 |
+
|
| 32 |
+
### Training hyperparameters
|
| 33 |
+
|
| 34 |
+
The following hyperparameters were used during training:
|
| 35 |
+
- learning_rate: 5e-05
|
| 36 |
+
- train_batch_size: 32
|
| 37 |
+
- eval_batch_size: 64
|
| 38 |
+
- seed: 42
|
| 39 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 40 |
+
- lr_scheduler_type: linear
|
| 41 |
+
- lr_scheduler_warmup_steps: 800
|
| 42 |
+
- num_epochs: 5
|
| 43 |
+
- mixed_precision_training: Native AMP
|
| 44 |
+
|
| 45 |
+
### Framework versions
|
| 46 |
+
|
| 47 |
+
- Transformers 4.38.2
|
| 48 |
+
- Pytorch 2.1.0
|
| 49 |
+
- Datasets 2.20.0
|
| 50 |
+
- Tokenizers 0.15.2
|
added_tokens.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"</ECTX>": 32103,
|
| 3 |
+
"</FCTX>": 32101,
|
| 4 |
+
"</PRIVATE_FCTX>": 32105,
|
| 5 |
+
"<ECTX>": 32102,
|
| 6 |
+
"<FCTX>": 32100,
|
| 7 |
+
"<PRIVATE_FCTX>": 32104
|
| 8 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "Salesforce/codet5p-220m",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"T5ForConditionalGeneration"
|
| 5 |
+
],
|
| 6 |
+
"bos_token_id": 1,
|
| 7 |
+
"classifier_dropout": 0.0,
|
| 8 |
+
"d_ff": 3072,
|
| 9 |
+
"d_kv": 64,
|
| 10 |
+
"d_model": 768,
|
| 11 |
+
"decoder_start_token_id": 0,
|
| 12 |
+
"dense_act_fn": "relu",
|
| 13 |
+
"dropout_rate": 0.1,
|
| 14 |
+
"eos_token_id": 2,
|
| 15 |
+
"feed_forward_proj": "relu",
|
| 16 |
+
"initializer_factor": 1.0,
|
| 17 |
+
"is_encoder_decoder": true,
|
| 18 |
+
"is_gated_act": false,
|
| 19 |
+
"layer_norm_epsilon": 1e-06,
|
| 20 |
+
"model_type": "t5",
|
| 21 |
+
"n_positions": 512,
|
| 22 |
+
"num_decoder_layers": 12,
|
| 23 |
+
"num_heads": 12,
|
| 24 |
+
"num_layers": 12,
|
| 25 |
+
"output_past": true,
|
| 26 |
+
"pad_token_id": 0,
|
| 27 |
+
"relative_attention_max_distance": 128,
|
| 28 |
+
"relative_attention_num_buckets": 32,
|
| 29 |
+
"torch_dtype": "float32",
|
| 30 |
+
"transformers_version": "4.38.2",
|
| 31 |
+
"use_cache": true,
|
| 32 |
+
"vocab_size": 32106
|
| 33 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 1,
|
| 4 |
+
"decoder_start_token_id": 0,
|
| 5 |
+
"eos_token_id": 2,
|
| 6 |
+
"pad_token_id": 0,
|
| 7 |
+
"transformers_version": "4.38.2"
|
| 8 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c3c450de6ca234b9791cabe32b7c7416f795cff2c18f4cbcaffde3c6c2df5286
|
| 3 |
+
size 891635790
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,59 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<FCTX>",
|
| 4 |
+
"</FCTX>",
|
| 5 |
+
"<ECTX>",
|
| 6 |
+
"</ECTX>",
|
| 7 |
+
"<PRIVATE_FCTX>",
|
| 8 |
+
"</PRIVATE_FCTX>"
|
| 9 |
+
],
|
| 10 |
+
"bos_token": {
|
| 11 |
+
"content": "<s>",
|
| 12 |
+
"lstrip": false,
|
| 13 |
+
"normalized": true,
|
| 14 |
+
"rstrip": false,
|
| 15 |
+
"single_word": false
|
| 16 |
+
},
|
| 17 |
+
"cls_token": {
|
| 18 |
+
"content": "<s>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": true,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
},
|
| 24 |
+
"eos_token": {
|
| 25 |
+
"content": "</s>",
|
| 26 |
+
"lstrip": false,
|
| 27 |
+
"normalized": true,
|
| 28 |
+
"rstrip": false,
|
| 29 |
+
"single_word": false
|
| 30 |
+
},
|
| 31 |
+
"mask_token": {
|
| 32 |
+
"content": "<mask>",
|
| 33 |
+
"lstrip": true,
|
| 34 |
+
"normalized": true,
|
| 35 |
+
"rstrip": false,
|
| 36 |
+
"single_word": false
|
| 37 |
+
},
|
| 38 |
+
"pad_token": {
|
| 39 |
+
"content": "<pad>",
|
| 40 |
+
"lstrip": false,
|
| 41 |
+
"normalized": true,
|
| 42 |
+
"rstrip": false,
|
| 43 |
+
"single_word": false
|
| 44 |
+
},
|
| 45 |
+
"sep_token": {
|
| 46 |
+
"content": "</s>",
|
| 47 |
+
"lstrip": false,
|
| 48 |
+
"normalized": true,
|
| 49 |
+
"rstrip": false,
|
| 50 |
+
"single_word": false
|
| 51 |
+
},
|
| 52 |
+
"unk_token": {
|
| 53 |
+
"content": "<unk>",
|
| 54 |
+
"lstrip": false,
|
| 55 |
+
"normalized": true,
|
| 56 |
+
"rstrip": false,
|
| 57 |
+
"single_word": false
|
| 58 |
+
}
|
| 59 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,113 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"0": {
|
| 5 |
+
"content": "<pad>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": true,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"1": {
|
| 13 |
+
"content": "<s>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": true,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": true
|
| 19 |
+
},
|
| 20 |
+
"2": {
|
| 21 |
+
"content": "</s>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": true,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"special": true
|
| 27 |
+
},
|
| 28 |
+
"3": {
|
| 29 |
+
"content": "<unk>",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": true,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false,
|
| 34 |
+
"special": true
|
| 35 |
+
},
|
| 36 |
+
"4": {
|
| 37 |
+
"content": "<mask>",
|
| 38 |
+
"lstrip": true,
|
| 39 |
+
"normalized": true,
|
| 40 |
+
"rstrip": false,
|
| 41 |
+
"single_word": false,
|
| 42 |
+
"special": true
|
| 43 |
+
},
|
| 44 |
+
"32100": {
|
| 45 |
+
"content": "<FCTX>",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": false,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false,
|
| 50 |
+
"special": true
|
| 51 |
+
},
|
| 52 |
+
"32101": {
|
| 53 |
+
"content": "</FCTX>",
|
| 54 |
+
"lstrip": false,
|
| 55 |
+
"normalized": false,
|
| 56 |
+
"rstrip": false,
|
| 57 |
+
"single_word": false,
|
| 58 |
+
"special": true
|
| 59 |
+
},
|
| 60 |
+
"32102": {
|
| 61 |
+
"content": "<ECTX>",
|
| 62 |
+
"lstrip": false,
|
| 63 |
+
"normalized": false,
|
| 64 |
+
"rstrip": false,
|
| 65 |
+
"single_word": false,
|
| 66 |
+
"special": true
|
| 67 |
+
},
|
| 68 |
+
"32103": {
|
| 69 |
+
"content": "</ECTX>",
|
| 70 |
+
"lstrip": false,
|
| 71 |
+
"normalized": false,
|
| 72 |
+
"rstrip": false,
|
| 73 |
+
"single_word": false,
|
| 74 |
+
"special": true
|
| 75 |
+
},
|
| 76 |
+
"32104": {
|
| 77 |
+
"content": "<PRIVATE_FCTX>",
|
| 78 |
+
"lstrip": false,
|
| 79 |
+
"normalized": false,
|
| 80 |
+
"rstrip": false,
|
| 81 |
+
"single_word": false,
|
| 82 |
+
"special": true
|
| 83 |
+
},
|
| 84 |
+
"32105": {
|
| 85 |
+
"content": "</PRIVATE_FCTX>",
|
| 86 |
+
"lstrip": false,
|
| 87 |
+
"normalized": false,
|
| 88 |
+
"rstrip": false,
|
| 89 |
+
"single_word": false,
|
| 90 |
+
"special": true
|
| 91 |
+
}
|
| 92 |
+
},
|
| 93 |
+
"additional_special_tokens": [
|
| 94 |
+
"<FCTX>",
|
| 95 |
+
"</FCTX>",
|
| 96 |
+
"<ECTX>",
|
| 97 |
+
"</ECTX>",
|
| 98 |
+
"<PRIVATE_FCTX>",
|
| 99 |
+
"</PRIVATE_FCTX>"
|
| 100 |
+
],
|
| 101 |
+
"bos_token": "<s>",
|
| 102 |
+
"clean_up_tokenization_spaces": true,
|
| 103 |
+
"cls_token": "<s>",
|
| 104 |
+
"eos_token": "</s>",
|
| 105 |
+
"errors": "replace",
|
| 106 |
+
"mask_token": "<mask>",
|
| 107 |
+
"model_max_length": 512,
|
| 108 |
+
"pad_token": "<pad>",
|
| 109 |
+
"sep_token": "</s>",
|
| 110 |
+
"tokenizer_class": "RobertaTokenizer",
|
| 111 |
+
"trim_offsets": true,
|
| 112 |
+
"unk_token": "<unk>"
|
| 113 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1603 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 1.0753824710845947,
|
| 3 |
+
"best_model_checkpoint": "/root/finetuning_executions/finetuning_02_codet5p_src_fm_fc_ms_ff/checkpoint-17548",
|
| 4 |
+
"epoch": 5.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 87740,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.02,
|
| 13 |
+
"grad_norm": 1.5287591218948364,
|
| 14 |
+
"learning_rate": 2.4687500000000004e-05,
|
| 15 |
+
"loss": 1.4862,
|
| 16 |
+
"step": 400
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.05,
|
| 20 |
+
"grad_norm": 1.919360876083374,
|
| 21 |
+
"learning_rate": 4.96875e-05,
|
| 22 |
+
"loss": 1.1714,
|
| 23 |
+
"step": 800
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.07,
|
| 27 |
+
"grad_norm": 1.1510220766067505,
|
| 28 |
+
"learning_rate": 4.977283183804923e-05,
|
| 29 |
+
"loss": 1.1326,
|
| 30 |
+
"step": 1200
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.09,
|
| 34 |
+
"grad_norm": 1.1849422454833984,
|
| 35 |
+
"learning_rate": 4.9542788129744654e-05,
|
| 36 |
+
"loss": 1.1176,
|
| 37 |
+
"step": 1600
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.11,
|
| 41 |
+
"grad_norm": 1.052920937538147,
|
| 42 |
+
"learning_rate": 4.931274442144008e-05,
|
| 43 |
+
"loss": 1.0981,
|
| 44 |
+
"step": 2000
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.14,
|
| 48 |
+
"grad_norm": 1.174275517463684,
|
| 49 |
+
"learning_rate": 4.90827007131355e-05,
|
| 50 |
+
"loss": 1.0811,
|
| 51 |
+
"step": 2400
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.16,
|
| 55 |
+
"grad_norm": 1.0344840288162231,
|
| 56 |
+
"learning_rate": 4.885265700483092e-05,
|
| 57 |
+
"loss": 1.065,
|
| 58 |
+
"step": 2800
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.18,
|
| 62 |
+
"grad_norm": 1.2671674489974976,
|
| 63 |
+
"learning_rate": 4.862261329652634e-05,
|
| 64 |
+
"loss": 1.0578,
|
| 65 |
+
"step": 3200
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.21,
|
| 69 |
+
"grad_norm": 1.1277002096176147,
|
| 70 |
+
"learning_rate": 4.839256958822176e-05,
|
| 71 |
+
"loss": 1.0421,
|
| 72 |
+
"step": 3600
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.23,
|
| 76 |
+
"grad_norm": 1.1894861459732056,
|
| 77 |
+
"learning_rate": 4.8162525879917186e-05,
|
| 78 |
+
"loss": 1.031,
|
| 79 |
+
"step": 4000
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.25,
|
| 83 |
+
"grad_norm": 1.2189041376113892,
|
| 84 |
+
"learning_rate": 4.793248217161261e-05,
|
| 85 |
+
"loss": 1.0322,
|
| 86 |
+
"step": 4400
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.27,
|
| 90 |
+
"grad_norm": 1.2372210025787354,
|
| 91 |
+
"learning_rate": 4.770243846330803e-05,
|
| 92 |
+
"loss": 1.0155,
|
| 93 |
+
"step": 4800
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.3,
|
| 97 |
+
"grad_norm": 1.2500073909759521,
|
| 98 |
+
"learning_rate": 4.7472394755003454e-05,
|
| 99 |
+
"loss": 1.0211,
|
| 100 |
+
"step": 5200
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.32,
|
| 104 |
+
"grad_norm": 0.9148824214935303,
|
| 105 |
+
"learning_rate": 4.724235104669887e-05,
|
| 106 |
+
"loss": 1.0001,
|
| 107 |
+
"step": 5600
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.34,
|
| 111 |
+
"grad_norm": 1.1473156213760376,
|
| 112 |
+
"learning_rate": 4.7012307338394294e-05,
|
| 113 |
+
"loss": 0.9869,
|
| 114 |
+
"step": 6000
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.36,
|
| 118 |
+
"grad_norm": 1.1870834827423096,
|
| 119 |
+
"learning_rate": 4.6782263630089717e-05,
|
| 120 |
+
"loss": 0.9799,
|
| 121 |
+
"step": 6400
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.39,
|
| 125 |
+
"grad_norm": 1.1499440670013428,
|
| 126 |
+
"learning_rate": 4.655221992178514e-05,
|
| 127 |
+
"loss": 0.9745,
|
| 128 |
+
"step": 6800
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.41,
|
| 132 |
+
"grad_norm": 1.0729453563690186,
|
| 133 |
+
"learning_rate": 4.632217621348056e-05,
|
| 134 |
+
"loss": 0.9871,
|
| 135 |
+
"step": 7200
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.43,
|
| 139 |
+
"grad_norm": 1.3007827997207642,
|
| 140 |
+
"learning_rate": 4.6092132505175986e-05,
|
| 141 |
+
"loss": 0.9612,
|
| 142 |
+
"step": 7600
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.46,
|
| 146 |
+
"grad_norm": 1.1860408782958984,
|
| 147 |
+
"learning_rate": 4.586208879687141e-05,
|
| 148 |
+
"loss": 0.9636,
|
| 149 |
+
"step": 8000
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.48,
|
| 153 |
+
"grad_norm": 1.0349955558776855,
|
| 154 |
+
"learning_rate": 4.5632045088566825e-05,
|
| 155 |
+
"loss": 0.9645,
|
| 156 |
+
"step": 8400
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.5,
|
| 160 |
+
"grad_norm": 1.3005322217941284,
|
| 161 |
+
"learning_rate": 4.5402001380262254e-05,
|
| 162 |
+
"loss": 0.9536,
|
| 163 |
+
"step": 8800
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.52,
|
| 167 |
+
"grad_norm": 1.2307965755462646,
|
| 168 |
+
"learning_rate": 4.517195767195768e-05,
|
| 169 |
+
"loss": 0.9474,
|
| 170 |
+
"step": 9200
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.55,
|
| 174 |
+
"grad_norm": 1.0385469198226929,
|
| 175 |
+
"learning_rate": 4.49419139636531e-05,
|
| 176 |
+
"loss": 0.9402,
|
| 177 |
+
"step": 9600
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.57,
|
| 181 |
+
"grad_norm": 1.1734727621078491,
|
| 182 |
+
"learning_rate": 4.471187025534852e-05,
|
| 183 |
+
"loss": 0.9321,
|
| 184 |
+
"step": 10000
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.59,
|
| 188 |
+
"grad_norm": 1.3363800048828125,
|
| 189 |
+
"learning_rate": 4.448182654704394e-05,
|
| 190 |
+
"loss": 0.9192,
|
| 191 |
+
"step": 10400
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.62,
|
| 195 |
+
"grad_norm": 1.073585033416748,
|
| 196 |
+
"learning_rate": 4.425178283873936e-05,
|
| 197 |
+
"loss": 0.9378,
|
| 198 |
+
"step": 10800
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.64,
|
| 202 |
+
"grad_norm": 1.0610324144363403,
|
| 203 |
+
"learning_rate": 4.4021739130434786e-05,
|
| 204 |
+
"loss": 0.9187,
|
| 205 |
+
"step": 11200
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.66,
|
| 209 |
+
"grad_norm": 1.039048194885254,
|
| 210 |
+
"learning_rate": 4.379169542213021e-05,
|
| 211 |
+
"loss": 0.9191,
|
| 212 |
+
"step": 11600
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.68,
|
| 216 |
+
"grad_norm": 1.0391401052474976,
|
| 217 |
+
"learning_rate": 4.356165171382563e-05,
|
| 218 |
+
"loss": 0.91,
|
| 219 |
+
"step": 12000
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.71,
|
| 223 |
+
"grad_norm": 1.082083821296692,
|
| 224 |
+
"learning_rate": 4.3331608005521054e-05,
|
| 225 |
+
"loss": 0.9166,
|
| 226 |
+
"step": 12400
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.73,
|
| 230 |
+
"grad_norm": 1.0464677810668945,
|
| 231 |
+
"learning_rate": 4.310156429721647e-05,
|
| 232 |
+
"loss": 0.9234,
|
| 233 |
+
"step": 12800
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.75,
|
| 237 |
+
"grad_norm": 1.0795680284500122,
|
| 238 |
+
"learning_rate": 4.2871520588911894e-05,
|
| 239 |
+
"loss": 0.9004,
|
| 240 |
+
"step": 13200
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.78,
|
| 244 |
+
"grad_norm": 1.2177696228027344,
|
| 245 |
+
"learning_rate": 4.2641476880607317e-05,
|
| 246 |
+
"loss": 0.8991,
|
| 247 |
+
"step": 13600
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.8,
|
| 251 |
+
"grad_norm": 0.9279542565345764,
|
| 252 |
+
"learning_rate": 4.241143317230274e-05,
|
| 253 |
+
"loss": 0.901,
|
| 254 |
+
"step": 14000
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.82,
|
| 258 |
+
"grad_norm": 1.2393149137496948,
|
| 259 |
+
"learning_rate": 4.218138946399816e-05,
|
| 260 |
+
"loss": 0.8898,
|
| 261 |
+
"step": 14400
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.84,
|
| 265 |
+
"grad_norm": 1.2811025381088257,
|
| 266 |
+
"learning_rate": 4.1951920864964345e-05,
|
| 267 |
+
"loss": 0.8975,
|
| 268 |
+
"step": 14800
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.87,
|
| 272 |
+
"grad_norm": 1.0508288145065308,
|
| 273 |
+
"learning_rate": 4.172187715665977e-05,
|
| 274 |
+
"loss": 0.897,
|
| 275 |
+
"step": 15200
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.89,
|
| 279 |
+
"grad_norm": 0.962242066860199,
|
| 280 |
+
"learning_rate": 4.149183344835519e-05,
|
| 281 |
+
"loss": 0.8776,
|
| 282 |
+
"step": 15600
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.91,
|
| 286 |
+
"grad_norm": 0.9615252017974854,
|
| 287 |
+
"learning_rate": 4.126178974005061e-05,
|
| 288 |
+
"loss": 0.873,
|
| 289 |
+
"step": 16000
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.93,
|
| 293 |
+
"grad_norm": 1.040337324142456,
|
| 294 |
+
"learning_rate": 4.103174603174603e-05,
|
| 295 |
+
"loss": 0.8831,
|
| 296 |
+
"step": 16400
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.96,
|
| 300 |
+
"grad_norm": 1.0600088834762573,
|
| 301 |
+
"learning_rate": 4.0801702323441453e-05,
|
| 302 |
+
"loss": 0.8759,
|
| 303 |
+
"step": 16800
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.98,
|
| 307 |
+
"grad_norm": 0.9814367890357971,
|
| 308 |
+
"learning_rate": 4.0572233724407636e-05,
|
| 309 |
+
"loss": 0.8732,
|
| 310 |
+
"step": 17200
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 1.0,
|
| 314 |
+
"eval_loss": 1.0753824710845947,
|
| 315 |
+
"eval_runtime": 239.6966,
|
| 316 |
+
"eval_samples_per_second": 251.464,
|
| 317 |
+
"eval_steps_per_second": 3.93,
|
| 318 |
+
"step": 17548
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 1.0,
|
| 322 |
+
"grad_norm": 1.055283784866333,
|
| 323 |
+
"learning_rate": 4.034219001610306e-05,
|
| 324 |
+
"loss": 0.8697,
|
| 325 |
+
"step": 17600
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 1.03,
|
| 329 |
+
"grad_norm": 1.1038569211959839,
|
| 330 |
+
"learning_rate": 4.011272141706924e-05,
|
| 331 |
+
"loss": 0.8246,
|
| 332 |
+
"step": 18000
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 1.05,
|
| 336 |
+
"grad_norm": 0.9692428708076477,
|
| 337 |
+
"learning_rate": 3.9882677708764665e-05,
|
| 338 |
+
"loss": 0.8284,
|
| 339 |
+
"step": 18400
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 1.07,
|
| 343 |
+
"grad_norm": 1.093485951423645,
|
| 344 |
+
"learning_rate": 3.965263400046009e-05,
|
| 345 |
+
"loss": 0.8271,
|
| 346 |
+
"step": 18800
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 1.09,
|
| 350 |
+
"grad_norm": 1.1435869932174683,
|
| 351 |
+
"learning_rate": 3.942259029215551e-05,
|
| 352 |
+
"loss": 0.8198,
|
| 353 |
+
"step": 19200
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 1.12,
|
| 357 |
+
"grad_norm": 1.389695644378662,
|
| 358 |
+
"learning_rate": 3.9192546583850934e-05,
|
| 359 |
+
"loss": 0.8223,
|
| 360 |
+
"step": 19600
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 1.14,
|
| 364 |
+
"grad_norm": 1.081563949584961,
|
| 365 |
+
"learning_rate": 3.896307798481712e-05,
|
| 366 |
+
"loss": 0.8078,
|
| 367 |
+
"step": 20000
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 1.16,
|
| 371 |
+
"grad_norm": 1.20356023311615,
|
| 372 |
+
"learning_rate": 3.873303427651253e-05,
|
| 373 |
+
"loss": 0.8216,
|
| 374 |
+
"step": 20400
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 1.19,
|
| 378 |
+
"grad_norm": 1.2045621871948242,
|
| 379 |
+
"learning_rate": 3.850299056820796e-05,
|
| 380 |
+
"loss": 0.8222,
|
| 381 |
+
"step": 20800
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 1.21,
|
| 385 |
+
"grad_norm": 0.969454824924469,
|
| 386 |
+
"learning_rate": 3.8272946859903386e-05,
|
| 387 |
+
"loss": 0.803,
|
| 388 |
+
"step": 21200
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 1.23,
|
| 392 |
+
"grad_norm": 1.2209794521331787,
|
| 393 |
+
"learning_rate": 3.804290315159881e-05,
|
| 394 |
+
"loss": 0.8115,
|
| 395 |
+
"step": 21600
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 1.25,
|
| 399 |
+
"grad_norm": 1.0688341856002808,
|
| 400 |
+
"learning_rate": 3.781285944329423e-05,
|
| 401 |
+
"loss": 0.8051,
|
| 402 |
+
"step": 22000
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 1.28,
|
| 406 |
+
"grad_norm": 1.1031506061553955,
|
| 407 |
+
"learning_rate": 3.7582815734989655e-05,
|
| 408 |
+
"loss": 0.8059,
|
| 409 |
+
"step": 22400
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 1.3,
|
| 413 |
+
"grad_norm": 0.9878343939781189,
|
| 414 |
+
"learning_rate": 3.735277202668507e-05,
|
| 415 |
+
"loss": 0.8054,
|
| 416 |
+
"step": 22800
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 1.32,
|
| 420 |
+
"grad_norm": 1.327987790107727,
|
| 421 |
+
"learning_rate": 3.7122728318380494e-05,
|
| 422 |
+
"loss": 0.8131,
|
| 423 |
+
"step": 23200
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 1.34,
|
| 427 |
+
"grad_norm": 1.0833244323730469,
|
| 428 |
+
"learning_rate": 3.689268461007592e-05,
|
| 429 |
+
"loss": 0.7936,
|
| 430 |
+
"step": 23600
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 1.37,
|
| 434 |
+
"grad_norm": 1.1618777513504028,
|
| 435 |
+
"learning_rate": 3.666264090177134e-05,
|
| 436 |
+
"loss": 0.7991,
|
| 437 |
+
"step": 24000
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 1.39,
|
| 441 |
+
"grad_norm": 1.022359013557434,
|
| 442 |
+
"learning_rate": 3.643259719346676e-05,
|
| 443 |
+
"loss": 0.8002,
|
| 444 |
+
"step": 24400
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 1.41,
|
| 448 |
+
"grad_norm": 1.2475693225860596,
|
| 449 |
+
"learning_rate": 3.6202553485162186e-05,
|
| 450 |
+
"loss": 0.8001,
|
| 451 |
+
"step": 24800
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 1.44,
|
| 455 |
+
"grad_norm": 1.1127784252166748,
|
| 456 |
+
"learning_rate": 3.59725097768576e-05,
|
| 457 |
+
"loss": 0.7865,
|
| 458 |
+
"step": 25200
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 1.46,
|
| 462 |
+
"grad_norm": 1.2091097831726074,
|
| 463 |
+
"learning_rate": 3.5742466068553025e-05,
|
| 464 |
+
"loss": 0.7899,
|
| 465 |
+
"step": 25600
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 1.48,
|
| 469 |
+
"grad_norm": 0.9588549733161926,
|
| 470 |
+
"learning_rate": 3.551242236024845e-05,
|
| 471 |
+
"loss": 0.7942,
|
| 472 |
+
"step": 26000
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 1.5,
|
| 476 |
+
"grad_norm": 1.195241093635559,
|
| 477 |
+
"learning_rate": 3.528237865194387e-05,
|
| 478 |
+
"loss": 0.7813,
|
| 479 |
+
"step": 26400
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 1.53,
|
| 483 |
+
"grad_norm": 0.9788525700569153,
|
| 484 |
+
"learning_rate": 3.5052334943639294e-05,
|
| 485 |
+
"loss": 0.7805,
|
| 486 |
+
"step": 26800
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 1.55,
|
| 490 |
+
"grad_norm": 1.2794181108474731,
|
| 491 |
+
"learning_rate": 3.482286634460548e-05,
|
| 492 |
+
"loss": 0.7763,
|
| 493 |
+
"step": 27200
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 1.57,
|
| 497 |
+
"grad_norm": 0.9700046181678772,
|
| 498 |
+
"learning_rate": 3.45928226363009e-05,
|
| 499 |
+
"loss": 0.7801,
|
| 500 |
+
"step": 27600
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 1.6,
|
| 504 |
+
"grad_norm": 1.2326452732086182,
|
| 505 |
+
"learning_rate": 3.436335403726708e-05,
|
| 506 |
+
"loss": 0.7864,
|
| 507 |
+
"step": 28000
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 1.62,
|
| 511 |
+
"grad_norm": 1.2367639541625977,
|
| 512 |
+
"learning_rate": 3.4133310328962506e-05,
|
| 513 |
+
"loss": 0.7845,
|
| 514 |
+
"step": 28400
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 1.64,
|
| 518 |
+
"grad_norm": 1.077854871749878,
|
| 519 |
+
"learning_rate": 3.390326662065793e-05,
|
| 520 |
+
"loss": 0.7869,
|
| 521 |
+
"step": 28800
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 1.66,
|
| 525 |
+
"grad_norm": 1.0575716495513916,
|
| 526 |
+
"learning_rate": 3.3673222912353345e-05,
|
| 527 |
+
"loss": 0.7838,
|
| 528 |
+
"step": 29200
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 1.69,
|
| 532 |
+
"grad_norm": 1.1674555540084839,
|
| 533 |
+
"learning_rate": 3.344317920404877e-05,
|
| 534 |
+
"loss": 0.7827,
|
| 535 |
+
"step": 29600
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 1.71,
|
| 539 |
+
"grad_norm": 1.148335337638855,
|
| 540 |
+
"learning_rate": 3.321313549574419e-05,
|
| 541 |
+
"loss": 0.7781,
|
| 542 |
+
"step": 30000
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 1.73,
|
| 546 |
+
"grad_norm": 1.0287448167800903,
|
| 547 |
+
"learning_rate": 3.2983091787439614e-05,
|
| 548 |
+
"loss": 0.7652,
|
| 549 |
+
"step": 30400
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 1.76,
|
| 553 |
+
"grad_norm": 1.2461556196212769,
|
| 554 |
+
"learning_rate": 3.275304807913504e-05,
|
| 555 |
+
"loss": 0.7773,
|
| 556 |
+
"step": 30800
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 1.78,
|
| 560 |
+
"grad_norm": 1.1946007013320923,
|
| 561 |
+
"learning_rate": 3.252357948010122e-05,
|
| 562 |
+
"loss": 0.7694,
|
| 563 |
+
"step": 31200
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 1.8,
|
| 567 |
+
"grad_norm": 1.019499659538269,
|
| 568 |
+
"learning_rate": 3.229353577179664e-05,
|
| 569 |
+
"loss": 0.7803,
|
| 570 |
+
"step": 31600
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 1.82,
|
| 574 |
+
"grad_norm": 1.3375366926193237,
|
| 575 |
+
"learning_rate": 3.2063492063492065e-05,
|
| 576 |
+
"loss": 0.7684,
|
| 577 |
+
"step": 32000
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 1.85,
|
| 581 |
+
"grad_norm": 1.2477443218231201,
|
| 582 |
+
"learning_rate": 3.183344835518749e-05,
|
| 583 |
+
"loss": 0.7657,
|
| 584 |
+
"step": 32400
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 1.87,
|
| 588 |
+
"grad_norm": 1.1749552488327026,
|
| 589 |
+
"learning_rate": 3.160340464688291e-05,
|
| 590 |
+
"loss": 0.767,
|
| 591 |
+
"step": 32800
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 1.89,
|
| 595 |
+
"grad_norm": 1.0863006114959717,
|
| 596 |
+
"learning_rate": 3.1373360938578334e-05,
|
| 597 |
+
"loss": 0.767,
|
| 598 |
+
"step": 33200
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 1.91,
|
| 602 |
+
"grad_norm": 0.9976168870925903,
|
| 603 |
+
"learning_rate": 3.114389233954452e-05,
|
| 604 |
+
"loss": 0.7536,
|
| 605 |
+
"step": 33600
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 1.94,
|
| 609 |
+
"grad_norm": 1.1924540996551514,
|
| 610 |
+
"learning_rate": 3.09144237405107e-05,
|
| 611 |
+
"loss": 0.7622,
|
| 612 |
+
"step": 34000
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 1.96,
|
| 616 |
+
"grad_norm": 1.0996850728988647,
|
| 617 |
+
"learning_rate": 3.068438003220612e-05,
|
| 618 |
+
"loss": 0.7569,
|
| 619 |
+
"step": 34400
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 1.98,
|
| 623 |
+
"grad_norm": 1.2163282632827759,
|
| 624 |
+
"learning_rate": 3.0454336323901546e-05,
|
| 625 |
+
"loss": 0.7667,
|
| 626 |
+
"step": 34800
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 2.0,
|
| 630 |
+
"eval_loss": 1.0829898118972778,
|
| 631 |
+
"eval_runtime": 239.7954,
|
| 632 |
+
"eval_samples_per_second": 251.36,
|
| 633 |
+
"eval_steps_per_second": 3.928,
|
| 634 |
+
"step": 35096
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 2.01,
|
| 638 |
+
"grad_norm": 1.1651737689971924,
|
| 639 |
+
"learning_rate": 3.0224292615596966e-05,
|
| 640 |
+
"loss": 0.7442,
|
| 641 |
+
"step": 35200
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 2.03,
|
| 645 |
+
"grad_norm": 1.1764894723892212,
|
| 646 |
+
"learning_rate": 2.999424890729239e-05,
|
| 647 |
+
"loss": 0.714,
|
| 648 |
+
"step": 35600
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 2.05,
|
| 652 |
+
"grad_norm": 1.1951353549957275,
|
| 653 |
+
"learning_rate": 2.976420519898781e-05,
|
| 654 |
+
"loss": 0.7076,
|
| 655 |
+
"step": 36000
|
| 656 |
+
},
|
| 657 |
+
{
|
| 658 |
+
"epoch": 2.07,
|
| 659 |
+
"grad_norm": 1.1282097101211548,
|
| 660 |
+
"learning_rate": 2.953416149068323e-05,
|
| 661 |
+
"loss": 0.7105,
|
| 662 |
+
"step": 36400
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 2.1,
|
| 666 |
+
"grad_norm": 1.3397319316864014,
|
| 667 |
+
"learning_rate": 2.9304117782378654e-05,
|
| 668 |
+
"loss": 0.7023,
|
| 669 |
+
"step": 36800
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 2.12,
|
| 673 |
+
"grad_norm": 1.1150188446044922,
|
| 674 |
+
"learning_rate": 2.9074074074074077e-05,
|
| 675 |
+
"loss": 0.7035,
|
| 676 |
+
"step": 37200
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 2.14,
|
| 680 |
+
"grad_norm": 1.2119678258895874,
|
| 681 |
+
"learning_rate": 2.8844030365769497e-05,
|
| 682 |
+
"loss": 0.7168,
|
| 683 |
+
"step": 37600
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 2.17,
|
| 687 |
+
"grad_norm": 1.167506456375122,
|
| 688 |
+
"learning_rate": 2.861398665746492e-05,
|
| 689 |
+
"loss": 0.7125,
|
| 690 |
+
"step": 38000
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 2.19,
|
| 694 |
+
"grad_norm": 1.0915708541870117,
|
| 695 |
+
"learning_rate": 2.8384518058431102e-05,
|
| 696 |
+
"loss": 0.7101,
|
| 697 |
+
"step": 38400
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 2.21,
|
| 701 |
+
"grad_norm": 1.135021686553955,
|
| 702 |
+
"learning_rate": 2.8154474350126525e-05,
|
| 703 |
+
"loss": 0.7145,
|
| 704 |
+
"step": 38800
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 2.23,
|
| 708 |
+
"grad_norm": 1.3739718198776245,
|
| 709 |
+
"learning_rate": 2.792443064182195e-05,
|
| 710 |
+
"loss": 0.7096,
|
| 711 |
+
"step": 39200
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 2.26,
|
| 715 |
+
"grad_norm": 1.1629129648208618,
|
| 716 |
+
"learning_rate": 2.7694386933517368e-05,
|
| 717 |
+
"loss": 0.7053,
|
| 718 |
+
"step": 39600
|
| 719 |
+
},
|
| 720 |
+
{
|
| 721 |
+
"epoch": 2.28,
|
| 722 |
+
"grad_norm": 0.9963687062263489,
|
| 723 |
+
"learning_rate": 2.746434322521279e-05,
|
| 724 |
+
"loss": 0.7012,
|
| 725 |
+
"step": 40000
|
| 726 |
+
},
|
| 727 |
+
{
|
| 728 |
+
"epoch": 2.3,
|
| 729 |
+
"grad_norm": 1.0318909883499146,
|
| 730 |
+
"learning_rate": 2.7234874626178974e-05,
|
| 731 |
+
"loss": 0.713,
|
| 732 |
+
"step": 40400
|
| 733 |
+
},
|
| 734 |
+
{
|
| 735 |
+
"epoch": 2.33,
|
| 736 |
+
"grad_norm": 1.0613532066345215,
|
| 737 |
+
"learning_rate": 2.7004830917874397e-05,
|
| 738 |
+
"loss": 0.704,
|
| 739 |
+
"step": 40800
|
| 740 |
+
},
|
| 741 |
+
{
|
| 742 |
+
"epoch": 2.35,
|
| 743 |
+
"grad_norm": 1.1298637390136719,
|
| 744 |
+
"learning_rate": 2.677478720956982e-05,
|
| 745 |
+
"loss": 0.708,
|
| 746 |
+
"step": 41200
|
| 747 |
+
},
|
| 748 |
+
{
|
| 749 |
+
"epoch": 2.37,
|
| 750 |
+
"grad_norm": 1.1079801321029663,
|
| 751 |
+
"learning_rate": 2.654474350126524e-05,
|
| 752 |
+
"loss": 0.6975,
|
| 753 |
+
"step": 41600
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 2.39,
|
| 757 |
+
"grad_norm": 1.0751113891601562,
|
| 758 |
+
"learning_rate": 2.6314699792960662e-05,
|
| 759 |
+
"loss": 0.6999,
|
| 760 |
+
"step": 42000
|
| 761 |
+
},
|
| 762 |
+
{
|
| 763 |
+
"epoch": 2.42,
|
| 764 |
+
"grad_norm": 1.1240077018737793,
|
| 765 |
+
"learning_rate": 2.6085231193926845e-05,
|
| 766 |
+
"loss": 0.7055,
|
| 767 |
+
"step": 42400
|
| 768 |
+
},
|
| 769 |
+
{
|
| 770 |
+
"epoch": 2.44,
|
| 771 |
+
"grad_norm": 1.0788402557373047,
|
| 772 |
+
"learning_rate": 2.5855187485622268e-05,
|
| 773 |
+
"loss": 0.7055,
|
| 774 |
+
"step": 42800
|
| 775 |
+
},
|
| 776 |
+
{
|
| 777 |
+
"epoch": 2.46,
|
| 778 |
+
"grad_norm": 1.00369131565094,
|
| 779 |
+
"learning_rate": 2.562514377731769e-05,
|
| 780 |
+
"loss": 0.6949,
|
| 781 |
+
"step": 43200
|
| 782 |
+
},
|
| 783 |
+
{
|
| 784 |
+
"epoch": 2.48,
|
| 785 |
+
"grad_norm": 1.1382017135620117,
|
| 786 |
+
"learning_rate": 2.539510006901311e-05,
|
| 787 |
+
"loss": 0.7093,
|
| 788 |
+
"step": 43600
|
| 789 |
+
},
|
| 790 |
+
{
|
| 791 |
+
"epoch": 2.51,
|
| 792 |
+
"grad_norm": 1.0273314714431763,
|
| 793 |
+
"learning_rate": 2.5165056360708534e-05,
|
| 794 |
+
"loss": 0.7066,
|
| 795 |
+
"step": 44000
|
| 796 |
+
},
|
| 797 |
+
{
|
| 798 |
+
"epoch": 2.53,
|
| 799 |
+
"grad_norm": 1.331964373588562,
|
| 800 |
+
"learning_rate": 2.4935012652403957e-05,
|
| 801 |
+
"loss": 0.7037,
|
| 802 |
+
"step": 44400
|
| 803 |
+
},
|
| 804 |
+
{
|
| 805 |
+
"epoch": 2.55,
|
| 806 |
+
"grad_norm": 1.102133870124817,
|
| 807 |
+
"learning_rate": 2.470496894409938e-05,
|
| 808 |
+
"loss": 0.7028,
|
| 809 |
+
"step": 44800
|
| 810 |
+
},
|
| 811 |
+
{
|
| 812 |
+
"epoch": 2.58,
|
| 813 |
+
"grad_norm": 1.131090521812439,
|
| 814 |
+
"learning_rate": 2.4474925235794803e-05,
|
| 815 |
+
"loss": 0.6871,
|
| 816 |
+
"step": 45200
|
| 817 |
+
},
|
| 818 |
+
{
|
| 819 |
+
"epoch": 2.6,
|
| 820 |
+
"grad_norm": 1.1939336061477661,
|
| 821 |
+
"learning_rate": 2.4244881527490222e-05,
|
| 822 |
+
"loss": 0.6966,
|
| 823 |
+
"step": 45600
|
| 824 |
+
},
|
| 825 |
+
{
|
| 826 |
+
"epoch": 2.62,
|
| 827 |
+
"grad_norm": 1.344831109046936,
|
| 828 |
+
"learning_rate": 2.4014837819185645e-05,
|
| 829 |
+
"loss": 0.6933,
|
| 830 |
+
"step": 46000
|
| 831 |
+
},
|
| 832 |
+
{
|
| 833 |
+
"epoch": 2.64,
|
| 834 |
+
"grad_norm": 0.9559622406959534,
|
| 835 |
+
"learning_rate": 2.3784794110881068e-05,
|
| 836 |
+
"loss": 0.6916,
|
| 837 |
+
"step": 46400
|
| 838 |
+
},
|
| 839 |
+
{
|
| 840 |
+
"epoch": 2.67,
|
| 841 |
+
"grad_norm": 1.182010293006897,
|
| 842 |
+
"learning_rate": 2.355475040257649e-05,
|
| 843 |
+
"loss": 0.6903,
|
| 844 |
+
"step": 46800
|
| 845 |
+
},
|
| 846 |
+
{
|
| 847 |
+
"epoch": 2.69,
|
| 848 |
+
"grad_norm": 1.080712080001831,
|
| 849 |
+
"learning_rate": 2.3325281803542674e-05,
|
| 850 |
+
"loss": 0.6965,
|
| 851 |
+
"step": 47200
|
| 852 |
+
},
|
| 853 |
+
{
|
| 854 |
+
"epoch": 2.71,
|
| 855 |
+
"grad_norm": 1.2468616962432861,
|
| 856 |
+
"learning_rate": 2.3095238095238097e-05,
|
| 857 |
+
"loss": 0.6906,
|
| 858 |
+
"step": 47600
|
| 859 |
+
},
|
| 860 |
+
{
|
| 861 |
+
"epoch": 2.74,
|
| 862 |
+
"grad_norm": 1.0585706233978271,
|
| 863 |
+
"learning_rate": 2.286519438693352e-05,
|
| 864 |
+
"loss": 0.6966,
|
| 865 |
+
"step": 48000
|
| 866 |
+
},
|
| 867 |
+
{
|
| 868 |
+
"epoch": 2.76,
|
| 869 |
+
"grad_norm": 1.2725940942764282,
|
| 870 |
+
"learning_rate": 2.2635150678628943e-05,
|
| 871 |
+
"loss": 0.6894,
|
| 872 |
+
"step": 48400
|
| 873 |
+
},
|
| 874 |
+
{
|
| 875 |
+
"epoch": 2.78,
|
| 876 |
+
"grad_norm": 1.1753593683242798,
|
| 877 |
+
"learning_rate": 2.2405106970324362e-05,
|
| 878 |
+
"loss": 0.6806,
|
| 879 |
+
"step": 48800
|
| 880 |
+
},
|
| 881 |
+
{
|
| 882 |
+
"epoch": 2.8,
|
| 883 |
+
"grad_norm": 1.117319941520691,
|
| 884 |
+
"learning_rate": 2.2175063262019785e-05,
|
| 885 |
+
"loss": 0.6879,
|
| 886 |
+
"step": 49200
|
| 887 |
+
},
|
| 888 |
+
{
|
| 889 |
+
"epoch": 2.83,
|
| 890 |
+
"grad_norm": 1.2521744966506958,
|
| 891 |
+
"learning_rate": 2.194501955371521e-05,
|
| 892 |
+
"loss": 0.6808,
|
| 893 |
+
"step": 49600
|
| 894 |
+
},
|
| 895 |
+
{
|
| 896 |
+
"epoch": 2.85,
|
| 897 |
+
"grad_norm": 1.396971344947815,
|
| 898 |
+
"learning_rate": 2.1714975845410628e-05,
|
| 899 |
+
"loss": 0.6798,
|
| 900 |
+
"step": 50000
|
| 901 |
+
},
|
| 902 |
+
{
|
| 903 |
+
"epoch": 2.87,
|
| 904 |
+
"grad_norm": 1.0855846405029297,
|
| 905 |
+
"learning_rate": 2.148493213710605e-05,
|
| 906 |
+
"loss": 0.6978,
|
| 907 |
+
"step": 50400
|
| 908 |
+
},
|
| 909 |
+
{
|
| 910 |
+
"epoch": 2.89,
|
| 911 |
+
"grad_norm": 1.199013113975525,
|
| 912 |
+
"learning_rate": 2.1254888428801474e-05,
|
| 913 |
+
"loss": 0.6882,
|
| 914 |
+
"step": 50800
|
| 915 |
+
},
|
| 916 |
+
{
|
| 917 |
+
"epoch": 2.92,
|
| 918 |
+
"grad_norm": 1.366407871246338,
|
| 919 |
+
"learning_rate": 2.1024844720496894e-05,
|
| 920 |
+
"loss": 0.6882,
|
| 921 |
+
"step": 51200
|
| 922 |
+
},
|
| 923 |
+
{
|
| 924 |
+
"epoch": 2.94,
|
| 925 |
+
"grad_norm": 1.1709498167037964,
|
| 926 |
+
"learning_rate": 2.0794801012192317e-05,
|
| 927 |
+
"loss": 0.6907,
|
| 928 |
+
"step": 51600
|
| 929 |
+
},
|
| 930 |
+
{
|
| 931 |
+
"epoch": 2.96,
|
| 932 |
+
"grad_norm": 1.1881307363510132,
|
| 933 |
+
"learning_rate": 2.05653324131585e-05,
|
| 934 |
+
"loss": 0.6883,
|
| 935 |
+
"step": 52000
|
| 936 |
+
},
|
| 937 |
+
{
|
| 938 |
+
"epoch": 2.99,
|
| 939 |
+
"grad_norm": 1.4105783700942993,
|
| 940 |
+
"learning_rate": 2.0335288704853922e-05,
|
| 941 |
+
"loss": 0.6833,
|
| 942 |
+
"step": 52400
|
| 943 |
+
},
|
| 944 |
+
{
|
| 945 |
+
"epoch": 3.0,
|
| 946 |
+
"eval_loss": 1.0844900608062744,
|
| 947 |
+
"eval_runtime": 239.8565,
|
| 948 |
+
"eval_samples_per_second": 251.296,
|
| 949 |
+
"eval_steps_per_second": 3.927,
|
| 950 |
+
"step": 52644
|
| 951 |
+
},
|
| 952 |
+
{
|
| 953 |
+
"epoch": 3.01,
|
| 954 |
+
"grad_norm": 1.4675981998443604,
|
| 955 |
+
"learning_rate": 2.0105244996549345e-05,
|
| 956 |
+
"loss": 0.6679,
|
| 957 |
+
"step": 52800
|
| 958 |
+
},
|
| 959 |
+
{
|
| 960 |
+
"epoch": 3.03,
|
| 961 |
+
"grad_norm": 1.151491403579712,
|
| 962 |
+
"learning_rate": 1.9875201288244768e-05,
|
| 963 |
+
"loss": 0.6501,
|
| 964 |
+
"step": 53200
|
| 965 |
+
},
|
| 966 |
+
{
|
| 967 |
+
"epoch": 3.05,
|
| 968 |
+
"grad_norm": 1.0938260555267334,
|
| 969 |
+
"learning_rate": 1.964515757994019e-05,
|
| 970 |
+
"loss": 0.6396,
|
| 971 |
+
"step": 53600
|
| 972 |
+
},
|
| 973 |
+
{
|
| 974 |
+
"epoch": 3.08,
|
| 975 |
+
"grad_norm": 1.055185317993164,
|
| 976 |
+
"learning_rate": 1.941511387163561e-05,
|
| 977 |
+
"loss": 0.6442,
|
| 978 |
+
"step": 54000
|
| 979 |
+
},
|
| 980 |
+
{
|
| 981 |
+
"epoch": 3.1,
|
| 982 |
+
"grad_norm": 1.0307785272598267,
|
| 983 |
+
"learning_rate": 1.9185645272601797e-05,
|
| 984 |
+
"loss": 0.6489,
|
| 985 |
+
"step": 54400
|
| 986 |
+
},
|
| 987 |
+
{
|
| 988 |
+
"epoch": 3.12,
|
| 989 |
+
"grad_norm": 1.184102177619934,
|
| 990 |
+
"learning_rate": 1.8955601564297217e-05,
|
| 991 |
+
"loss": 0.6454,
|
| 992 |
+
"step": 54800
|
| 993 |
+
},
|
| 994 |
+
{
|
| 995 |
+
"epoch": 3.15,
|
| 996 |
+
"grad_norm": 1.1798542737960815,
|
| 997 |
+
"learning_rate": 1.872555785599264e-05,
|
| 998 |
+
"loss": 0.6552,
|
| 999 |
+
"step": 55200
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"epoch": 3.17,
|
| 1003 |
+
"grad_norm": 1.1375089883804321,
|
| 1004 |
+
"learning_rate": 1.8496089256958822e-05,
|
| 1005 |
+
"loss": 0.6359,
|
| 1006 |
+
"step": 55600
|
| 1007 |
+
},
|
| 1008 |
+
{
|
| 1009 |
+
"epoch": 3.19,
|
| 1010 |
+
"grad_norm": 1.0475974082946777,
|
| 1011 |
+
"learning_rate": 1.8266045548654245e-05,
|
| 1012 |
+
"loss": 0.6374,
|
| 1013 |
+
"step": 56000
|
| 1014 |
+
},
|
| 1015 |
+
{
|
| 1016 |
+
"epoch": 3.21,
|
| 1017 |
+
"grad_norm": 1.0948106050491333,
|
| 1018 |
+
"learning_rate": 1.803600184034967e-05,
|
| 1019 |
+
"loss": 0.6431,
|
| 1020 |
+
"step": 56400
|
| 1021 |
+
},
|
| 1022 |
+
{
|
| 1023 |
+
"epoch": 3.24,
|
| 1024 |
+
"grad_norm": 1.1488378047943115,
|
| 1025 |
+
"learning_rate": 1.7805958132045088e-05,
|
| 1026 |
+
"loss": 0.646,
|
| 1027 |
+
"step": 56800
|
| 1028 |
+
},
|
| 1029 |
+
{
|
| 1030 |
+
"epoch": 3.26,
|
| 1031 |
+
"grad_norm": 1.1257692575454712,
|
| 1032 |
+
"learning_rate": 1.757591442374051e-05,
|
| 1033 |
+
"loss": 0.6408,
|
| 1034 |
+
"step": 57200
|
| 1035 |
+
},
|
| 1036 |
+
{
|
| 1037 |
+
"epoch": 3.28,
|
| 1038 |
+
"grad_norm": 1.1101455688476562,
|
| 1039 |
+
"learning_rate": 1.7345870715435934e-05,
|
| 1040 |
+
"loss": 0.6389,
|
| 1041 |
+
"step": 57600
|
| 1042 |
+
},
|
| 1043 |
+
{
|
| 1044 |
+
"epoch": 3.31,
|
| 1045 |
+
"grad_norm": 1.329904556274414,
|
| 1046 |
+
"learning_rate": 1.7115827007131354e-05,
|
| 1047 |
+
"loss": 0.6399,
|
| 1048 |
+
"step": 58000
|
| 1049 |
+
},
|
| 1050 |
+
{
|
| 1051 |
+
"epoch": 3.33,
|
| 1052 |
+
"grad_norm": 1.2944815158843994,
|
| 1053 |
+
"learning_rate": 1.6885783298826777e-05,
|
| 1054 |
+
"loss": 0.6421,
|
| 1055 |
+
"step": 58400
|
| 1056 |
+
},
|
| 1057 |
+
{
|
| 1058 |
+
"epoch": 3.35,
|
| 1059 |
+
"grad_norm": 1.1607027053833008,
|
| 1060 |
+
"learning_rate": 1.6655739590522203e-05,
|
| 1061 |
+
"loss": 0.637,
|
| 1062 |
+
"step": 58800
|
| 1063 |
+
},
|
| 1064 |
+
{
|
| 1065 |
+
"epoch": 3.37,
|
| 1066 |
+
"grad_norm": 1.0392543077468872,
|
| 1067 |
+
"learning_rate": 1.6426270991488382e-05,
|
| 1068 |
+
"loss": 0.6411,
|
| 1069 |
+
"step": 59200
|
| 1070 |
+
},
|
| 1071 |
+
{
|
| 1072 |
+
"epoch": 3.4,
|
| 1073 |
+
"grad_norm": 1.3244273662567139,
|
| 1074 |
+
"learning_rate": 1.6196227283183805e-05,
|
| 1075 |
+
"loss": 0.6473,
|
| 1076 |
+
"step": 59600
|
| 1077 |
+
},
|
| 1078 |
+
{
|
| 1079 |
+
"epoch": 3.42,
|
| 1080 |
+
"grad_norm": 1.1351373195648193,
|
| 1081 |
+
"learning_rate": 1.5966183574879228e-05,
|
| 1082 |
+
"loss": 0.6298,
|
| 1083 |
+
"step": 60000
|
| 1084 |
+
},
|
| 1085 |
+
{
|
| 1086 |
+
"epoch": 3.44,
|
| 1087 |
+
"grad_norm": 1.1698590517044067,
|
| 1088 |
+
"learning_rate": 1.573613986657465e-05,
|
| 1089 |
+
"loss": 0.6355,
|
| 1090 |
+
"step": 60400
|
| 1091 |
+
},
|
| 1092 |
+
{
|
| 1093 |
+
"epoch": 3.46,
|
| 1094 |
+
"grad_norm": 1.2005553245544434,
|
| 1095 |
+
"learning_rate": 1.5506671267540834e-05,
|
| 1096 |
+
"loss": 0.6395,
|
| 1097 |
+
"step": 60800
|
| 1098 |
+
},
|
| 1099 |
+
{
|
| 1100 |
+
"epoch": 3.49,
|
| 1101 |
+
"grad_norm": 0.97503662109375,
|
| 1102 |
+
"learning_rate": 1.5276627559236257e-05,
|
| 1103 |
+
"loss": 0.6437,
|
| 1104 |
+
"step": 61200
|
| 1105 |
+
},
|
| 1106 |
+
{
|
| 1107 |
+
"epoch": 3.51,
|
| 1108 |
+
"grad_norm": 1.2518908977508545,
|
| 1109 |
+
"learning_rate": 1.5046583850931678e-05,
|
| 1110 |
+
"loss": 0.6385,
|
| 1111 |
+
"step": 61600
|
| 1112 |
+
},
|
| 1113 |
+
{
|
| 1114 |
+
"epoch": 3.53,
|
| 1115 |
+
"grad_norm": 1.2661454677581787,
|
| 1116 |
+
"learning_rate": 1.48165401426271e-05,
|
| 1117 |
+
"loss": 0.6403,
|
| 1118 |
+
"step": 62000
|
| 1119 |
+
},
|
| 1120 |
+
{
|
| 1121 |
+
"epoch": 3.56,
|
| 1122 |
+
"grad_norm": 1.2612046003341675,
|
| 1123 |
+
"learning_rate": 1.4586496434322523e-05,
|
| 1124 |
+
"loss": 0.6442,
|
| 1125 |
+
"step": 62400
|
| 1126 |
+
},
|
| 1127 |
+
{
|
| 1128 |
+
"epoch": 3.58,
|
| 1129 |
+
"grad_norm": 1.1942335367202759,
|
| 1130 |
+
"learning_rate": 1.4356452726017944e-05,
|
| 1131 |
+
"loss": 0.6383,
|
| 1132 |
+
"step": 62800
|
| 1133 |
+
},
|
| 1134 |
+
{
|
| 1135 |
+
"epoch": 3.6,
|
| 1136 |
+
"grad_norm": 1.1030133962631226,
|
| 1137 |
+
"learning_rate": 1.4126409017713365e-05,
|
| 1138 |
+
"loss": 0.6277,
|
| 1139 |
+
"step": 63200
|
| 1140 |
+
},
|
| 1141 |
+
{
|
| 1142 |
+
"epoch": 3.62,
|
| 1143 |
+
"grad_norm": 1.2485852241516113,
|
| 1144 |
+
"learning_rate": 1.3896365309408788e-05,
|
| 1145 |
+
"loss": 0.6414,
|
| 1146 |
+
"step": 63600
|
| 1147 |
+
},
|
| 1148 |
+
{
|
| 1149 |
+
"epoch": 3.65,
|
| 1150 |
+
"grad_norm": 0.9925839900970459,
|
| 1151 |
+
"learning_rate": 1.366632160110421e-05,
|
| 1152 |
+
"loss": 0.6337,
|
| 1153 |
+
"step": 64000
|
| 1154 |
+
},
|
| 1155 |
+
{
|
| 1156 |
+
"epoch": 3.67,
|
| 1157 |
+
"grad_norm": 1.3896905183792114,
|
| 1158 |
+
"learning_rate": 1.343627789279963e-05,
|
| 1159 |
+
"loss": 0.6314,
|
| 1160 |
+
"step": 64400
|
| 1161 |
+
},
|
| 1162 |
+
{
|
| 1163 |
+
"epoch": 3.69,
|
| 1164 |
+
"grad_norm": 1.1392475366592407,
|
| 1165 |
+
"learning_rate": 1.3206809293765815e-05,
|
| 1166 |
+
"loss": 0.6312,
|
| 1167 |
+
"step": 64800
|
| 1168 |
+
},
|
| 1169 |
+
{
|
| 1170 |
+
"epoch": 3.72,
|
| 1171 |
+
"grad_norm": 1.2051880359649658,
|
| 1172 |
+
"learning_rate": 1.2976765585461237e-05,
|
| 1173 |
+
"loss": 0.6198,
|
| 1174 |
+
"step": 65200
|
| 1175 |
+
},
|
| 1176 |
+
{
|
| 1177 |
+
"epoch": 3.74,
|
| 1178 |
+
"grad_norm": 1.3581410646438599,
|
| 1179 |
+
"learning_rate": 1.2746721877156661e-05,
|
| 1180 |
+
"loss": 0.634,
|
| 1181 |
+
"step": 65600
|
| 1182 |
+
},
|
| 1183 |
+
{
|
| 1184 |
+
"epoch": 3.76,
|
| 1185 |
+
"grad_norm": 1.4071406126022339,
|
| 1186 |
+
"learning_rate": 1.2516678168852084e-05,
|
| 1187 |
+
"loss": 0.633,
|
| 1188 |
+
"step": 66000
|
| 1189 |
+
},
|
| 1190 |
+
{
|
| 1191 |
+
"epoch": 3.78,
|
| 1192 |
+
"grad_norm": 1.1921656131744385,
|
| 1193 |
+
"learning_rate": 1.2286634460547504e-05,
|
| 1194 |
+
"loss": 0.6206,
|
| 1195 |
+
"step": 66400
|
| 1196 |
+
},
|
| 1197 |
+
{
|
| 1198 |
+
"epoch": 3.81,
|
| 1199 |
+
"grad_norm": 1.4039461612701416,
|
| 1200 |
+
"learning_rate": 1.2056590752242927e-05,
|
| 1201 |
+
"loss": 0.6341,
|
| 1202 |
+
"step": 66800
|
| 1203 |
+
},
|
| 1204 |
+
{
|
| 1205 |
+
"epoch": 3.83,
|
| 1206 |
+
"grad_norm": 1.3369255065917969,
|
| 1207 |
+
"learning_rate": 1.182654704393835e-05,
|
| 1208 |
+
"loss": 0.6427,
|
| 1209 |
+
"step": 67200
|
| 1210 |
+
},
|
| 1211 |
+
{
|
| 1212 |
+
"epoch": 3.85,
|
| 1213 |
+
"grad_norm": 1.2129446268081665,
|
| 1214 |
+
"learning_rate": 1.1596503335633771e-05,
|
| 1215 |
+
"loss": 0.6293,
|
| 1216 |
+
"step": 67600
|
| 1217 |
+
},
|
| 1218 |
+
{
|
| 1219 |
+
"epoch": 3.88,
|
| 1220 |
+
"grad_norm": 1.264256238937378,
|
| 1221 |
+
"learning_rate": 1.1366459627329192e-05,
|
| 1222 |
+
"loss": 0.6282,
|
| 1223 |
+
"step": 68000
|
| 1224 |
+
},
|
| 1225 |
+
{
|
| 1226 |
+
"epoch": 3.9,
|
| 1227 |
+
"grad_norm": 1.1778966188430786,
|
| 1228 |
+
"learning_rate": 1.1136415919024615e-05,
|
| 1229 |
+
"loss": 0.6383,
|
| 1230 |
+
"step": 68400
|
| 1231 |
+
},
|
| 1232 |
+
{
|
| 1233 |
+
"epoch": 3.92,
|
| 1234 |
+
"grad_norm": 1.045240044593811,
|
| 1235 |
+
"learning_rate": 1.0906372210720037e-05,
|
| 1236 |
+
"loss": 0.6315,
|
| 1237 |
+
"step": 68800
|
| 1238 |
+
},
|
| 1239 |
+
{
|
| 1240 |
+
"epoch": 3.94,
|
| 1241 |
+
"grad_norm": 1.2942785024642944,
|
| 1242 |
+
"learning_rate": 1.0676903611686221e-05,
|
| 1243 |
+
"loss": 0.6276,
|
| 1244 |
+
"step": 69200
|
| 1245 |
+
},
|
| 1246 |
+
{
|
| 1247 |
+
"epoch": 3.97,
|
| 1248 |
+
"grad_norm": 1.2519258260726929,
|
| 1249 |
+
"learning_rate": 1.0446859903381644e-05,
|
| 1250 |
+
"loss": 0.6228,
|
| 1251 |
+
"step": 69600
|
| 1252 |
+
},
|
| 1253 |
+
{
|
| 1254 |
+
"epoch": 3.99,
|
| 1255 |
+
"grad_norm": 1.2884622812271118,
|
| 1256 |
+
"learning_rate": 1.0216816195077065e-05,
|
| 1257 |
+
"loss": 0.6234,
|
| 1258 |
+
"step": 70000
|
| 1259 |
+
},
|
| 1260 |
+
{
|
| 1261 |
+
"epoch": 4.0,
|
| 1262 |
+
"eval_loss": 1.09929621219635,
|
| 1263 |
+
"eval_runtime": 239.9825,
|
| 1264 |
+
"eval_samples_per_second": 251.164,
|
| 1265 |
+
"eval_steps_per_second": 3.925,
|
| 1266 |
+
"step": 70192
|
| 1267 |
+
},
|
| 1268 |
+
{
|
| 1269 |
+
"epoch": 4.01,
|
| 1270 |
+
"grad_norm": 1.029523253440857,
|
| 1271 |
+
"learning_rate": 9.986772486772487e-06,
|
| 1272 |
+
"loss": 0.607,
|
| 1273 |
+
"step": 70400
|
| 1274 |
+
},
|
| 1275 |
+
{
|
| 1276 |
+
"epoch": 4.03,
|
| 1277 |
+
"grad_norm": 1.1874665021896362,
|
| 1278 |
+
"learning_rate": 9.75672877846791e-06,
|
| 1279 |
+
"loss": 0.5992,
|
| 1280 |
+
"step": 70800
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"epoch": 4.06,
|
| 1284 |
+
"grad_norm": 1.3719263076782227,
|
| 1285 |
+
"learning_rate": 9.526685070163331e-06,
|
| 1286 |
+
"loss": 0.5932,
|
| 1287 |
+
"step": 71200
|
| 1288 |
+
},
|
| 1289 |
+
{
|
| 1290 |
+
"epoch": 4.08,
|
| 1291 |
+
"grad_norm": 1.1106728315353394,
|
| 1292 |
+
"learning_rate": 9.296641361858754e-06,
|
| 1293 |
+
"loss": 0.6082,
|
| 1294 |
+
"step": 71600
|
| 1295 |
+
},
|
| 1296 |
+
{
|
| 1297 |
+
"epoch": 4.1,
|
| 1298 |
+
"grad_norm": 1.1333997249603271,
|
| 1299 |
+
"learning_rate": 9.066597653554177e-06,
|
| 1300 |
+
"loss": 0.5958,
|
| 1301 |
+
"step": 72000
|
| 1302 |
+
},
|
| 1303 |
+
{
|
| 1304 |
+
"epoch": 4.13,
|
| 1305 |
+
"grad_norm": 1.2606267929077148,
|
| 1306 |
+
"learning_rate": 8.837129054520358e-06,
|
| 1307 |
+
"loss": 0.6015,
|
| 1308 |
+
"step": 72400
|
| 1309 |
+
},
|
| 1310 |
+
{
|
| 1311 |
+
"epoch": 4.15,
|
| 1312 |
+
"grad_norm": 1.123744249343872,
|
| 1313 |
+
"learning_rate": 8.607085346215783e-06,
|
| 1314 |
+
"loss": 0.6011,
|
| 1315 |
+
"step": 72800
|
| 1316 |
+
},
|
| 1317 |
+
{
|
| 1318 |
+
"epoch": 4.17,
|
| 1319 |
+
"grad_norm": 1.155521273612976,
|
| 1320 |
+
"learning_rate": 8.377041637911204e-06,
|
| 1321 |
+
"loss": 0.5973,
|
| 1322 |
+
"step": 73200
|
| 1323 |
+
},
|
| 1324 |
+
{
|
| 1325 |
+
"epoch": 4.19,
|
| 1326 |
+
"grad_norm": 1.1591954231262207,
|
| 1327 |
+
"learning_rate": 8.146997929606625e-06,
|
| 1328 |
+
"loss": 0.5924,
|
| 1329 |
+
"step": 73600
|
| 1330 |
+
},
|
| 1331 |
+
{
|
| 1332 |
+
"epoch": 4.22,
|
| 1333 |
+
"grad_norm": 1.3380868434906006,
|
| 1334 |
+
"learning_rate": 7.916954221302048e-06,
|
| 1335 |
+
"loss": 0.5983,
|
| 1336 |
+
"step": 74000
|
| 1337 |
+
},
|
| 1338 |
+
{
|
| 1339 |
+
"epoch": 4.24,
|
| 1340 |
+
"grad_norm": 1.2216105461120605,
|
| 1341 |
+
"learning_rate": 7.68691051299747e-06,
|
| 1342 |
+
"loss": 0.5947,
|
| 1343 |
+
"step": 74400
|
| 1344 |
+
},
|
| 1345 |
+
{
|
| 1346 |
+
"epoch": 4.26,
|
| 1347 |
+
"grad_norm": 1.0791873931884766,
|
| 1348 |
+
"learning_rate": 7.4568668046928916e-06,
|
| 1349 |
+
"loss": 0.6054,
|
| 1350 |
+
"step": 74800
|
| 1351 |
+
},
|
| 1352 |
+
{
|
| 1353 |
+
"epoch": 4.29,
|
| 1354 |
+
"grad_norm": 1.1365481615066528,
|
| 1355 |
+
"learning_rate": 7.2268230963883145e-06,
|
| 1356 |
+
"loss": 0.6092,
|
| 1357 |
+
"step": 75200
|
| 1358 |
+
},
|
| 1359 |
+
{
|
| 1360 |
+
"epoch": 4.31,
|
| 1361 |
+
"grad_norm": 1.1376712322235107,
|
| 1362 |
+
"learning_rate": 6.997354497354498e-06,
|
| 1363 |
+
"loss": 0.5942,
|
| 1364 |
+
"step": 75600
|
| 1365 |
+
},
|
| 1366 |
+
{
|
| 1367 |
+
"epoch": 4.33,
|
| 1368 |
+
"grad_norm": 1.1192513704299927,
|
| 1369 |
+
"learning_rate": 6.76731078904992e-06,
|
| 1370 |
+
"loss": 0.5955,
|
| 1371 |
+
"step": 76000
|
| 1372 |
+
},
|
| 1373 |
+
{
|
| 1374 |
+
"epoch": 4.35,
|
| 1375 |
+
"grad_norm": 1.1927390098571777,
|
| 1376 |
+
"learning_rate": 6.537267080745342e-06,
|
| 1377 |
+
"loss": 0.5901,
|
| 1378 |
+
"step": 76400
|
| 1379 |
+
},
|
| 1380 |
+
{
|
| 1381 |
+
"epoch": 4.38,
|
| 1382 |
+
"grad_norm": 1.236060619354248,
|
| 1383 |
+
"learning_rate": 6.307223372440764e-06,
|
| 1384 |
+
"loss": 0.6,
|
| 1385 |
+
"step": 76800
|
| 1386 |
+
},
|
| 1387 |
+
{
|
| 1388 |
+
"epoch": 4.4,
|
| 1389 |
+
"grad_norm": 1.077643871307373,
|
| 1390 |
+
"learning_rate": 6.077179664136186e-06,
|
| 1391 |
+
"loss": 0.6088,
|
| 1392 |
+
"step": 77200
|
| 1393 |
+
},
|
| 1394 |
+
{
|
| 1395 |
+
"epoch": 4.42,
|
| 1396 |
+
"grad_norm": 1.3172234296798706,
|
| 1397 |
+
"learning_rate": 5.847135955831608e-06,
|
| 1398 |
+
"loss": 0.5944,
|
| 1399 |
+
"step": 77600
|
| 1400 |
+
},
|
| 1401 |
+
{
|
| 1402 |
+
"epoch": 4.44,
|
| 1403 |
+
"grad_norm": 1.2222837209701538,
|
| 1404 |
+
"learning_rate": 5.61709224752703e-06,
|
| 1405 |
+
"loss": 0.5976,
|
| 1406 |
+
"step": 78000
|
| 1407 |
+
},
|
| 1408 |
+
{
|
| 1409 |
+
"epoch": 4.47,
|
| 1410 |
+
"grad_norm": 1.2887938022613525,
|
| 1411 |
+
"learning_rate": 5.387048539222452e-06,
|
| 1412 |
+
"loss": 0.6023,
|
| 1413 |
+
"step": 78400
|
| 1414 |
+
},
|
| 1415 |
+
{
|
| 1416 |
+
"epoch": 4.49,
|
| 1417 |
+
"grad_norm": 1.1380060911178589,
|
| 1418 |
+
"learning_rate": 5.157579940188636e-06,
|
| 1419 |
+
"loss": 0.5938,
|
| 1420 |
+
"step": 78800
|
| 1421 |
+
},
|
| 1422 |
+
{
|
| 1423 |
+
"epoch": 4.51,
|
| 1424 |
+
"grad_norm": 1.2178806066513062,
|
| 1425 |
+
"learning_rate": 4.927536231884058e-06,
|
| 1426 |
+
"loss": 0.5916,
|
| 1427 |
+
"step": 79200
|
| 1428 |
+
},
|
| 1429 |
+
{
|
| 1430 |
+
"epoch": 4.54,
|
| 1431 |
+
"grad_norm": 1.2010163068771362,
|
| 1432 |
+
"learning_rate": 4.69749252357948e-06,
|
| 1433 |
+
"loss": 0.5891,
|
| 1434 |
+
"step": 79600
|
| 1435 |
+
},
|
| 1436 |
+
{
|
| 1437 |
+
"epoch": 4.56,
|
| 1438 |
+
"grad_norm": 1.2172470092773438,
|
| 1439 |
+
"learning_rate": 4.467448815274902e-06,
|
| 1440 |
+
"loss": 0.6019,
|
| 1441 |
+
"step": 80000
|
| 1442 |
+
},
|
| 1443 |
+
{
|
| 1444 |
+
"epoch": 4.58,
|
| 1445 |
+
"grad_norm": 1.2008330821990967,
|
| 1446 |
+
"learning_rate": 4.2374051069703245e-06,
|
| 1447 |
+
"loss": 0.596,
|
| 1448 |
+
"step": 80400
|
| 1449 |
+
},
|
| 1450 |
+
{
|
| 1451 |
+
"epoch": 4.6,
|
| 1452 |
+
"grad_norm": 1.3656328916549683,
|
| 1453 |
+
"learning_rate": 4.007936507936508e-06,
|
| 1454 |
+
"loss": 0.6001,
|
| 1455 |
+
"step": 80800
|
| 1456 |
+
},
|
| 1457 |
+
{
|
| 1458 |
+
"epoch": 4.63,
|
| 1459 |
+
"grad_norm": 1.336308240890503,
|
| 1460 |
+
"learning_rate": 3.7778927996319303e-06,
|
| 1461 |
+
"loss": 0.5912,
|
| 1462 |
+
"step": 81200
|
| 1463 |
+
},
|
| 1464 |
+
{
|
| 1465 |
+
"epoch": 4.65,
|
| 1466 |
+
"grad_norm": 1.1399625539779663,
|
| 1467 |
+
"learning_rate": 3.5478490913273524e-06,
|
| 1468 |
+
"loss": 0.5962,
|
| 1469 |
+
"step": 81600
|
| 1470 |
+
},
|
| 1471 |
+
{
|
| 1472 |
+
"epoch": 4.67,
|
| 1473 |
+
"grad_norm": 1.237598180770874,
|
| 1474 |
+
"learning_rate": 3.317805383022775e-06,
|
| 1475 |
+
"loss": 0.5869,
|
| 1476 |
+
"step": 82000
|
| 1477 |
+
},
|
| 1478 |
+
{
|
| 1479 |
+
"epoch": 4.7,
|
| 1480 |
+
"grad_norm": 1.1215174198150635,
|
| 1481 |
+
"learning_rate": 3.0877616747181967e-06,
|
| 1482 |
+
"loss": 0.5927,
|
| 1483 |
+
"step": 82400
|
| 1484 |
+
},
|
| 1485 |
+
{
|
| 1486 |
+
"epoch": 4.72,
|
| 1487 |
+
"grad_norm": 1.3274859189987183,
|
| 1488 |
+
"learning_rate": 2.857717966413619e-06,
|
| 1489 |
+
"loss": 0.6066,
|
| 1490 |
+
"step": 82800
|
| 1491 |
+
},
|
| 1492 |
+
{
|
| 1493 |
+
"epoch": 4.74,
|
| 1494 |
+
"grad_norm": 1.276289463043213,
|
| 1495 |
+
"learning_rate": 2.628249367379802e-06,
|
| 1496 |
+
"loss": 0.5994,
|
| 1497 |
+
"step": 83200
|
| 1498 |
+
},
|
| 1499 |
+
{
|
| 1500 |
+
"epoch": 4.76,
|
| 1501 |
+
"grad_norm": 1.154296636581421,
|
| 1502 |
+
"learning_rate": 2.3982056590752246e-06,
|
| 1503 |
+
"loss": 0.5907,
|
| 1504 |
+
"step": 83600
|
| 1505 |
+
},
|
| 1506 |
+
{
|
| 1507 |
+
"epoch": 4.79,
|
| 1508 |
+
"grad_norm": 1.1015737056732178,
|
| 1509 |
+
"learning_rate": 2.1681619507706463e-06,
|
| 1510 |
+
"loss": 0.6043,
|
| 1511 |
+
"step": 84000
|
| 1512 |
+
},
|
| 1513 |
+
{
|
| 1514 |
+
"epoch": 4.81,
|
| 1515 |
+
"grad_norm": 1.356696367263794,
|
| 1516 |
+
"learning_rate": 1.9381182424660685e-06,
|
| 1517 |
+
"loss": 0.5883,
|
| 1518 |
+
"step": 84400
|
| 1519 |
+
},
|
| 1520 |
+
{
|
| 1521 |
+
"epoch": 4.83,
|
| 1522 |
+
"grad_norm": 1.1508524417877197,
|
| 1523 |
+
"learning_rate": 1.7080745341614908e-06,
|
| 1524 |
+
"loss": 0.5899,
|
| 1525 |
+
"step": 84800
|
| 1526 |
+
},
|
| 1527 |
+
{
|
| 1528 |
+
"epoch": 4.86,
|
| 1529 |
+
"grad_norm": 1.1132149696350098,
|
| 1530 |
+
"learning_rate": 1.478030825856913e-06,
|
| 1531 |
+
"loss": 0.5994,
|
| 1532 |
+
"step": 85200
|
| 1533 |
+
},
|
| 1534 |
+
{
|
| 1535 |
+
"epoch": 4.88,
|
| 1536 |
+
"grad_norm": 1.306624174118042,
|
| 1537 |
+
"learning_rate": 1.2485622268230964e-06,
|
| 1538 |
+
"loss": 0.5891,
|
| 1539 |
+
"step": 85600
|
| 1540 |
+
},
|
| 1541 |
+
{
|
| 1542 |
+
"epoch": 4.9,
|
| 1543 |
+
"grad_norm": 1.234307050704956,
|
| 1544 |
+
"learning_rate": 1.0185185185185188e-06,
|
| 1545 |
+
"loss": 0.5916,
|
| 1546 |
+
"step": 86000
|
| 1547 |
+
},
|
| 1548 |
+
{
|
| 1549 |
+
"epoch": 4.92,
|
| 1550 |
+
"grad_norm": 1.0994372367858887,
|
| 1551 |
+
"learning_rate": 7.884748102139407e-07,
|
| 1552 |
+
"loss": 0.5908,
|
| 1553 |
+
"step": 86400
|
| 1554 |
+
},
|
| 1555 |
+
{
|
| 1556 |
+
"epoch": 4.95,
|
| 1557 |
+
"grad_norm": 1.2712494134902954,
|
| 1558 |
+
"learning_rate": 5.584311019093628e-07,
|
| 1559 |
+
"loss": 0.5963,
|
| 1560 |
+
"step": 86800
|
| 1561 |
+
},
|
| 1562 |
+
{
|
| 1563 |
+
"epoch": 4.97,
|
| 1564 |
+
"grad_norm": 1.2190104722976685,
|
| 1565 |
+
"learning_rate": 3.283873936047849e-07,
|
| 1566 |
+
"loss": 0.5902,
|
| 1567 |
+
"step": 87200
|
| 1568 |
+
},
|
| 1569 |
+
{
|
| 1570 |
+
"epoch": 4.99,
|
| 1571 |
+
"grad_norm": 1.3301359415054321,
|
| 1572 |
+
"learning_rate": 9.891879457096849e-08,
|
| 1573 |
+
"loss": 0.591,
|
| 1574 |
+
"step": 87600
|
| 1575 |
+
},
|
| 1576 |
+
{
|
| 1577 |
+
"epoch": 5.0,
|
| 1578 |
+
"eval_loss": 1.1109092235565186,
|
| 1579 |
+
"eval_runtime": 240.0172,
|
| 1580 |
+
"eval_samples_per_second": 251.128,
|
| 1581 |
+
"eval_steps_per_second": 3.925,
|
| 1582 |
+
"step": 87740
|
| 1583 |
+
},
|
| 1584 |
+
{
|
| 1585 |
+
"epoch": 5.0,
|
| 1586 |
+
"step": 87740,
|
| 1587 |
+
"total_flos": 1.7097588901675008e+18,
|
| 1588 |
+
"train_loss": 0.7401387438351292,
|
| 1589 |
+
"train_runtime": 31448.3717,
|
| 1590 |
+
"train_samples_per_second": 89.283,
|
| 1591 |
+
"train_steps_per_second": 2.79
|
| 1592 |
+
}
|
| 1593 |
+
],
|
| 1594 |
+
"logging_steps": 400,
|
| 1595 |
+
"max_steps": 87740,
|
| 1596 |
+
"num_input_tokens_seen": 0,
|
| 1597 |
+
"num_train_epochs": 5,
|
| 1598 |
+
"save_steps": 500,
|
| 1599 |
+
"total_flos": 1.7097588901675008e+18,
|
| 1600 |
+
"train_batch_size": 32,
|
| 1601 |
+
"trial_name": null,
|
| 1602 |
+
"trial_params": null
|
| 1603 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:621a59c1fa7abfb2989a3fb9a8fe10944574d433fca08f964e9d5588799068a9
|
| 3 |
+
size 5176
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|