Initial commit

.gitattributes

@@ -0,0 +1,4 @@
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text
+runs/** filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,129 @@
+---
+language:
+  - de
+tags:
+  - question-generation
+  - german
+  - text2text-generation
+  - generated_from_trainer
+datasets:
+  - lmqg/qg_dequad
+metrics:
+  - bleu4
+  - f1
+  - rouge
+  - exact_match
+model-index:
+  - name: german-jeopardy-longt5-large
+    results:
+      - task:
+          name: Sequence-to-sequence Language Modeling
+          type: text2text-generation
+        dataset:
+          name: lmqg/qg_dequad
+          type: default
+          args: default
+        metrics:
+          - name: BLEU-4
+            type: bleu4
+            value: 9.50
+          - name: F1
+            type: f1
+            value: 32.03
+          - name: ROUGE-1
+            type: rouge1
+            value: 32.79
+          - name: ROUGE-2
+            type: rouge2
+            value: 14.95
+          - name: ROUGE-L
+            type: rougel
+            value: 31.56
+          - name: ROUGE-Lsum
+            type: rougelsum
+            value: 31.57
+          - name: Exact Match
+            type: exact_match
+            value: 1.36
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# german-jeopardy-longt5-large-1k-64-constant
+
+This model is a fine-tuned version of [google/long-t5-tglobal-large](https://huggingface.co/google/long-t5-tglobal-large) on the [lmqg/qg_dequad](https://huggingface.co/datasets/lmqg/qg_dequad) dataset.
+It achieves the following results on the evaluation set:
+- Loss: 2.5907
+- Brevity Penalty: 0.9367
+- System Length: 19517
+- Reference Length: 20793
+- ROUGE-1: 32.79
+- ROUGE-2: 14.95
+- ROUGE-L: 31.56
+- ROUGE-Lsum: 31.57
+- Exact Match: 1.36
+- BLEU: 9.50
+- F1: 32.03
+
+## Model description
+
+See [google/long-t5-tglobal-large](https://huggingface.co/google/long-t5-tglobal-large) for more information about the
+model architecture.  
+The model was trained on a single NVIDIA RTX 3090 GPU with 24GB of VRAM.
+
+## Intended uses & limitations
+
+This model can be used for question generation on German text.
+
+## Training and evaluation data
+
+See [lmqg/qg_dequad](https://huggingface.co/datasets/lmqg/qg_dequad).
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 0.0001
+- train_batch_size: 2
+- eval_batch_size: 2
+- seed: 7
+- gradient_accumulation_steps: 32
+- total_train_batch_size: 64
+- optimizer: Adafactor
+- lr_scheduler_type: constant
+- num_epochs: 20
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Counts 1 | Counts 2 | Counts 3 | Counts 4 | Totals 1 | Totals 2 | Totals 3 | Totals 4 | Precisions 1 | Precisions 2 | Precisions 3 | Precisions 4 | Brevity Penalty | System Length | Reference Length | ROUGE-1 | ROUGE-2 | ROUGE-L | ROUGE-Lsum | Exact Match |  BLEU   | Mean Generated Length |   F1   |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:--------:|:--------:|:--------:|:--------:|:--------:|:--------:|:--------:|:------------:|:------------:|:------------:|:------------:|:---------------:|:-------------:|:----------------:|:-------:|:-------:|:-------:|:----------:|:-----------:|:-------:|:---------------------:|:------:|
+|    6.5987     |  1.0  | 145  |     5.0696      |   3804   |   134    |    2     |    0     |  22913   |  20709   |  18505   |  16301   |   16.6019    |    0.6471    |    0.0108    |    0.0031    |       1.0       |     22913     |      21250       | 0.0783  |  0.007  | 0.0769  |   0.0768   |     0.0     | 0.1374  |        16.2899        | 0.0814 |
+|    4.7443     |  2.0  | 291  |     4.2270      |   4022   |   188    |    20    |    0     |  17366   |  15162   |  12958   |  10754   |   23.1602    |    1.2399    |    0.1543    |    0.0046    |     0.7996      |     17366     |      21250       | 0.1028  |  0.012  | 0.0991  |   0.099    |     0.0     |  0.303  |        12.9038        | 0.1073 |
+|    4.1412     |  3.0  | 436  |     3.7838      |   3723   |   187    |    26    |    2     |  16515   |  14311   |  12107   |   9903   |   22.5431    |    1.3067    |    0.2148    |    0.0202    |     0.7507      |     16515     |      21250       | 0.0899  | 0.0124  | 0.0886  |   0.0884   |     0.0     | 0.4488  |        12.4769        | 0.0938 |
+|    3.6791     |  4.0  | 582  |     3.4246      |   4576   |   549    |   134    |    26    |  21871   |  19667   |  17463   |  15259   |   20.9227    |    2.7915    |    0.7673    |    0.1704    |       1.0       |     21871     |      21250       | 0.1259  | 0.0296  | 0.1204  |   0.1201   |     0.0     | 1.6623  |        14.5676        | 0.1323 |
+|    3.3523     |  5.0  | 727  |     3.1723      |   4900   |   796    |   210    |    41    |  19389   |  17185   |  14981   |  12777   |   25.2721    |    4.6319    |    1.4018    |    0.3209    |     0.9085      |     19389     |      21250       | 0.1542  | 0.0449  | 0.1486  |   0.1484   |   0.0005    | 2.4472  |        14.3943        | 0.1585 |
+|    3.0161     |  6.0  | 873  |     2.9268      |   5633   |   1182   |   390    |   111    |  19045   |  16841   |  14637   |  12433   |   29.5773    |    7.0186    |    2.6645    |    0.8928    |     0.8907      |     19045     |      21250       |  0.204  |  0.069  |  0.196  |   0.1961   |   0.0045    | 4.1987  |        14.5789        | 0.2074 |
+|    2.7639     |  7.0  | 1018 |     2.7601      |   6100   |   1461   |   499    |   165    |  17924   |  15720   |  13516   |  11312   |   34.0326    |    9.2939    |    3.6919    |    1.4586    |     0.8306      |     17924     |      21250       | 0.2409  | 0.0885  | 0.2332  |   0.2331   |   0.0073    | 5.3362  |        13.8553        | 0.2431 |
+|    2.5036     |  8.0  | 1164 |     2.5729      |   6765   |   1845   |   701    |   273    |  20179   |  17975   |  15771   |  13567   |    33.525    |   10.2643    |    4.4449    |    2.0122    |     0.9483      |     20179     |      21250       | 0.2682  | 0.1079  | 0.2589  |   0.259    |   0.0059    | 7.0633  |        15.7232        | 0.2689 |
+|     2.307     | 8.99  | 1309 |     2.4637      |   7018   |   2047   |   826    |   348    |  19054   |  16850   |  14646   |  12442   |   36.8322    |   12.1484    |    5.6398    |    2.797     |     0.8911      |     19054     |      21250       | 0.2907  | 0.1218  | 0.2799  |   0.2798   |   0.0095    | 8.1681  |        14.8076        | 0.2907 |
+|    2.1012     | 10.0  | 1455 |     2.3614      |   7147   |   2127   |   883    |   389    |  18473   |  16269   |  14065   |  11861   |   38.6889    |   13.0739    |    6.278     |    3.2797    |     0.8604      |     18473     |      21250       | 0.3003  | 0.1275  |  0.289  |   0.2888   |   0.0118    | 8.6921  |        14.2736        | 0.3008 |
+|    1.9538     | 10.99 | 1600 |     2.2980      |   7481   |   2339   |   997    |   459    |  18524   |  16320   |  14116   |  11912   |   40.3854    |   14.3321    |    7.0629    |    3.8533    |     0.8632      |     18524     |      21250       | 0.3192  | 0.1423  | 0.3064  |   0.3068   |   0.0127    |  9.67   |        14.3757        | 0.3167 |
+|    1.7909     | 12.0  | 1746 |     2.2389      |   7675   |   2546   |   1144   |   546    |  18849   |  16645   |  14441   |  12237   |   40.7183    |   15.2959    |    7.9219    |    4.4619    |     0.8804      |     18849     |      21250       | 0.3299  | 0.1528  | 0.3174  |   0.3175   |    0.015    | 10.724  |        14.583         | 0.3279 |
+|    1.6691     | 12.99 | 1891 |     2.1813      |   7858   |   2635   |   1179   |   576    |  18643   |  16439   |  14235   |  12031   |   42.1499    |    16.029    |    8.2824    |    4.7876    |     0.8695      |     18643     |      21250       |  0.344  | 0.1626  |  0.33   |    0.33    |   0.0163    | 11.1241 |        14.3848        | 0.3395 |
+|    1.5361     | 14.0  | 2037 |     2.1546      |   8016   |   2729   |   1249   |   606    |  18754   |  16550   |  14346   |  12142   |   42.7429    |   16.4894    |    8.7063    |    4.9909    |     0.8754      |     18754     |      21250       | 0.3494  | 0.1664  | 0.3349  |   0.3351   |   0.0163    | 11.5803 |        14.564         | 0.3462 |
+|    1.4365     | 14.99 | 2182 |     2.1358      |   8112   |   2839   |   1316   |   647    |  18390   |  16186   |  13982   |  11778   |   44.1109    |   17.5398    |    9.4121    |    5.4933    |      0.856      |     18390     |      21250       | 0.3581  | 0.1761  | 0.3448  |   0.3448   |    0.02     | 12.1055 |        14.1656        | 0.3538 |
+|    1.3263     | 16.0  | 2328 |     2.1190      |   8381   |   2990   |   1430   |   731    |  18892   |  16688   |  14484   |  12280   |   44.3627    |   17.9171    |    9.873     |    5.9528    |     0.8827      |     18892     |      21250       | 0.3681  | 0.1831  | 0.3532  |   0.3534   |   0.0209    | 12.9765 |        14.5445        | 0.363  |
+|    1.2329     | 17.0  | 2474 |     2.1202      |   8449   |   3101   |   1520   |   786    |  18612   |  16408   |  14204   |  12000   |   45.3954    |   18.8993    |   10.7012    |     6.55     |     0.8678      |     18612     |      21250       | 0.3743  | 0.1901  | 0.3603  |   0.3603   |   0.0227    | 13.5903 |        14.1779        | 0.3692 |
+|    1.1557     | 18.0  | 2619 |     2.1282      |   8406   |   3154   |   1558   |   804    |  17958   |  15754   |  13550   |  11346   |   46.8092    |   20.0203    |   11.4982    |    7.0862    |     0.8325      |     17958     |      21250       | 0.3761  |  0.194  | 0.3633  |   0.3636   |   0.0277    | 13.8388 |        13.677         | 0.371  |
+|    1.0658     | 19.0  | 2765 |     2.1232      |   8614   |   3241   |   1610   |   839    |  18955   |  16751   |  14547   |  12343   |   45.4445    |   19.3481    |   11.0676    |    6.7974    |      0.886      |     18955     |      21250       | 0.3803  |  0.196  | 0.3654  |   0.3656   |   0.0272    | 14.2084 |        14.3816        | 0.3749 |
+|    0.9944     | 19.93 | 2900 |     2.1203      |   8658   |   3273   |   1625   |   859    |  18853   |  16649   |  14445   |  12241   |   45.9237    |   19.6588    |   11.2496    |    7.0174    |     0.8806      |     18853     |      21250       | 0.3833  | 0.1977  |  0.369  |   0.3691   |   0.0268    | 14.3883 |        14.2881        | 0.3775 |
+
+
+### Framework versions
+
+- Transformers 4.32.1
+- Pytorch 2.1.0
+- Datasets 2.12.0
+- Tokenizers 0.13.3

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<hl>": 32100
+}

all_results.json

@@ -0,0 +1,64 @@
+{
+    "epoch": 19.93,
+    "eval_bleu": 14.3883,
+    "eval_bp": 0.8806,
+    "eval_counts_1": 8658,
+    "eval_counts_2": 3273,
+    "eval_counts_3": 1625,
+    "eval_counts_4": 859,
+    "eval_exact_match": 0.0268,
+    "eval_f1": 0.3775,
+    "eval_gen_len": 14.2881,
+    "eval_loss": 2.1203458309173584,
+    "eval_precisions_1": 45.9237,
+    "eval_precisions_2": 19.6588,
+    "eval_precisions_3": 11.2496,
+    "eval_precisions_4": 7.0174,
+    "eval_ref_len": 21250,
+    "eval_rouge1": 0.3833,
+    "eval_rouge2": 0.1977,
+    "eval_rougeL": 0.369,
+    "eval_rougeLsum": 0.3691,
+    "eval_runtime": 1370.6553,
+    "eval_samples": 2204,
+    "eval_samples_per_second": 1.608,
+    "eval_steps_per_second": 0.804,
+    "eval_sys_len": 18853,
+    "eval_totals_1": 18853,
+    "eval_totals_2": 16649,
+    "eval_totals_3": 14445,
+    "eval_totals_4": 12241,
+    "predict_bleu": 9.3033,
+    "predict_bp": 0.9422,
+    "predict_counts_1": 7488,
+    "predict_counts_2": 2251,
+    "predict_counts_3": 952,
+    "predict_counts_4": 401,
+    "predict_exact_match": 0.0136,
+    "predict_f1": 0.3147,
+    "predict_gen_len": 15.3144,
+    "predict_loss": 2.6592931747436523,
+    "predict_precisions_1": 38.1554,
+    "predict_precisions_2": 12.9212,
+    "predict_precisions_3": 6.2562,
+    "predict_precisions_4": 3.0815,
+    "predict_ref_len": 20793,
+    "predict_rouge1": 0.3217,
+    "predict_rouge2": 0.1458,
+    "predict_rougeL": 0.3094,
+    "predict_rougeLsum": 0.3093,
+    "predict_runtime": 1413.0164,
+    "predict_samples": 2204,
+    "predict_samples_per_second": 1.56,
+    "predict_steps_per_second": 0.78,
+    "predict_sys_len": 19625,
+    "predict_totals_1": 19625,
+    "predict_totals_2": 17421,
+    "predict_totals_3": 15217,
+    "predict_totals_4": 13013,
+    "train_loss": 2.472949571280644,
+    "train_runtime": 103540.1577,
+    "train_samples": 9314,
+    "train_samples_per_second": 1.799,
+    "train_steps_per_second": 0.028
+}

config.json

@@ -0,0 +1,38 @@
+{
+  "_name_or_path": "google/long-t5-tglobal-large",
+  "architectures": [
+    "LongT5ForConditionalGeneration"
+  ],
+  "d_ff": 2816,
+  "d_kv": 64,
+  "d_model": 1024,
+  "decoder_start_token_id": 0,
+  "dense_act_fn": "gelu_new",
+  "dropout_rate": 0.1,
+  "encoder_attention_type": "transient-global",
+  "eos_token_id": 1,
+  "feed_forward_proj": "gated-gelu",
+  "global_block_size": 16,
+  "initializer_factor": 1.0,
+  "is_encoder_decoder": true,
+  "is_gated_act": true,
+  "layer_norm_epsilon": 1e-06,
+  "length_penalty": 0.0,
+  "local_radius": 127,
+  "max_length": 64,
+  "model_type": "longt5",
+  "n_positions": 4096,
+  "num_beams": 4,
+  "num_decoder_layers": 24,
+  "num_heads": 16,
+  "num_layers": 24,
+  "output_past": true,
+  "pad_token_id": 0,
+  "relative_attention_max_distance": 128,
+  "relative_attention_num_buckets": 32,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.32.1",
+  "use_cache": true,
+  "vocab_size": 32128
+}

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "decoder_start_token_id": 0,
+  "eos_token_id": 1,
+  "length_penalty": 0.0,
+  "max_length": 64,
+  "num_beams": 4,
+  "pad_token_id": 0,
+  "transformers_version": "4.32.1"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:887bb8dc331151daaadcb09d2728182e4a720d0e27c369b132a73a5c84c2d325
+size 3132774536

runs/Oct23_20-43-41_MARVIN-PC/events.out.tfevents.1698086647.MARVIN-PC.17376.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29ff0efc73189ec258ba098ac6e640174f36f7c516dc306cb2cbcaefb827b485
+size 37418

runs/Oct23_20-43-41_MARVIN-PC/events.out.tfevents.1698191568.MARVIN-PC.17376.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b1e59a041573b695c04106c243678211256e5cd73ba7681fce6c4b9afaca6a7
+size 1550

special_tokens_map.json

@@ -0,0 +1,8 @@
+{
+  "additional_special_tokens": [
+    "<hl>"
+  ],
+  "eos_token": "</s>",
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
+}

spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86
+size 791656

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7849fbc2663e2243b74c6bec05a83d501e82817586c56ed636778f2357a8f0c4
+size 2422538

tokenizer_config.json

@@ -0,0 +1,111 @@
+{
+  "additional_special_tokens": [
+    "<extra_id_0>",
+    "<extra_id_1>",
+    "<extra_id_2>",
+    "<extra_id_3>",
+    "<extra_id_4>",
+    "<extra_id_5>",
+    "<extra_id_6>",
+    "<extra_id_7>",
+    "<extra_id_8>",
+    "<extra_id_9>",
+    "<extra_id_10>",
+    "<extra_id_11>",
+    "<extra_id_12>",
+    "<extra_id_13>",
+    "<extra_id_14>",
+    "<extra_id_15>",
+    "<extra_id_16>",
+    "<extra_id_17>",
+    "<extra_id_18>",
+    "<extra_id_19>",
+    "<extra_id_20>",
+    "<extra_id_21>",
+    "<extra_id_22>",
+    "<extra_id_23>",
+    "<extra_id_24>",
+    "<extra_id_25>",
+    "<extra_id_26>",
+    "<extra_id_27>",
+    "<extra_id_28>",
+    "<extra_id_29>",
+    "<extra_id_30>",
+    "<extra_id_31>",
+    "<extra_id_32>",
+    "<extra_id_33>",
+    "<extra_id_34>",
+    "<extra_id_35>",
+    "<extra_id_36>",
+    "<extra_id_37>",
+    "<extra_id_38>",
+    "<extra_id_39>",
+    "<extra_id_40>",
+    "<extra_id_41>",
+    "<extra_id_42>",
+    "<extra_id_43>",
+    "<extra_id_44>",
+    "<extra_id_45>",
+    "<extra_id_46>",
+    "<extra_id_47>",
+    "<extra_id_48>",
+    "<extra_id_49>",
+    "<extra_id_50>",
+    "<extra_id_51>",
+    "<extra_id_52>",
+    "<extra_id_53>",
+    "<extra_id_54>",
+    "<extra_id_55>",
+    "<extra_id_56>",
+    "<extra_id_57>",
+    "<extra_id_58>",
+    "<extra_id_59>",
+    "<extra_id_60>",
+    "<extra_id_61>",
+    "<extra_id_62>",
+    "<extra_id_63>",
+    "<extra_id_64>",
+    "<extra_id_65>",
+    "<extra_id_66>",
+    "<extra_id_67>",
+    "<extra_id_68>",
+    "<extra_id_69>",
+    "<extra_id_70>",
+    "<extra_id_71>",
+    "<extra_id_72>",
+    "<extra_id_73>",
+    "<extra_id_74>",
+    "<extra_id_75>",
+    "<extra_id_76>",
+    "<extra_id_77>",
+    "<extra_id_78>",
+    "<extra_id_79>",
+    "<extra_id_80>",
+    "<extra_id_81>",
+    "<extra_id_82>",
+    "<extra_id_83>",
+    "<extra_id_84>",
+    "<extra_id_85>",
+    "<extra_id_86>",
+    "<extra_id_87>",
+    "<extra_id_88>",
+    "<extra_id_89>",
+    "<extra_id_90>",
+    "<extra_id_91>",
+    "<extra_id_92>",
+    "<extra_id_93>",
+    "<extra_id_94>",
+    "<extra_id_95>",
+    "<extra_id_96>",
+    "<extra_id_97>",
+    "<extra_id_98>",
+    "<extra_id_99>"
+  ],
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "</s>",
+  "extra_ids": 100,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "tokenizer_class": "T5Tokenizer",
+  "unk_token": "<unk>"
+}

trainer_state.json

@@ -0,0 +1,768 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 19.926991625509984,
+  "eval_steps": 500,
+  "global_step": 2900,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.0001,
+      "loss": 6.5987,
+      "step": 145
+    },
+    {
+      "epoch": 1.0,
+      "eval_bleu": 0.1374,
+      "eval_bp": 1.0,
+      "eval_counts_1": 3804,
+      "eval_counts_2": 134,
+      "eval_counts_3": 2,
+      "eval_counts_4": 0,
+      "eval_exact_match": 0.0,
+      "eval_f1": 0.0814,
+      "eval_gen_len": 16.2899,
+      "eval_loss": 5.069606304168701,
+      "eval_precisions_1": 16.6019,
+      "eval_precisions_2": 0.6471,
+      "eval_precisions_3": 0.0108,
+      "eval_precisions_4": 0.0031,
+      "eval_ref_len": 21250,
+      "eval_rouge1": 0.0783,
+      "eval_rouge2": 0.007,
+      "eval_rougeL": 0.0769,
+      "eval_rougeLsum": 0.0768,
+      "eval_runtime": 2008.1612,
+      "eval_samples_per_second": 1.098,
+      "eval_steps_per_second": 0.549,
+      "eval_sys_len": 22913,
+      "eval_totals_1": 22913,
+      "eval_totals_2": 20709,
+      "eval_totals_3": 18505,
+      "eval_totals_4": 16301,
+      "step": 145
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 0.0001,
+      "loss": 4.7443,
+      "step": 291
+    },
+    {
+      "epoch": 2.0,
+      "eval_bleu": 0.303,
+      "eval_bp": 0.7996,
+      "eval_counts_1": 4022,
+      "eval_counts_2": 188,
+      "eval_counts_3": 20,
+      "eval_counts_4": 0,
+      "eval_exact_match": 0.0,
+      "eval_f1": 0.1073,
+      "eval_gen_len": 12.9038,
+      "eval_loss": 4.227029323577881,
+      "eval_precisions_1": 23.1602,
+      "eval_precisions_2": 1.2399,
+      "eval_precisions_3": 0.1543,
+      "eval_precisions_4": 0.0046,
+      "eval_ref_len": 21250,
+      "eval_rouge1": 0.1028,
+      "eval_rouge2": 0.012,
+      "eval_rougeL": 0.0991,
+      "eval_rougeLsum": 0.099,
+      "eval_runtime": 2942.0368,
+      "eval_samples_per_second": 0.749,
+      "eval_steps_per_second": 0.375,
+      "eval_sys_len": 17366,
+      "eval_totals_1": 17366,
+      "eval_totals_2": 15162,
+      "eval_totals_3": 12958,
+      "eval_totals_4": 10754,
+      "step": 291
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 0.0001,
+      "loss": 4.1412,
+      "step": 436
+    },
+    {
+      "epoch": 3.0,
+      "eval_bleu": 0.4488,
+      "eval_bp": 0.7507,
+      "eval_counts_1": 3723,
+      "eval_counts_2": 187,
+      "eval_counts_3": 26,
+      "eval_counts_4": 2,
+      "eval_exact_match": 0.0,
+      "eval_f1": 0.0938,
+      "eval_gen_len": 12.4769,
+      "eval_loss": 3.7837560176849365,
+      "eval_precisions_1": 22.5431,
+      "eval_precisions_2": 1.3067,
+      "eval_precisions_3": 0.2148,
+      "eval_precisions_4": 0.0202,
+      "eval_ref_len": 21250,
+      "eval_rouge1": 0.0899,
+      "eval_rouge2": 0.0124,
+      "eval_rougeL": 0.0886,
+      "eval_rougeLsum": 0.0884,
+      "eval_runtime": 2963.118,
+      "eval_samples_per_second": 0.744,
+      "eval_steps_per_second": 0.372,
+      "eval_sys_len": 16515,
+      "eval_totals_1": 16515,
+      "eval_totals_2": 14311,
+      "eval_totals_3": 12107,
+      "eval_totals_4": 9903,
+      "step": 436
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 0.0001,
+      "loss": 3.6791,
+      "step": 582
+    },
+    {
+      "epoch": 4.0,
+      "eval_bleu": 1.6623,
+      "eval_bp": 1.0,
+      "eval_counts_1": 4576,
+      "eval_counts_2": 549,
+      "eval_counts_3": 134,
+      "eval_counts_4": 26,
+      "eval_exact_match": 0.0,
+      "eval_f1": 0.1323,
+      "eval_gen_len": 14.5676,
+      "eval_loss": 3.4246089458465576,
+      "eval_precisions_1": 20.9227,
+      "eval_precisions_2": 2.7915,
+      "eval_precisions_3": 0.7673,
+      "eval_precisions_4": 0.1704,
+      "eval_ref_len": 21250,
+      "eval_rouge1": 0.1259,
+      "eval_rouge2": 0.0296,
+      "eval_rougeL": 0.1204,
+      "eval_rougeLsum": 0.1201,
+      "eval_runtime": 3118.2455,
+      "eval_samples_per_second": 0.707,
+      "eval_steps_per_second": 0.353,
+      "eval_sys_len": 21871,
+      "eval_totals_1": 21871,
+      "eval_totals_2": 19667,
+      "eval_totals_3": 17463,
+      "eval_totals_4": 15259,
+      "step": 582
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 0.0001,
+      "loss": 3.3523,
+      "step": 727
+    },
+    {
+      "epoch": 5.0,
+      "eval_bleu": 2.4472,
+      "eval_bp": 0.9085,
+      "eval_counts_1": 4900,
+      "eval_counts_2": 796,
+      "eval_counts_3": 210,
+      "eval_counts_4": 41,
+      "eval_exact_match": 0.0005,
+      "eval_f1": 0.1585,
+      "eval_gen_len": 14.3943,
+      "eval_loss": 3.172255277633667,
+      "eval_precisions_1": 25.2721,
+      "eval_precisions_2": 4.6319,
+      "eval_precisions_3": 1.4018,
+      "eval_precisions_4": 0.3209,
+      "eval_ref_len": 21250,
+      "eval_rouge1": 0.1542,
+      "eval_rouge2": 0.0449,
+      "eval_rougeL": 0.1486,
+      "eval_rougeLsum": 0.1484,
+      "eval_runtime": 3087.9672,
+      "eval_samples_per_second": 0.714,
+      "eval_steps_per_second": 0.357,
+      "eval_sys_len": 19389,
+      "eval_totals_1": 19389,
+      "eval_totals_2": 17185,
+      "eval_totals_3": 14981,
+      "eval_totals_4": 12777,
+      "step": 727
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 0.0001,
+      "loss": 3.0161,
+      "step": 873
+    },
+    {
+      "epoch": 6.0,
+      "eval_bleu": 4.1987,
+      "eval_bp": 0.8907,
+      "eval_counts_1": 5633,
+      "eval_counts_2": 1182,
+      "eval_counts_3": 390,
+      "eval_counts_4": 111,
+      "eval_exact_match": 0.0045,
+      "eval_f1": 0.2074,
+      "eval_gen_len": 14.5789,
+      "eval_loss": 2.926840305328369,
+      "eval_precisions_1": 29.5773,
+      "eval_precisions_2": 7.0186,
+      "eval_precisions_3": 2.6645,
+      "eval_precisions_4": 0.8928,
+      "eval_ref_len": 21250,
+      "eval_rouge1": 0.204,
+      "eval_rouge2": 0.069,
+      "eval_rougeL": 0.196,
+      "eval_rougeLsum": 0.1961,
+      "eval_runtime": 3093.3528,
+      "eval_samples_per_second": 0.712,
+      "eval_steps_per_second": 0.356,
+      "eval_sys_len": 19045,
+      "eval_totals_1": 19045,
+      "eval_totals_2": 16841,
+      "eval_totals_3": 14637,
+      "eval_totals_4": 12433,
+      "step": 873
+    },
+    {
+      "epoch": 7.0,
+      "learning_rate": 0.0001,
+      "loss": 2.7639,
+      "step": 1018
+    },
+    {
+      "epoch": 7.0,
+      "eval_bleu": 5.3362,
+      "eval_bp": 0.8306,
+      "eval_counts_1": 6100,
+      "eval_counts_2": 1461,
+      "eval_counts_3": 499,
+      "eval_counts_4": 165,
+      "eval_exact_match": 0.0073,
+      "eval_f1": 0.2431,
+      "eval_gen_len": 13.8553,
+      "eval_loss": 2.760089635848999,
+      "eval_precisions_1": 34.0326,
+      "eval_precisions_2": 9.2939,
+      "eval_precisions_3": 3.6919,
+      "eval_precisions_4": 1.4586,
+      "eval_ref_len": 21250,
+      "eval_rouge1": 0.2409,
+      "eval_rouge2": 0.0885,
+      "eval_rougeL": 0.2332,
+      "eval_rougeLsum": 0.2331,
+      "eval_runtime": 2991.0063,
+      "eval_samples_per_second": 0.737,
+      "eval_steps_per_second": 0.368,
+      "eval_sys_len": 17924,
+      "eval_totals_1": 17924,
+      "eval_totals_2": 15720,
+      "eval_totals_3": 13516,
+      "eval_totals_4": 11312,
+      "step": 1018
+    },
+    {
+      "epoch": 8.0,
+      "learning_rate": 0.0001,
+      "loss": 2.5036,
+      "step": 1164
+    },
+    {
+      "epoch": 8.0,
+      "eval_bleu": 7.0633,
+      "eval_bp": 0.9483,
+      "eval_counts_1": 6765,
+      "eval_counts_2": 1845,
+      "eval_counts_3": 701,
+      "eval_counts_4": 273,
+      "eval_exact_match": 0.0059,
+      "eval_f1": 0.2689,
+      "eval_gen_len": 15.7232,
+      "eval_loss": 2.572913885116577,
+      "eval_precisions_1": 33.525,
+      "eval_precisions_2": 10.2643,
+      "eval_precisions_3": 4.4449,
+      "eval_precisions_4": 2.0122,
+      "eval_ref_len": 21250,
+      "eval_rouge1": 0.2682,
+      "eval_rouge2": 0.1079,
+      "eval_rougeL": 0.2589,
+      "eval_rougeLsum": 0.259,
+      "eval_runtime": 3343.9439,
+      "eval_samples_per_second": 0.659,
+      "eval_steps_per_second": 0.33,
+      "eval_sys_len": 20179,
+      "eval_totals_1": 20179,
+      "eval_totals_2": 17975,
+      "eval_totals_3": 15771,
+      "eval_totals_4": 13567,
+      "step": 1164
+    },
+    {
+      "epoch": 8.99,
+      "learning_rate": 0.0001,
+      "loss": 2.307,
+      "step": 1309
+    },
+    {
+      "epoch": 8.99,
+      "eval_bleu": 8.1681,
+      "eval_bp": 0.8911,
+      "eval_counts_1": 7018,
+      "eval_counts_2": 2047,
+      "eval_counts_3": 826,
+      "eval_counts_4": 348,
+      "eval_exact_match": 0.0095,
+      "eval_f1": 0.2907,
+      "eval_gen_len": 14.8076,
+      "eval_loss": 2.4636850357055664,
+      "eval_precisions_1": 36.8322,
+      "eval_precisions_2": 12.1484,
+      "eval_precisions_3": 5.6398,
+      "eval_precisions_4": 2.797,
+      "eval_ref_len": 21250,
+      "eval_rouge1": 0.2907,
+      "eval_rouge2": 0.1218,
+      "eval_rougeL": 0.2799,
+      "eval_rougeLsum": 0.2798,
+      "eval_runtime": 3082.8011,
+      "eval_samples_per_second": 0.715,
+      "eval_steps_per_second": 0.357,
+      "eval_sys_len": 19054,
+      "eval_totals_1": 19054,
+      "eval_totals_2": 16850,
+      "eval_totals_3": 14646,
+      "eval_totals_4": 12442,
+      "step": 1309
+    },
+    {
+      "epoch": 10.0,
+      "learning_rate": 0.0001,
+      "loss": 2.1012,
+      "step": 1455
+    },
+    {
+      "epoch": 10.0,
+      "eval_bleu": 8.6921,
+      "eval_bp": 0.8604,
+      "eval_counts_1": 7147,
+      "eval_counts_2": 2127,
+      "eval_counts_3": 883,
+      "eval_counts_4": 389,
+      "eval_exact_match": 0.0118,
+      "eval_f1": 0.3008,
+      "eval_gen_len": 14.2736,
+      "eval_loss": 2.361370325088501,
+      "eval_precisions_1": 38.6889,
+      "eval_precisions_2": 13.0739,
+      "eval_precisions_3": 6.278,
+      "eval_precisions_4": 3.2797,
+      "eval_ref_len": 21250,
+      "eval_rouge1": 0.3003,
+      "eval_rouge2": 0.1275,
+      "eval_rougeL": 0.289,
+      "eval_rougeLsum": 0.2888,
+      "eval_runtime": 2980.6044,
+      "eval_samples_per_second": 0.739,
+      "eval_steps_per_second": 0.37,
+      "eval_sys_len": 18473,
+      "eval_totals_1": 18473,
+      "eval_totals_2": 16269,
+      "eval_totals_3": 14065,
+      "eval_totals_4": 11861,
+      "step": 1455
+    },
+    {
+      "epoch": 10.99,
+      "learning_rate": 0.0001,
+      "loss": 1.9538,
+      "step": 1600
+    },
+    {
+      "epoch": 10.99,
+      "eval_bleu": 9.67,
+      "eval_bp": 0.8632,
+      "eval_counts_1": 7481,
+      "eval_counts_2": 2339,
+      "eval_counts_3": 997,
+      "eval_counts_4": 459,
+      "eval_exact_match": 0.0127,
+      "eval_f1": 0.3167,
+      "eval_gen_len": 14.3757,
+      "eval_loss": 2.297987461090088,
+      "eval_precisions_1": 40.3854,
+      "eval_precisions_2": 14.3321,
+      "eval_precisions_3": 7.0629,
+      "eval_precisions_4": 3.8533,
+      "eval_ref_len": 21250,
+      "eval_rouge1": 0.3192,
+      "eval_rouge2": 0.1423,
+      "eval_rougeL": 0.3064,
+      "eval_rougeLsum": 0.3068,
+      "eval_runtime": 1745.8738,
+      "eval_samples_per_second": 1.262,
+      "eval_steps_per_second": 0.631,
+      "eval_sys_len": 18524,
+      "eval_totals_1": 18524,
+      "eval_totals_2": 16320,
+      "eval_totals_3": 14116,
+      "eval_totals_4": 11912,
+      "step": 1600
+    },
+    {
+      "epoch": 12.0,
+      "learning_rate": 0.0001,
+      "loss": 1.7909,
+      "step": 1746
+    },
+    {
+      "epoch": 12.0,
+      "eval_bleu": 10.724,
+      "eval_bp": 0.8804,
+      "eval_counts_1": 7675,
+      "eval_counts_2": 2546,
+      "eval_counts_3": 1144,
+      "eval_counts_4": 546,
+      "eval_exact_match": 0.015,
+      "eval_f1": 0.3279,
+      "eval_gen_len": 14.583,
+      "eval_loss": 2.2389414310455322,
+      "eval_precisions_1": 40.7183,
+      "eval_precisions_2": 15.2959,
+      "eval_precisions_3": 7.9219,
+      "eval_precisions_4": 4.4619,
+      "eval_ref_len": 21250,
+      "eval_rouge1": 0.3299,
+      "eval_rouge2": 0.1528,
+      "eval_rougeL": 0.3174,
+      "eval_rougeLsum": 0.3175,
+      "eval_runtime": 1768.3367,
+      "eval_samples_per_second": 1.246,
+      "eval_steps_per_second": 0.623,
+      "eval_sys_len": 18849,
+      "eval_totals_1": 18849,
+      "eval_totals_2": 16645,
+      "eval_totals_3": 14441,
+      "eval_totals_4": 12237,
+      "step": 1746
+    },
+    {
+      "epoch": 12.99,
+      "learning_rate": 0.0001,
+      "loss": 1.6691,
+      "step": 1891
+    },
+    {
+      "epoch": 12.99,
+      "eval_bleu": 11.1241,
+      "eval_bp": 0.8695,
+      "eval_counts_1": 7858,
+      "eval_counts_2": 2635,
+      "eval_counts_3": 1179,
+      "eval_counts_4": 576,
+      "eval_exact_match": 0.0163,
+      "eval_f1": 0.3395,
+      "eval_gen_len": 14.3848,
+      "eval_loss": 2.181286096572876,
+      "eval_precisions_1": 42.1499,
+      "eval_precisions_2": 16.029,
+      "eval_precisions_3": 8.2824,
+      "eval_precisions_4": 4.7876,
+      "eval_ref_len": 21250,
+      "eval_rouge1": 0.344,
+      "eval_rouge2": 0.1626,
+      "eval_rougeL": 0.33,
+      "eval_rougeLsum": 0.33,
+      "eval_runtime": 1475.7204,
+      "eval_samples_per_second": 1.494,
+      "eval_steps_per_second": 0.747,
+      "eval_sys_len": 18643,
+      "eval_totals_1": 18643,
+      "eval_totals_2": 16439,
+      "eval_totals_3": 14235,
+      "eval_totals_4": 12031,
+      "step": 1891
+    },
+    {
+      "epoch": 14.0,
+      "learning_rate": 0.0001,
+      "loss": 1.5361,
+      "step": 2037
+    },
+    {
+      "epoch": 14.0,
+      "eval_bleu": 11.5803,
+      "eval_bp": 0.8754,
+      "eval_counts_1": 8016,
+      "eval_counts_2": 2729,
+      "eval_counts_3": 1249,
+      "eval_counts_4": 606,
+      "eval_exact_match": 0.0163,
+      "eval_f1": 0.3462,
+      "eval_gen_len": 14.564,
+      "eval_loss": 2.15460205078125,
+      "eval_precisions_1": 42.7429,
+      "eval_precisions_2": 16.4894,
+      "eval_precisions_3": 8.7063,
+      "eval_precisions_4": 4.9909,
+      "eval_ref_len": 21250,
+      "eval_rouge1": 0.3494,
+      "eval_rouge2": 0.1664,
+      "eval_rougeL": 0.3349,
+      "eval_rougeLsum": 0.3351,
+      "eval_runtime": 2521.9472,
+      "eval_samples_per_second": 0.874,
+      "eval_steps_per_second": 0.437,
+      "eval_sys_len": 18754,
+      "eval_totals_1": 18754,
+      "eval_totals_2": 16550,
+      "eval_totals_3": 14346,
+      "eval_totals_4": 12142,
+      "step": 2037
+    },
+    {
+      "epoch": 14.99,
+      "learning_rate": 0.0001,
+      "loss": 1.4365,
+      "step": 2182
+    },
+    {
+      "epoch": 14.99,
+      "eval_bleu": 12.1055,
+      "eval_bp": 0.856,
+      "eval_counts_1": 8112,
+      "eval_counts_2": 2839,
+      "eval_counts_3": 1316,
+      "eval_counts_4": 647,
+      "eval_exact_match": 0.02,
+      "eval_f1": 0.3538,
+      "eval_gen_len": 14.1656,
+      "eval_loss": 2.1357789039611816,
+      "eval_precisions_1": 44.1109,
+      "eval_precisions_2": 17.5398,
+      "eval_precisions_3": 9.4121,
+      "eval_precisions_4": 5.4933,
+      "eval_ref_len": 21250,
+      "eval_rouge1": 0.3581,
+      "eval_rouge2": 0.1761,
+      "eval_rougeL": 0.3448,
+      "eval_rougeLsum": 0.3448,
+      "eval_runtime": 2133.8974,
+      "eval_samples_per_second": 1.033,
+      "eval_steps_per_second": 0.516,
+      "eval_sys_len": 18390,
+      "eval_totals_1": 18390,
+      "eval_totals_2": 16186,
+      "eval_totals_3": 13982,
+      "eval_totals_4": 11778,
+      "step": 2182
+    },
+    {
+      "epoch": 16.0,
+      "learning_rate": 0.0001,
+      "loss": 1.3263,
+      "step": 2328
+    },
+    {
+      "epoch": 16.0,
+      "eval_bleu": 12.9765,
+      "eval_bp": 0.8827,
+      "eval_counts_1": 8381,
+      "eval_counts_2": 2990,
+      "eval_counts_3": 1430,
+      "eval_counts_4": 731,
+      "eval_exact_match": 0.0209,
+      "eval_f1": 0.363,
+      "eval_gen_len": 14.5445,
+      "eval_loss": 2.1189985275268555,
+      "eval_precisions_1": 44.3627,
+      "eval_precisions_2": 17.9171,
+      "eval_precisions_3": 9.873,
+      "eval_precisions_4": 5.9528,
+      "eval_ref_len": 21250,
+      "eval_rouge1": 0.3681,
+      "eval_rouge2": 0.1831,
+      "eval_rougeL": 0.3532,
+      "eval_rougeLsum": 0.3534,
+      "eval_runtime": 1849.5796,
+      "eval_samples_per_second": 1.192,
+      "eval_steps_per_second": 0.596,
+      "eval_sys_len": 18892,
+      "eval_totals_1": 18892,
+      "eval_totals_2": 16688,
+      "eval_totals_3": 14484,
+      "eval_totals_4": 12280,
+      "step": 2328
+    },
+    {
+      "epoch": 17.0,
+      "learning_rate": 0.0001,
+      "loss": 1.2329,
+      "step": 2474
+    },
+    {
+      "epoch": 17.0,
+      "eval_bleu": 13.5903,
+      "eval_bp": 0.8678,
+      "eval_counts_1": 8449,
+      "eval_counts_2": 3101,
+      "eval_counts_3": 1520,
+      "eval_counts_4": 786,
+      "eval_exact_match": 0.0227,
+      "eval_f1": 0.3692,
+      "eval_gen_len": 14.1779,
+      "eval_loss": 2.1201868057250977,
+      "eval_precisions_1": 45.3954,
+      "eval_precisions_2": 18.8993,
+      "eval_precisions_3": 10.7012,
+      "eval_precisions_4": 6.55,
+      "eval_ref_len": 21250,
+      "eval_rouge1": 0.3743,
+      "eval_rouge2": 0.1901,
+      "eval_rougeL": 0.3603,
+      "eval_rougeLsum": 0.3603,
+      "eval_runtime": 1363.814,
+      "eval_samples_per_second": 1.616,
+      "eval_steps_per_second": 0.808,
+      "eval_sys_len": 18612,
+      "eval_totals_1": 18612,
+      "eval_totals_2": 16408,
+      "eval_totals_3": 14204,
+      "eval_totals_4": 12000,
+      "step": 2474
+    },
+    {
+      "epoch": 18.0,
+      "learning_rate": 0.0001,
+      "loss": 1.1557,
+      "step": 2619
+    },
+    {
+      "epoch": 18.0,
+      "eval_bleu": 13.8388,
+      "eval_bp": 0.8325,
+      "eval_counts_1": 8406,
+      "eval_counts_2": 3154,
+      "eval_counts_3": 1558,
+      "eval_counts_4": 804,
+      "eval_exact_match": 0.0277,
+      "eval_f1": 0.371,
+      "eval_gen_len": 13.677,
+      "eval_loss": 2.1282455921173096,
+      "eval_precisions_1": 46.8092,
+      "eval_precisions_2": 20.0203,
+      "eval_precisions_3": 11.4982,
+      "eval_precisions_4": 7.0862,
+      "eval_ref_len": 21250,
+      "eval_rouge1": 0.3761,
+      "eval_rouge2": 0.194,
+      "eval_rougeL": 0.3633,
+      "eval_rougeLsum": 0.3636,
+      "eval_runtime": 1323.8829,
+      "eval_samples_per_second": 1.665,
+      "eval_steps_per_second": 0.832,
+      "eval_sys_len": 17958,
+      "eval_totals_1": 17958,
+      "eval_totals_2": 15754,
+      "eval_totals_3": 13550,
+      "eval_totals_4": 11346,
+      "step": 2619
+    },
+    {
+      "epoch": 19.0,
+      "learning_rate": 0.0001,
+      "loss": 1.0658,
+      "step": 2765
+    },
+    {
+      "epoch": 19.0,
+      "eval_bleu": 14.2084,
+      "eval_bp": 0.886,
+      "eval_counts_1": 8614,
+      "eval_counts_2": 3241,
+      "eval_counts_3": 1610,
+      "eval_counts_4": 839,
+      "eval_exact_match": 0.0272,
+      "eval_f1": 0.3749,
+      "eval_gen_len": 14.3816,
+      "eval_loss": 2.123244524002075,
+      "eval_precisions_1": 45.4445,
+      "eval_precisions_2": 19.3481,
+      "eval_precisions_3": 11.0676,
+      "eval_precisions_4": 6.7974,
+      "eval_ref_len": 21250,
+      "eval_rouge1": 0.3803,
+      "eval_rouge2": 0.196,
+      "eval_rougeL": 0.3654,
+      "eval_rougeLsum": 0.3656,
+      "eval_runtime": 1378.8855,
+      "eval_samples_per_second": 1.598,
+      "eval_steps_per_second": 0.799,
+      "eval_sys_len": 18955,
+      "eval_totals_1": 18955,
+      "eval_totals_2": 16751,
+      "eval_totals_3": 14547,
+      "eval_totals_4": 12343,
+      "step": 2765
+    },
+    {
+      "epoch": 19.93,
+      "learning_rate": 0.0001,
+      "loss": 0.9944,
+      "step": 2900
+    },
+    {
+      "epoch": 19.93,
+      "eval_bleu": 14.3883,
+      "eval_bp": 0.8806,
+      "eval_counts_1": 8658,
+      "eval_counts_2": 3273,
+      "eval_counts_3": 1625,
+      "eval_counts_4": 859,
+      "eval_exact_match": 0.0268,
+      "eval_f1": 0.3775,
+      "eval_gen_len": 14.2881,
+      "eval_loss": 2.1203458309173584,
+      "eval_precisions_1": 45.9237,
+      "eval_precisions_2": 19.6588,
+      "eval_precisions_3": 11.2496,
+      "eval_precisions_4": 7.0174,
+      "eval_ref_len": 21250,
+      "eval_rouge1": 0.3833,
+      "eval_rouge2": 0.1977,
+      "eval_rougeL": 0.369,
+      "eval_rougeLsum": 0.3691,
+      "eval_runtime": 1364.695,
+      "eval_samples_per_second": 1.615,
+      "eval_steps_per_second": 0.808,
+      "eval_sys_len": 18853,
+      "eval_totals_1": 18853,
+      "eval_totals_2": 16649,
+      "eval_totals_3": 14445,
+      "eval_totals_4": 12241,
+      "step": 2900
+    },
+    {
+      "epoch": 19.93,
+      "step": 2900,
+      "total_flos": 8.55557888016384e+17,
+      "train_loss": 2.472949571280644,
+      "train_runtime": 103540.1577,
+      "train_samples_per_second": 1.799,
+      "train_steps_per_second": 0.028
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2900,
+  "num_train_epochs": 20,
+  "save_steps": 500,
+  "total_flos": 8.55557888016384e+17,
+  "trial_name": null,
+  "trial_params": null
+}