Model save
Browse files- README.md +18 -75
- all_results.json +14 -14
- config.json +6 -6
- eval_results.json +10 -10
- model.safetensors +2 -2
- special_tokens_map.json +3 -21
- tokenizer.json +1 -6
- tokenizer_config.json +1 -1
- train_results.json +5 -5
- trainer_state.json +63 -666
- training_args.bin +1 -1
README.md
CHANGED
|
@@ -1,25 +1,13 @@
|
|
| 1 |
---
|
| 2 |
license: apache-2.0
|
| 3 |
-
base_model: google-t5/t5-
|
| 4 |
tags:
|
| 5 |
- generated_from_trainer
|
| 6 |
-
datasets:
|
| 7 |
-
- fedora-copr/pep-sum
|
| 8 |
metrics:
|
| 9 |
- rouge
|
| 10 |
model-index:
|
| 11 |
- name: pep_summarization
|
| 12 |
-
results:
|
| 13 |
-
- task:
|
| 14 |
-
name: Summarization
|
| 15 |
-
type: summarization
|
| 16 |
-
dataset:
|
| 17 |
-
name: fedora-copr/pep-sum
|
| 18 |
-
type: fedora-copr/pep-sum
|
| 19 |
-
metrics:
|
| 20 |
-
- name: Rouge1
|
| 21 |
-
type: rouge
|
| 22 |
-
value: 87.1522
|
| 23 |
---
|
| 24 |
|
| 25 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
@@ -27,14 +15,14 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 27 |
|
| 28 |
# pep_summarization
|
| 29 |
|
| 30 |
-
This model is a fine-tuned version of [google-t5/t5-
|
| 31 |
It achieves the following results on the evaluation set:
|
| 32 |
-
- Loss: 0.
|
| 33 |
-
- Rouge1:
|
| 34 |
-
- Rouge2:
|
| 35 |
-
- Rougel:
|
| 36 |
-
- Rougelsum:
|
| 37 |
-
- Gen Len: 68.
|
| 38 |
|
| 39 |
## Model description
|
| 40 |
|
|
@@ -53,68 +41,23 @@ More information needed
|
|
| 53 |
### Training hyperparameters
|
| 54 |
|
| 55 |
The following hyperparameters were used during training:
|
| 56 |
-
- learning_rate:
|
| 57 |
-
- train_batch_size:
|
| 58 |
-
- eval_batch_size:
|
| 59 |
- seed: 42
|
| 60 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 61 |
- lr_scheduler_type: linear
|
| 62 |
-
- num_epochs:
|
| 63 |
|
| 64 |
### Training results
|
| 65 |
|
| 66 |
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|
| 67 |
|:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|:-------:|:---------:|:-------:|
|
| 68 |
-
| No log | 1.0 |
|
| 69 |
-
| No log | 2.0 |
|
| 70 |
-
| No log | 3.0 |
|
| 71 |
-
| No log | 4.0 |
|
| 72 |
-
| No log | 5.0 |
|
| 73 |
-
| No log | 6.0 | 210 | 0.1346 | 77.1153 | 75.713 | 77.0396 | 76.815 | 63.0 |
|
| 74 |
-
| No log | 7.0 | 245 | 0.1213 | 80.2369 | 79.6485 | 80.4178 | 80.1986 | 65.5507 |
|
| 75 |
-
| No log | 8.0 | 280 | 0.1057 | 82.3014 | 81.6093 | 82.3372 | 82.1797 | 65.2319 |
|
| 76 |
-
| No log | 9.0 | 315 | 0.0937 | 83.5682 | 82.9738 | 83.6388 | 83.5486 | 66.0870 |
|
| 77 |
-
| No log | 10.0 | 350 | 0.0843 | 83.5735 | 82.9779 | 83.6425 | 83.5533 | 66.0870 |
|
| 78 |
-
| No log | 11.0 | 385 | 0.0763 | 83.5502 | 83.0151 | 83.7004 | 83.6188 | 67.6957 |
|
| 79 |
-
| No log | 12.0 | 420 | 0.0688 | 83.8612 | 83.4112 | 84.0555 | 83.8541 | 65.6087 |
|
| 80 |
-
| No log | 13.0 | 455 | 0.0653 | 83.2559 | 82.7398 | 83.437 | 83.3363 | 68.4928 |
|
| 81 |
-
| No log | 14.0 | 490 | 0.0613 | 84.2407 | 83.738 | 84.3104 | 84.3012 | 67.7681 |
|
| 82 |
-
| 0.1963 | 15.0 | 525 | 0.0584 | 83.8361 | 83.3141 | 83.8976 | 83.8751 | 68.5507 |
|
| 83 |
-
| 0.1963 | 16.0 | 560 | 0.0563 | 83.5952 | 83.1416 | 83.5644 | 83.5389 | 71.4928 |
|
| 84 |
-
| 0.1963 | 17.0 | 595 | 0.0539 | 84.6048 | 84.1681 | 84.7325 | 84.567 | 69.4783 |
|
| 85 |
-
| 0.1963 | 18.0 | 630 | 0.0520 | 84.9204 | 84.4493 | 85.0357 | 84.9063 | 68.7246 |
|
| 86 |
-
| 0.1963 | 19.0 | 665 | 0.0514 | 84.3924 | 83.9735 | 84.4126 | 84.3779 | 69.7971 |
|
| 87 |
-
| 0.1963 | 20.0 | 700 | 0.0504 | 86.1503 | 85.6151 | 86.2393 | 86.0495 | 67.2319 |
|
| 88 |
-
| 0.1963 | 21.0 | 735 | 0.0496 | 86.4875 | 85.9614 | 86.5042 | 86.3616 | 66.5217 |
|
| 89 |
-
| 0.1963 | 22.0 | 770 | 0.0496 | 85.6339 | 85.1604 | 85.6862 | 85.5112 | 67.9420 |
|
| 90 |
-
| 0.1963 | 23.0 | 805 | 0.0490 | 87.0368 | 86.5415 | 87.1099 | 86.9317 | 65.5217 |
|
| 91 |
-
| 0.1963 | 24.0 | 840 | 0.0493 | 85.6323 | 85.1577 | 85.6823 | 85.5102 | 67.9420 |
|
| 92 |
-
| 0.1963 | 25.0 | 875 | 0.0493 | 86.3078 | 85.7832 | 86.3026 | 86.1442 | 69.0435 |
|
| 93 |
-
| 0.1963 | 26.0 | 910 | 0.0490 | 85.877 | 85.3534 | 85.9035 | 85.8208 | 70.2899 |
|
| 94 |
-
| 0.1963 | 27.0 | 945 | 0.0478 | 86.6353 | 86.054 | 86.5856 | 86.5515 | 69.2464 |
|
| 95 |
-
| 0.1963 | 28.0 | 980 | 0.0478 | 87.0975 | 86.5716 | 87.1452 | 87.0713 | 68.5652 |
|
| 96 |
-
| 0.0499 | 29.0 | 1015 | 0.0468 | 87.9989 | 87.509 | 88.0597 | 87.9458 | 67.0 |
|
| 97 |
-
| 0.0499 | 30.0 | 1050 | 0.0468 | 86.6642 | 86.1007 | 86.6429 | 86.582 | 69.1304 |
|
| 98 |
-
| 0.0499 | 31.0 | 1085 | 0.0467 | 86.3475 | 85.7566 | 86.257 | 86.2544 | 69.3043 |
|
| 99 |
-
| 0.0499 | 32.0 | 1120 | 0.0463 | 86.6794 | 86.1044 | 86.6438 | 86.5856 | 69.1449 |
|
| 100 |
-
| 0.0499 | 33.0 | 1155 | 0.0462 | 86.6794 | 86.1044 | 86.6438 | 86.5856 | 69.1449 |
|
| 101 |
-
| 0.0499 | 34.0 | 1190 | 0.0461 | 87.1151 | 86.605 | 87.1857 | 87.1151 | 68.4638 |
|
| 102 |
-
| 0.0499 | 35.0 | 1225 | 0.0459 | 88.0068 | 87.5135 | 88.0611 | 87.9535 | 67.0145 |
|
| 103 |
-
| 0.0499 | 36.0 | 1260 | 0.0459 | 87.6823 | 87.1982 | 87.7207 | 87.6541 | 67.5797 |
|
| 104 |
-
| 0.0499 | 37.0 | 1295 | 0.0461 | 86.6794 | 86.1044 | 86.6438 | 86.5856 | 69.1449 |
|
| 105 |
-
| 0.0499 | 38.0 | 1330 | 0.0460 | 86.6794 | 86.1044 | 86.6438 | 86.5856 | 69.1449 |
|
| 106 |
-
| 0.0499 | 39.0 | 1365 | 0.0458 | 86.701 | 86.1532 | 86.6831 | 86.6226 | 69.0435 |
|
| 107 |
-
| 0.0499 | 40.0 | 1400 | 0.0458 | 86.701 | 86.1532 | 86.6831 | 86.6226 | 69.0435 |
|
| 108 |
-
| 0.0499 | 41.0 | 1435 | 0.0457 | 87.6998 | 87.2471 | 87.7695 | 87.6934 | 67.4783 |
|
| 109 |
-
| 0.0499 | 42.0 | 1470 | 0.0460 | 86.6794 | 86.1044 | 86.6438 | 86.5856 | 69.1449 |
|
| 110 |
-
| 0.0362 | 43.0 | 1505 | 0.0460 | 87.5977 | 87.1424 | 87.6777 | 87.5976 | 67.6522 |
|
| 111 |
-
| 0.0362 | 44.0 | 1540 | 0.0458 | 87.571 | 87.1237 | 87.6515 | 87.5747 | 67.7681 |
|
| 112 |
-
| 0.0362 | 45.0 | 1575 | 0.0457 | 87.9476 | 87.4526 | 88.0306 | 87.9122 | 67.1014 |
|
| 113 |
-
| 0.0362 | 46.0 | 1610 | 0.0458 | 87.6074 | 87.1494 | 87.6861 | 87.6103 | 67.6667 |
|
| 114 |
-
| 0.0362 | 47.0 | 1645 | 0.0458 | 87.6074 | 87.1494 | 87.6861 | 87.6103 | 67.6667 |
|
| 115 |
-
| 0.0362 | 48.0 | 1680 | 0.0458 | 87.6074 | 87.1494 | 87.6861 | 87.6103 | 67.6667 |
|
| 116 |
-
| 0.0362 | 49.0 | 1715 | 0.0459 | 87.1522 | 86.6031 | 87.1206 | 87.0701 | 68.3478 |
|
| 117 |
-
| 0.0362 | 50.0 | 1750 | 0.0459 | 87.1522 | 86.6031 | 87.1206 | 87.0701 | 68.3478 |
|
| 118 |
|
| 119 |
|
| 120 |
### Framework versions
|
|
|
|
| 1 |
---
|
| 2 |
license: apache-2.0
|
| 3 |
+
base_model: google-t5/t5-base
|
| 4 |
tags:
|
| 5 |
- generated_from_trainer
|
|
|
|
|
|
|
| 6 |
metrics:
|
| 7 |
- rouge
|
| 8 |
model-index:
|
| 9 |
- name: pep_summarization
|
| 10 |
+
results: []
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 11 |
---
|
| 12 |
|
| 13 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
|
| 15 |
|
| 16 |
# pep_summarization
|
| 17 |
|
| 18 |
+
This model is a fine-tuned version of [google-t5/t5-base](https://huggingface.co/google-t5/t5-base) on an unknown dataset.
|
| 19 |
It achieves the following results on the evaluation set:
|
| 20 |
+
- Loss: 0.9288
|
| 21 |
+
- Rouge1: 39.7591
|
| 22 |
+
- Rouge2: 24.1983
|
| 23 |
+
- Rougel: 32.2869
|
| 24 |
+
- Rougelsum: 36.1493
|
| 25 |
+
- Gen Len: 68.0435
|
| 26 |
|
| 27 |
## Model description
|
| 28 |
|
|
|
|
| 41 |
### Training hyperparameters
|
| 42 |
|
| 43 |
The following hyperparameters were used during training:
|
| 44 |
+
- learning_rate: 1e-09
|
| 45 |
+
- train_batch_size: 4
|
| 46 |
+
- eval_batch_size: 4
|
| 47 |
- seed: 42
|
| 48 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 49 |
- lr_scheduler_type: linear
|
| 50 |
+
- num_epochs: 5.0
|
| 51 |
|
| 52 |
### Training results
|
| 53 |
|
| 54 |
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|
| 55 |
|:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|:-------:|:---------:|:-------:|
|
| 56 |
+
| No log | 1.0 | 69 | 0.9289 | 39.7591 | 24.1983 | 32.2869 | 36.1493 | 68.0435 |
|
| 57 |
+
| No log | 2.0 | 138 | 0.9289 | 39.7591 | 24.1983 | 32.2869 | 36.1493 | 68.0435 |
|
| 58 |
+
| No log | 3.0 | 207 | 0.9288 | 39.7591 | 24.1983 | 32.2869 | 36.1493 | 68.0435 |
|
| 59 |
+
| No log | 4.0 | 276 | 0.9288 | 39.7591 | 24.1983 | 32.2869 | 36.1493 | 68.0435 |
|
| 60 |
+
| No log | 5.0 | 345 | 0.9288 | 39.7591 | 24.1983 | 32.2869 | 36.1493 | 68.0435 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 61 |
|
| 62 |
|
| 63 |
### Framework versions
|
all_results.json
CHANGED
|
@@ -1,18 +1,18 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"eval_gen_len":
|
| 4 |
-
"eval_loss": 0.
|
| 5 |
-
"eval_rouge1":
|
| 6 |
-
"eval_rouge2":
|
| 7 |
-
"eval_rougeL":
|
| 8 |
-
"eval_rougeLsum":
|
| 9 |
-
"eval_runtime":
|
| 10 |
"eval_samples": 69,
|
| 11 |
-
"eval_samples_per_second":
|
| 12 |
-
"eval_steps_per_second":
|
| 13 |
-
"train_loss": 0.
|
| 14 |
-
"train_runtime":
|
| 15 |
"train_samples": 276,
|
| 16 |
-
"train_samples_per_second":
|
| 17 |
-
"train_steps_per_second":
|
| 18 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 5.0,
|
| 3 |
+
"eval_gen_len": 62.05797101449275,
|
| 4 |
+
"eval_loss": 0.0359114333987236,
|
| 5 |
+
"eval_rouge1": 84.8601,
|
| 6 |
+
"eval_rouge2": 84.2185,
|
| 7 |
+
"eval_rougeL": 84.7842,
|
| 8 |
+
"eval_rougeLsum": 84.8657,
|
| 9 |
+
"eval_runtime": 9.4102,
|
| 10 |
"eval_samples": 69,
|
| 11 |
+
"eval_samples_per_second": 7.332,
|
| 12 |
+
"eval_steps_per_second": 1.913,
|
| 13 |
+
"train_loss": 0.16054312664529552,
|
| 14 |
+
"train_runtime": 120.7301,
|
| 15 |
"train_samples": 276,
|
| 16 |
+
"train_samples_per_second": 11.43,
|
| 17 |
+
"train_steps_per_second": 2.858
|
| 18 |
}
|
config.json
CHANGED
|
@@ -1,12 +1,12 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "google-t5/t5-
|
| 3 |
"architectures": [
|
| 4 |
"T5ForConditionalGeneration"
|
| 5 |
],
|
| 6 |
"classifier_dropout": 0.0,
|
| 7 |
-
"d_ff":
|
| 8 |
"d_kv": 64,
|
| 9 |
-
"d_model":
|
| 10 |
"decoder_start_token_id": 0,
|
| 11 |
"dense_act_fn": "relu",
|
| 12 |
"dropout_rate": 0.1,
|
|
@@ -18,9 +18,9 @@
|
|
| 18 |
"layer_norm_epsilon": 1e-06,
|
| 19 |
"model_type": "t5",
|
| 20 |
"n_positions": 512,
|
| 21 |
-
"num_decoder_layers":
|
| 22 |
-
"num_heads":
|
| 23 |
-
"num_layers":
|
| 24 |
"output_past": true,
|
| 25 |
"pad_token_id": 0,
|
| 26 |
"relative_attention_max_distance": 128,
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "google-t5/t5-base",
|
| 3 |
"architectures": [
|
| 4 |
"T5ForConditionalGeneration"
|
| 5 |
],
|
| 6 |
"classifier_dropout": 0.0,
|
| 7 |
+
"d_ff": 3072,
|
| 8 |
"d_kv": 64,
|
| 9 |
+
"d_model": 768,
|
| 10 |
"decoder_start_token_id": 0,
|
| 11 |
"dense_act_fn": "relu",
|
| 12 |
"dropout_rate": 0.1,
|
|
|
|
| 18 |
"layer_norm_epsilon": 1e-06,
|
| 19 |
"model_type": "t5",
|
| 20 |
"n_positions": 512,
|
| 21 |
+
"num_decoder_layers": 12,
|
| 22 |
+
"num_heads": 12,
|
| 23 |
+
"num_layers": 12,
|
| 24 |
"output_past": true,
|
| 25 |
"pad_token_id": 0,
|
| 26 |
"relative_attention_max_distance": 128,
|
eval_results.json
CHANGED
|
@@ -1,13 +1,13 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"eval_gen_len":
|
| 4 |
-
"eval_loss": 0.
|
| 5 |
-
"eval_rouge1":
|
| 6 |
-
"eval_rouge2":
|
| 7 |
-
"eval_rougeL":
|
| 8 |
-
"eval_rougeLsum":
|
| 9 |
-
"eval_runtime":
|
| 10 |
"eval_samples": 69,
|
| 11 |
-
"eval_samples_per_second":
|
| 12 |
-
"eval_steps_per_second":
|
| 13 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 5.0,
|
| 3 |
+
"eval_gen_len": 62.05797101449275,
|
| 4 |
+
"eval_loss": 0.0359114333987236,
|
| 5 |
+
"eval_rouge1": 84.8601,
|
| 6 |
+
"eval_rouge2": 84.2185,
|
| 7 |
+
"eval_rougeL": 84.7842,
|
| 8 |
+
"eval_rougeLsum": 84.8657,
|
| 9 |
+
"eval_runtime": 9.4102,
|
| 10 |
"eval_samples": 69,
|
| 11 |
+
"eval_samples_per_second": 7.332,
|
| 12 |
+
"eval_steps_per_second": 1.913
|
| 13 |
}
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4e246720b637d1f8b21602feb21506054bfa943035657a6a0a489f6ecff230fa
|
| 3 |
+
size 891644712
|
special_tokens_map.json
CHANGED
|
@@ -101,25 +101,7 @@
|
|
| 101 |
"<extra_id_98>",
|
| 102 |
"<extra_id_99>"
|
| 103 |
],
|
| 104 |
-
"eos_token":
|
| 105 |
-
|
| 106 |
-
|
| 107 |
-
"normalized": false,
|
| 108 |
-
"rstrip": false,
|
| 109 |
-
"single_word": false
|
| 110 |
-
},
|
| 111 |
-
"pad_token": {
|
| 112 |
-
"content": "<pad>",
|
| 113 |
-
"lstrip": false,
|
| 114 |
-
"normalized": false,
|
| 115 |
-
"rstrip": false,
|
| 116 |
-
"single_word": false
|
| 117 |
-
},
|
| 118 |
-
"unk_token": {
|
| 119 |
-
"content": "<unk>",
|
| 120 |
-
"lstrip": false,
|
| 121 |
-
"normalized": false,
|
| 122 |
-
"rstrip": false,
|
| 123 |
-
"single_word": false
|
| 124 |
-
}
|
| 125 |
}
|
|
|
|
| 101 |
"<extra_id_98>",
|
| 102 |
"<extra_id_99>"
|
| 103 |
],
|
| 104 |
+
"eos_token": "</s>",
|
| 105 |
+
"pad_token": "<pad>",
|
| 106 |
+
"unk_token": "<unk>"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 107 |
}
|
tokenizer.json
CHANGED
|
@@ -1,11 +1,6 @@
|
|
| 1 |
{
|
| 2 |
"version": "1.0",
|
| 3 |
-
"truncation":
|
| 4 |
-
"direction": "Right",
|
| 5 |
-
"max_length": 128,
|
| 6 |
-
"strategy": "LongestFirst",
|
| 7 |
-
"stride": 0
|
| 8 |
-
},
|
| 9 |
"padding": null,
|
| 10 |
"added_tokens": [
|
| 11 |
{
|
|
|
|
| 1 |
{
|
| 2 |
"version": "1.0",
|
| 3 |
+
"truncation": null,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4 |
"padding": null,
|
| 5 |
"added_tokens": [
|
| 6 |
{
|
tokenizer_config.json
CHANGED
|
@@ -930,7 +930,7 @@
|
|
| 930 |
"clean_up_tokenization_spaces": true,
|
| 931 |
"eos_token": "</s>",
|
| 932 |
"extra_ids": 100,
|
| 933 |
-
"model_max_length":
|
| 934 |
"pad_token": "<pad>",
|
| 935 |
"tokenizer_class": "T5Tokenizer",
|
| 936 |
"unk_token": "<unk>"
|
|
|
|
| 930 |
"clean_up_tokenization_spaces": true,
|
| 931 |
"eos_token": "</s>",
|
| 932 |
"extra_ids": 100,
|
| 933 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 934 |
"pad_token": "<pad>",
|
| 935 |
"tokenizer_class": "T5Tokenizer",
|
| 936 |
"unk_token": "<unk>"
|
train_results.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
-
"epoch":
|
| 3 |
-
"train_loss": 0.
|
| 4 |
-
"train_runtime":
|
| 5 |
"train_samples": 276,
|
| 6 |
-
"train_samples_per_second":
|
| 7 |
-
"train_steps_per_second":
|
| 8 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"epoch": 5.0,
|
| 3 |
+
"train_loss": 0.16054312664529552,
|
| 4 |
+
"train_runtime": 120.7301,
|
| 5 |
"train_samples": 276,
|
| 6 |
+
"train_samples_per_second": 11.43,
|
| 7 |
+
"train_steps_per_second": 2.858
|
| 8 |
}
|
trainer_state.json
CHANGED
|
@@ -1,698 +1,95 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
-
"epoch":
|
| 5 |
"eval_steps": 500,
|
| 6 |
-
"global_step":
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
"epoch": 1.0,
|
| 13 |
-
"eval_gen_len":
|
| 14 |
-
"eval_loss": 0.
|
| 15 |
-
"eval_rouge1":
|
| 16 |
-
"eval_rouge2":
|
| 17 |
-
"eval_rougeL":
|
| 18 |
-
"eval_rougeLsum":
|
| 19 |
-
"eval_runtime":
|
| 20 |
-
"eval_samples_per_second":
|
| 21 |
-
"eval_steps_per_second":
|
| 22 |
-
"step":
|
| 23 |
},
|
| 24 |
{
|
| 25 |
"epoch": 2.0,
|
| 26 |
-
"eval_gen_len":
|
| 27 |
-
"eval_loss": 0.
|
| 28 |
-
"eval_rouge1":
|
| 29 |
-
"eval_rouge2":
|
| 30 |
-
"eval_rougeL":
|
| 31 |
-
"eval_rougeLsum":
|
| 32 |
-
"eval_runtime":
|
| 33 |
-
"eval_samples_per_second":
|
| 34 |
-
"eval_steps_per_second":
|
| 35 |
-
"step":
|
| 36 |
},
|
| 37 |
{
|
| 38 |
"epoch": 3.0,
|
| 39 |
-
"eval_gen_len":
|
| 40 |
-
"eval_loss": 0.
|
| 41 |
-
"eval_rouge1":
|
| 42 |
-
"eval_rouge2":
|
| 43 |
-
"eval_rougeL":
|
| 44 |
-
"eval_rougeLsum":
|
| 45 |
-
"eval_runtime":
|
| 46 |
-
"eval_samples_per_second":
|
| 47 |
-
"eval_steps_per_second":
|
| 48 |
-
"step":
|
| 49 |
},
|
| 50 |
{
|
| 51 |
"epoch": 4.0,
|
| 52 |
-
"eval_gen_len":
|
| 53 |
-
"eval_loss": 0.
|
| 54 |
-
"eval_rouge1":
|
| 55 |
-
"eval_rouge2":
|
| 56 |
-
"eval_rougeL":
|
| 57 |
-
"eval_rougeLsum":
|
| 58 |
-
"eval_runtime":
|
| 59 |
-
"eval_samples_per_second":
|
| 60 |
-
"eval_steps_per_second":
|
| 61 |
-
"step":
|
| 62 |
},
|
| 63 |
{
|
| 64 |
"epoch": 5.0,
|
| 65 |
-
"eval_gen_len":
|
| 66 |
-
"eval_loss": 0.
|
| 67 |
-
"eval_rouge1":
|
| 68 |
-
"eval_rouge2":
|
| 69 |
-
"eval_rougeL":
|
| 70 |
-
"eval_rougeLsum":
|
| 71 |
-
"eval_runtime":
|
| 72 |
-
"eval_samples_per_second":
|
| 73 |
-
"eval_steps_per_second":
|
| 74 |
-
"step":
|
| 75 |
},
|
| 76 |
{
|
| 77 |
-
"epoch":
|
| 78 |
-
"
|
| 79 |
-
"
|
| 80 |
-
"
|
| 81 |
-
"
|
| 82 |
-
"
|
| 83 |
-
"
|
| 84 |
-
"eval_runtime": 2.9058,
|
| 85 |
-
"eval_samples_per_second": 23.745,
|
| 86 |
-
"eval_steps_per_second": 3.097,
|
| 87 |
-
"step": 210
|
| 88 |
-
},
|
| 89 |
-
{
|
| 90 |
-
"epoch": 7.0,
|
| 91 |
-
"eval_gen_len": 65.55072463768116,
|
| 92 |
-
"eval_loss": 0.12134861946105957,
|
| 93 |
-
"eval_rouge1": 80.2369,
|
| 94 |
-
"eval_rouge2": 79.6485,
|
| 95 |
-
"eval_rougeL": 80.4178,
|
| 96 |
-
"eval_rougeLsum": 80.1986,
|
| 97 |
-
"eval_runtime": 2.934,
|
| 98 |
-
"eval_samples_per_second": 23.517,
|
| 99 |
-
"eval_steps_per_second": 3.067,
|
| 100 |
-
"step": 245
|
| 101 |
-
},
|
| 102 |
-
{
|
| 103 |
-
"epoch": 8.0,
|
| 104 |
-
"eval_gen_len": 65.23188405797102,
|
| 105 |
-
"eval_loss": 0.10570676624774933,
|
| 106 |
-
"eval_rouge1": 82.3014,
|
| 107 |
-
"eval_rouge2": 81.6093,
|
| 108 |
-
"eval_rougeL": 82.3372,
|
| 109 |
-
"eval_rougeLsum": 82.1797,
|
| 110 |
-
"eval_runtime": 2.7932,
|
| 111 |
-
"eval_samples_per_second": 24.703,
|
| 112 |
-
"eval_steps_per_second": 3.222,
|
| 113 |
-
"step": 280
|
| 114 |
-
},
|
| 115 |
-
{
|
| 116 |
-
"epoch": 9.0,
|
| 117 |
-
"eval_gen_len": 66.08695652173913,
|
| 118 |
-
"eval_loss": 0.09365525096654892,
|
| 119 |
-
"eval_rouge1": 83.5682,
|
| 120 |
-
"eval_rouge2": 82.9738,
|
| 121 |
-
"eval_rougeL": 83.6388,
|
| 122 |
-
"eval_rougeLsum": 83.5486,
|
| 123 |
-
"eval_runtime": 2.9365,
|
| 124 |
-
"eval_samples_per_second": 23.497,
|
| 125 |
-
"eval_steps_per_second": 3.065,
|
| 126 |
-
"step": 315
|
| 127 |
-
},
|
| 128 |
-
{
|
| 129 |
-
"epoch": 10.0,
|
| 130 |
-
"eval_gen_len": 66.08695652173913,
|
| 131 |
-
"eval_loss": 0.08428314328193665,
|
| 132 |
-
"eval_rouge1": 83.5735,
|
| 133 |
-
"eval_rouge2": 82.9779,
|
| 134 |
-
"eval_rougeL": 83.6425,
|
| 135 |
-
"eval_rougeLsum": 83.5533,
|
| 136 |
-
"eval_runtime": 2.9255,
|
| 137 |
-
"eval_samples_per_second": 23.586,
|
| 138 |
-
"eval_steps_per_second": 3.076,
|
| 139 |
-
"step": 350
|
| 140 |
-
},
|
| 141 |
-
{
|
| 142 |
-
"epoch": 11.0,
|
| 143 |
-
"eval_gen_len": 67.69565217391305,
|
| 144 |
-
"eval_loss": 0.07632659375667572,
|
| 145 |
-
"eval_rouge1": 83.5502,
|
| 146 |
-
"eval_rouge2": 83.0151,
|
| 147 |
-
"eval_rougeL": 83.7004,
|
| 148 |
-
"eval_rougeLsum": 83.6188,
|
| 149 |
-
"eval_runtime": 3.0282,
|
| 150 |
-
"eval_samples_per_second": 22.786,
|
| 151 |
-
"eval_steps_per_second": 2.972,
|
| 152 |
-
"step": 385
|
| 153 |
-
},
|
| 154 |
-
{
|
| 155 |
-
"epoch": 12.0,
|
| 156 |
-
"eval_gen_len": 65.6086956521739,
|
| 157 |
-
"eval_loss": 0.06880246102809906,
|
| 158 |
-
"eval_rouge1": 83.8612,
|
| 159 |
-
"eval_rouge2": 83.4112,
|
| 160 |
-
"eval_rougeL": 84.0555,
|
| 161 |
-
"eval_rougeLsum": 83.8541,
|
| 162 |
-
"eval_runtime": 2.9936,
|
| 163 |
-
"eval_samples_per_second": 23.049,
|
| 164 |
-
"eval_steps_per_second": 3.006,
|
| 165 |
-
"step": 420
|
| 166 |
-
},
|
| 167 |
-
{
|
| 168 |
-
"epoch": 13.0,
|
| 169 |
-
"eval_gen_len": 68.4927536231884,
|
| 170 |
-
"eval_loss": 0.0652654618024826,
|
| 171 |
-
"eval_rouge1": 83.2559,
|
| 172 |
-
"eval_rouge2": 82.7398,
|
| 173 |
-
"eval_rougeL": 83.437,
|
| 174 |
-
"eval_rougeLsum": 83.3363,
|
| 175 |
-
"eval_runtime": 3.0469,
|
| 176 |
-
"eval_samples_per_second": 22.646,
|
| 177 |
-
"eval_steps_per_second": 2.954,
|
| 178 |
-
"step": 455
|
| 179 |
-
},
|
| 180 |
-
{
|
| 181 |
-
"epoch": 14.0,
|
| 182 |
-
"eval_gen_len": 67.76811594202898,
|
| 183 |
-
"eval_loss": 0.06127766892313957,
|
| 184 |
-
"eval_rouge1": 84.2407,
|
| 185 |
-
"eval_rouge2": 83.738,
|
| 186 |
-
"eval_rougeL": 84.3104,
|
| 187 |
-
"eval_rougeLsum": 84.3012,
|
| 188 |
-
"eval_runtime": 3.1021,
|
| 189 |
-
"eval_samples_per_second": 22.243,
|
| 190 |
-
"eval_steps_per_second": 2.901,
|
| 191 |
-
"step": 490
|
| 192 |
-
},
|
| 193 |
-
{
|
| 194 |
-
"epoch": 14.29,
|
| 195 |
-
"learning_rate": 1.4285714285714287e-05,
|
| 196 |
-
"loss": 0.1963,
|
| 197 |
-
"step": 500
|
| 198 |
-
},
|
| 199 |
-
{
|
| 200 |
-
"epoch": 15.0,
|
| 201 |
-
"eval_gen_len": 68.55072463768116,
|
| 202 |
-
"eval_loss": 0.05842842161655426,
|
| 203 |
-
"eval_rouge1": 83.8361,
|
| 204 |
-
"eval_rouge2": 83.3141,
|
| 205 |
-
"eval_rougeL": 83.8976,
|
| 206 |
-
"eval_rougeLsum": 83.8751,
|
| 207 |
-
"eval_runtime": 3.2109,
|
| 208 |
-
"eval_samples_per_second": 21.489,
|
| 209 |
-
"eval_steps_per_second": 2.803,
|
| 210 |
-
"step": 525
|
| 211 |
-
},
|
| 212 |
-
{
|
| 213 |
-
"epoch": 16.0,
|
| 214 |
-
"eval_gen_len": 71.4927536231884,
|
| 215 |
-
"eval_loss": 0.05631176754832268,
|
| 216 |
-
"eval_rouge1": 83.5952,
|
| 217 |
-
"eval_rouge2": 83.1416,
|
| 218 |
-
"eval_rougeL": 83.5644,
|
| 219 |
-
"eval_rougeLsum": 83.5389,
|
| 220 |
-
"eval_runtime": 3.2752,
|
| 221 |
-
"eval_samples_per_second": 21.067,
|
| 222 |
-
"eval_steps_per_second": 2.748,
|
| 223 |
-
"step": 560
|
| 224 |
-
},
|
| 225 |
-
{
|
| 226 |
-
"epoch": 17.0,
|
| 227 |
-
"eval_gen_len": 69.47826086956522,
|
| 228 |
-
"eval_loss": 0.05389421060681343,
|
| 229 |
-
"eval_rouge1": 84.6048,
|
| 230 |
-
"eval_rouge2": 84.1681,
|
| 231 |
-
"eval_rougeL": 84.7325,
|
| 232 |
-
"eval_rougeLsum": 84.567,
|
| 233 |
-
"eval_runtime": 3.2569,
|
| 234 |
-
"eval_samples_per_second": 21.186,
|
| 235 |
-
"eval_steps_per_second": 2.763,
|
| 236 |
-
"step": 595
|
| 237 |
-
},
|
| 238 |
-
{
|
| 239 |
-
"epoch": 18.0,
|
| 240 |
-
"eval_gen_len": 68.72463768115942,
|
| 241 |
-
"eval_loss": 0.052007660269737244,
|
| 242 |
-
"eval_rouge1": 84.9204,
|
| 243 |
-
"eval_rouge2": 84.4493,
|
| 244 |
-
"eval_rougeL": 85.0357,
|
| 245 |
-
"eval_rougeLsum": 84.9063,
|
| 246 |
-
"eval_runtime": 3.1538,
|
| 247 |
-
"eval_samples_per_second": 21.879,
|
| 248 |
-
"eval_steps_per_second": 2.854,
|
| 249 |
-
"step": 630
|
| 250 |
-
},
|
| 251 |
-
{
|
| 252 |
-
"epoch": 19.0,
|
| 253 |
-
"eval_gen_len": 69.79710144927536,
|
| 254 |
-
"eval_loss": 0.051409389823675156,
|
| 255 |
-
"eval_rouge1": 84.3924,
|
| 256 |
-
"eval_rouge2": 83.9735,
|
| 257 |
-
"eval_rougeL": 84.4126,
|
| 258 |
-
"eval_rougeLsum": 84.3779,
|
| 259 |
-
"eval_runtime": 3.2185,
|
| 260 |
-
"eval_samples_per_second": 21.438,
|
| 261 |
-
"eval_steps_per_second": 2.796,
|
| 262 |
-
"step": 665
|
| 263 |
-
},
|
| 264 |
-
{
|
| 265 |
-
"epoch": 20.0,
|
| 266 |
-
"eval_gen_len": 67.23188405797102,
|
| 267 |
-
"eval_loss": 0.050410542637109756,
|
| 268 |
-
"eval_rouge1": 86.1503,
|
| 269 |
-
"eval_rouge2": 85.6151,
|
| 270 |
-
"eval_rougeL": 86.2393,
|
| 271 |
-
"eval_rougeLsum": 86.0495,
|
| 272 |
-
"eval_runtime": 3.144,
|
| 273 |
-
"eval_samples_per_second": 21.947,
|
| 274 |
-
"eval_steps_per_second": 2.863,
|
| 275 |
-
"step": 700
|
| 276 |
-
},
|
| 277 |
-
{
|
| 278 |
-
"epoch": 21.0,
|
| 279 |
-
"eval_gen_len": 66.52173913043478,
|
| 280 |
-
"eval_loss": 0.04962162673473358,
|
| 281 |
-
"eval_rouge1": 86.4875,
|
| 282 |
-
"eval_rouge2": 85.9614,
|
| 283 |
-
"eval_rougeL": 86.5042,
|
| 284 |
-
"eval_rougeLsum": 86.3616,
|
| 285 |
-
"eval_runtime": 3.1455,
|
| 286 |
-
"eval_samples_per_second": 21.936,
|
| 287 |
-
"eval_steps_per_second": 2.861,
|
| 288 |
-
"step": 735
|
| 289 |
-
},
|
| 290 |
-
{
|
| 291 |
-
"epoch": 22.0,
|
| 292 |
-
"eval_gen_len": 67.94202898550725,
|
| 293 |
-
"eval_loss": 0.04964025691151619,
|
| 294 |
-
"eval_rouge1": 85.6339,
|
| 295 |
-
"eval_rouge2": 85.1604,
|
| 296 |
-
"eval_rougeL": 85.6862,
|
| 297 |
-
"eval_rougeLsum": 85.5112,
|
| 298 |
-
"eval_runtime": 3.1386,
|
| 299 |
-
"eval_samples_per_second": 21.984,
|
| 300 |
-
"eval_steps_per_second": 2.868,
|
| 301 |
-
"step": 770
|
| 302 |
-
},
|
| 303 |
-
{
|
| 304 |
-
"epoch": 23.0,
|
| 305 |
-
"eval_gen_len": 65.52173913043478,
|
| 306 |
-
"eval_loss": 0.04901711642742157,
|
| 307 |
-
"eval_rouge1": 87.0368,
|
| 308 |
-
"eval_rouge2": 86.5415,
|
| 309 |
-
"eval_rougeL": 87.1099,
|
| 310 |
-
"eval_rougeLsum": 86.9317,
|
| 311 |
-
"eval_runtime": 3.1705,
|
| 312 |
-
"eval_samples_per_second": 21.763,
|
| 313 |
-
"eval_steps_per_second": 2.839,
|
| 314 |
-
"step": 805
|
| 315 |
-
},
|
| 316 |
-
{
|
| 317 |
-
"epoch": 24.0,
|
| 318 |
-
"eval_gen_len": 67.94202898550725,
|
| 319 |
-
"eval_loss": 0.04925404489040375,
|
| 320 |
-
"eval_rouge1": 85.6323,
|
| 321 |
-
"eval_rouge2": 85.1577,
|
| 322 |
-
"eval_rougeL": 85.6823,
|
| 323 |
-
"eval_rougeLsum": 85.5102,
|
| 324 |
-
"eval_runtime": 3.1481,
|
| 325 |
-
"eval_samples_per_second": 21.918,
|
| 326 |
-
"eval_steps_per_second": 2.859,
|
| 327 |
-
"step": 840
|
| 328 |
-
},
|
| 329 |
-
{
|
| 330 |
-
"epoch": 25.0,
|
| 331 |
-
"eval_gen_len": 69.04347826086956,
|
| 332 |
-
"eval_loss": 0.049253568053245544,
|
| 333 |
-
"eval_rouge1": 86.3078,
|
| 334 |
-
"eval_rouge2": 85.7832,
|
| 335 |
-
"eval_rougeL": 86.3026,
|
| 336 |
-
"eval_rougeLsum": 86.1442,
|
| 337 |
-
"eval_runtime": 3.2721,
|
| 338 |
-
"eval_samples_per_second": 21.087,
|
| 339 |
-
"eval_steps_per_second": 2.751,
|
| 340 |
-
"step": 875
|
| 341 |
-
},
|
| 342 |
-
{
|
| 343 |
-
"epoch": 26.0,
|
| 344 |
-
"eval_gen_len": 70.28985507246377,
|
| 345 |
-
"eval_loss": 0.04901302605867386,
|
| 346 |
-
"eval_rouge1": 85.877,
|
| 347 |
-
"eval_rouge2": 85.3534,
|
| 348 |
-
"eval_rougeL": 85.9035,
|
| 349 |
-
"eval_rougeLsum": 85.8208,
|
| 350 |
-
"eval_runtime": 3.3048,
|
| 351 |
-
"eval_samples_per_second": 20.879,
|
| 352 |
-
"eval_steps_per_second": 2.723,
|
| 353 |
-
"step": 910
|
| 354 |
-
},
|
| 355 |
-
{
|
| 356 |
-
"epoch": 27.0,
|
| 357 |
-
"eval_gen_len": 69.2463768115942,
|
| 358 |
-
"eval_loss": 0.04779437184333801,
|
| 359 |
-
"eval_rouge1": 86.6353,
|
| 360 |
-
"eval_rouge2": 86.054,
|
| 361 |
-
"eval_rougeL": 86.5856,
|
| 362 |
-
"eval_rougeLsum": 86.5515,
|
| 363 |
-
"eval_runtime": 3.295,
|
| 364 |
-
"eval_samples_per_second": 20.941,
|
| 365 |
-
"eval_steps_per_second": 2.731,
|
| 366 |
-
"step": 945
|
| 367 |
-
},
|
| 368 |
-
{
|
| 369 |
-
"epoch": 28.0,
|
| 370 |
-
"eval_gen_len": 68.56521739130434,
|
| 371 |
-
"eval_loss": 0.047761447727680206,
|
| 372 |
-
"eval_rouge1": 87.0975,
|
| 373 |
-
"eval_rouge2": 86.5716,
|
| 374 |
-
"eval_rougeL": 87.1452,
|
| 375 |
-
"eval_rougeLsum": 87.0713,
|
| 376 |
-
"eval_runtime": 3.2938,
|
| 377 |
-
"eval_samples_per_second": 20.948,
|
| 378 |
-
"eval_steps_per_second": 2.732,
|
| 379 |
-
"step": 980
|
| 380 |
-
},
|
| 381 |
-
{
|
| 382 |
-
"epoch": 28.57,
|
| 383 |
-
"learning_rate": 8.571428571428571e-06,
|
| 384 |
-
"loss": 0.0499,
|
| 385 |
-
"step": 1000
|
| 386 |
-
},
|
| 387 |
-
{
|
| 388 |
-
"epoch": 29.0,
|
| 389 |
-
"eval_gen_len": 67.0,
|
| 390 |
-
"eval_loss": 0.04680383577942848,
|
| 391 |
-
"eval_rouge1": 87.9989,
|
| 392 |
-
"eval_rouge2": 87.509,
|
| 393 |
-
"eval_rougeL": 88.0597,
|
| 394 |
-
"eval_rougeLsum": 87.9458,
|
| 395 |
-
"eval_runtime": 3.282,
|
| 396 |
-
"eval_samples_per_second": 21.024,
|
| 397 |
-
"eval_steps_per_second": 2.742,
|
| 398 |
-
"step": 1015
|
| 399 |
-
},
|
| 400 |
-
{
|
| 401 |
-
"epoch": 30.0,
|
| 402 |
-
"eval_gen_len": 69.1304347826087,
|
| 403 |
-
"eval_loss": 0.046802520751953125,
|
| 404 |
-
"eval_rouge1": 86.6642,
|
| 405 |
-
"eval_rouge2": 86.1007,
|
| 406 |
-
"eval_rougeL": 86.6429,
|
| 407 |
-
"eval_rougeLsum": 86.582,
|
| 408 |
-
"eval_runtime": 3.306,
|
| 409 |
-
"eval_samples_per_second": 20.871,
|
| 410 |
-
"eval_steps_per_second": 2.722,
|
| 411 |
-
"step": 1050
|
| 412 |
-
},
|
| 413 |
-
{
|
| 414 |
-
"epoch": 31.0,
|
| 415 |
-
"eval_gen_len": 69.30434782608695,
|
| 416 |
-
"eval_loss": 0.04671892151236534,
|
| 417 |
-
"eval_rouge1": 86.3475,
|
| 418 |
-
"eval_rouge2": 85.7566,
|
| 419 |
-
"eval_rougeL": 86.257,
|
| 420 |
-
"eval_rougeLsum": 86.2544,
|
| 421 |
-
"eval_runtime": 3.2952,
|
| 422 |
-
"eval_samples_per_second": 20.94,
|
| 423 |
-
"eval_steps_per_second": 2.731,
|
| 424 |
-
"step": 1085
|
| 425 |
-
},
|
| 426 |
-
{
|
| 427 |
-
"epoch": 32.0,
|
| 428 |
-
"eval_gen_len": 69.14492753623189,
|
| 429 |
-
"eval_loss": 0.046326328068971634,
|
| 430 |
-
"eval_rouge1": 86.6794,
|
| 431 |
-
"eval_rouge2": 86.1044,
|
| 432 |
-
"eval_rougeL": 86.6438,
|
| 433 |
-
"eval_rougeLsum": 86.5856,
|
| 434 |
-
"eval_runtime": 3.3092,
|
| 435 |
-
"eval_samples_per_second": 20.851,
|
| 436 |
-
"eval_steps_per_second": 2.72,
|
| 437 |
-
"step": 1120
|
| 438 |
-
},
|
| 439 |
-
{
|
| 440 |
-
"epoch": 33.0,
|
| 441 |
-
"eval_gen_len": 69.14492753623189,
|
| 442 |
-
"eval_loss": 0.0462319478392601,
|
| 443 |
-
"eval_rouge1": 86.6794,
|
| 444 |
-
"eval_rouge2": 86.1044,
|
| 445 |
-
"eval_rougeL": 86.6438,
|
| 446 |
-
"eval_rougeLsum": 86.5856,
|
| 447 |
-
"eval_runtime": 3.2895,
|
| 448 |
-
"eval_samples_per_second": 20.976,
|
| 449 |
-
"eval_steps_per_second": 2.736,
|
| 450 |
-
"step": 1155
|
| 451 |
-
},
|
| 452 |
-
{
|
| 453 |
-
"epoch": 34.0,
|
| 454 |
-
"eval_gen_len": 68.46376811594203,
|
| 455 |
-
"eval_loss": 0.04606299102306366,
|
| 456 |
-
"eval_rouge1": 87.1151,
|
| 457 |
-
"eval_rouge2": 86.605,
|
| 458 |
-
"eval_rougeL": 87.1857,
|
| 459 |
-
"eval_rougeLsum": 87.1151,
|
| 460 |
-
"eval_runtime": 3.2939,
|
| 461 |
-
"eval_samples_per_second": 20.948,
|
| 462 |
-
"eval_steps_per_second": 2.732,
|
| 463 |
-
"step": 1190
|
| 464 |
-
},
|
| 465 |
-
{
|
| 466 |
-
"epoch": 35.0,
|
| 467 |
-
"eval_gen_len": 67.01449275362319,
|
| 468 |
-
"eval_loss": 0.045941609889268875,
|
| 469 |
-
"eval_rouge1": 88.0068,
|
| 470 |
-
"eval_rouge2": 87.5135,
|
| 471 |
-
"eval_rougeL": 88.0611,
|
| 472 |
-
"eval_rougeLsum": 87.9535,
|
| 473 |
-
"eval_runtime": 3.2649,
|
| 474 |
-
"eval_samples_per_second": 21.134,
|
| 475 |
-
"eval_steps_per_second": 2.757,
|
| 476 |
-
"step": 1225
|
| 477 |
-
},
|
| 478 |
-
{
|
| 479 |
-
"epoch": 36.0,
|
| 480 |
-
"eval_gen_len": 67.57971014492753,
|
| 481 |
-
"eval_loss": 0.045919787138700485,
|
| 482 |
-
"eval_rouge1": 87.6823,
|
| 483 |
-
"eval_rouge2": 87.1982,
|
| 484 |
-
"eval_rougeL": 87.7207,
|
| 485 |
-
"eval_rougeLsum": 87.6541,
|
| 486 |
-
"eval_runtime": 3.2871,
|
| 487 |
-
"eval_samples_per_second": 20.991,
|
| 488 |
-
"eval_steps_per_second": 2.738,
|
| 489 |
-
"step": 1260
|
| 490 |
-
},
|
| 491 |
-
{
|
| 492 |
-
"epoch": 37.0,
|
| 493 |
-
"eval_gen_len": 69.14492753623189,
|
| 494 |
-
"eval_loss": 0.04610535874962807,
|
| 495 |
-
"eval_rouge1": 86.6794,
|
| 496 |
-
"eval_rouge2": 86.1044,
|
| 497 |
-
"eval_rougeL": 86.6438,
|
| 498 |
-
"eval_rougeLsum": 86.5856,
|
| 499 |
-
"eval_runtime": 3.2941,
|
| 500 |
-
"eval_samples_per_second": 20.946,
|
| 501 |
-
"eval_steps_per_second": 2.732,
|
| 502 |
-
"step": 1295
|
| 503 |
-
},
|
| 504 |
-
{
|
| 505 |
-
"epoch": 38.0,
|
| 506 |
-
"eval_gen_len": 69.14492753623189,
|
| 507 |
-
"eval_loss": 0.046049315482378006,
|
| 508 |
-
"eval_rouge1": 86.6794,
|
| 509 |
-
"eval_rouge2": 86.1044,
|
| 510 |
-
"eval_rougeL": 86.6438,
|
| 511 |
-
"eval_rougeLsum": 86.5856,
|
| 512 |
-
"eval_runtime": 3.2849,
|
| 513 |
-
"eval_samples_per_second": 21.005,
|
| 514 |
-
"eval_steps_per_second": 2.74,
|
| 515 |
-
"step": 1330
|
| 516 |
-
},
|
| 517 |
-
{
|
| 518 |
-
"epoch": 39.0,
|
| 519 |
-
"eval_gen_len": 69.04347826086956,
|
| 520 |
-
"eval_loss": 0.04580928757786751,
|
| 521 |
-
"eval_rouge1": 86.701,
|
| 522 |
-
"eval_rouge2": 86.1532,
|
| 523 |
-
"eval_rougeL": 86.6831,
|
| 524 |
-
"eval_rougeLsum": 86.6226,
|
| 525 |
-
"eval_runtime": 3.2714,
|
| 526 |
-
"eval_samples_per_second": 21.092,
|
| 527 |
-
"eval_steps_per_second": 2.751,
|
| 528 |
-
"step": 1365
|
| 529 |
-
},
|
| 530 |
-
{
|
| 531 |
-
"epoch": 40.0,
|
| 532 |
-
"eval_gen_len": 69.04347826086956,
|
| 533 |
-
"eval_loss": 0.04582460597157478,
|
| 534 |
-
"eval_rouge1": 86.701,
|
| 535 |
-
"eval_rouge2": 86.1532,
|
| 536 |
-
"eval_rougeL": 86.6831,
|
| 537 |
-
"eval_rougeLsum": 86.6226,
|
| 538 |
-
"eval_runtime": 3.2721,
|
| 539 |
-
"eval_samples_per_second": 21.087,
|
| 540 |
-
"eval_steps_per_second": 2.751,
|
| 541 |
-
"step": 1400
|
| 542 |
-
},
|
| 543 |
-
{
|
| 544 |
-
"epoch": 41.0,
|
| 545 |
-
"eval_gen_len": 67.47826086956522,
|
| 546 |
-
"eval_loss": 0.0457453578710556,
|
| 547 |
-
"eval_rouge1": 87.6998,
|
| 548 |
-
"eval_rouge2": 87.2471,
|
| 549 |
-
"eval_rougeL": 87.7695,
|
| 550 |
-
"eval_rougeLsum": 87.6934,
|
| 551 |
-
"eval_runtime": 3.2688,
|
| 552 |
-
"eval_samples_per_second": 21.109,
|
| 553 |
-
"eval_steps_per_second": 2.753,
|
| 554 |
-
"step": 1435
|
| 555 |
-
},
|
| 556 |
-
{
|
| 557 |
-
"epoch": 42.0,
|
| 558 |
-
"eval_gen_len": 69.14492753623189,
|
| 559 |
-
"eval_loss": 0.04603540897369385,
|
| 560 |
-
"eval_rouge1": 86.6794,
|
| 561 |
-
"eval_rouge2": 86.1044,
|
| 562 |
-
"eval_rougeL": 86.6438,
|
| 563 |
-
"eval_rougeLsum": 86.5856,
|
| 564 |
-
"eval_runtime": 3.3002,
|
| 565 |
-
"eval_samples_per_second": 20.908,
|
| 566 |
-
"eval_steps_per_second": 2.727,
|
| 567 |
-
"step": 1470
|
| 568 |
-
},
|
| 569 |
-
{
|
| 570 |
-
"epoch": 42.86,
|
| 571 |
-
"learning_rate": 2.8571428571428573e-06,
|
| 572 |
-
"loss": 0.0362,
|
| 573 |
-
"step": 1500
|
| 574 |
-
},
|
| 575 |
-
{
|
| 576 |
-
"epoch": 43.0,
|
| 577 |
-
"eval_gen_len": 67.65217391304348,
|
| 578 |
-
"eval_loss": 0.045989979058504105,
|
| 579 |
-
"eval_rouge1": 87.5977,
|
| 580 |
-
"eval_rouge2": 87.1424,
|
| 581 |
-
"eval_rougeL": 87.6777,
|
| 582 |
-
"eval_rougeLsum": 87.5976,
|
| 583 |
-
"eval_runtime": 3.2827,
|
| 584 |
-
"eval_samples_per_second": 21.02,
|
| 585 |
-
"eval_steps_per_second": 2.742,
|
| 586 |
-
"step": 1505
|
| 587 |
-
},
|
| 588 |
-
{
|
| 589 |
-
"epoch": 44.0,
|
| 590 |
-
"eval_gen_len": 67.76811594202898,
|
| 591 |
-
"eval_loss": 0.04582388699054718,
|
| 592 |
-
"eval_rouge1": 87.571,
|
| 593 |
-
"eval_rouge2": 87.1237,
|
| 594 |
-
"eval_rougeL": 87.6515,
|
| 595 |
-
"eval_rougeLsum": 87.5747,
|
| 596 |
-
"eval_runtime": 3.3039,
|
| 597 |
-
"eval_samples_per_second": 20.884,
|
| 598 |
-
"eval_steps_per_second": 2.724,
|
| 599 |
-
"step": 1540
|
| 600 |
-
},
|
| 601 |
-
{
|
| 602 |
-
"epoch": 45.0,
|
| 603 |
-
"eval_gen_len": 67.10144927536231,
|
| 604 |
-
"eval_loss": 0.045716848224401474,
|
| 605 |
-
"eval_rouge1": 87.9476,
|
| 606 |
-
"eval_rouge2": 87.4526,
|
| 607 |
-
"eval_rougeL": 88.0306,
|
| 608 |
-
"eval_rougeLsum": 87.9122,
|
| 609 |
-
"eval_runtime": 3.2864,
|
| 610 |
-
"eval_samples_per_second": 20.996,
|
| 611 |
-
"eval_steps_per_second": 2.739,
|
| 612 |
-
"step": 1575
|
| 613 |
-
},
|
| 614 |
-
{
|
| 615 |
-
"epoch": 46.0,
|
| 616 |
-
"eval_gen_len": 67.66666666666667,
|
| 617 |
-
"eval_loss": 0.04581255465745926,
|
| 618 |
-
"eval_rouge1": 87.6074,
|
| 619 |
-
"eval_rouge2": 87.1494,
|
| 620 |
-
"eval_rougeL": 87.6861,
|
| 621 |
-
"eval_rougeLsum": 87.6103,
|
| 622 |
-
"eval_runtime": 3.297,
|
| 623 |
-
"eval_samples_per_second": 20.928,
|
| 624 |
-
"eval_steps_per_second": 2.73,
|
| 625 |
-
"step": 1610
|
| 626 |
-
},
|
| 627 |
-
{
|
| 628 |
-
"epoch": 47.0,
|
| 629 |
-
"eval_gen_len": 67.66666666666667,
|
| 630 |
-
"eval_loss": 0.045844241976737976,
|
| 631 |
-
"eval_rouge1": 87.6074,
|
| 632 |
-
"eval_rouge2": 87.1494,
|
| 633 |
-
"eval_rougeL": 87.6861,
|
| 634 |
-
"eval_rougeLsum": 87.6103,
|
| 635 |
-
"eval_runtime": 3.2878,
|
| 636 |
-
"eval_samples_per_second": 20.987,
|
| 637 |
-
"eval_steps_per_second": 2.737,
|
| 638 |
-
"step": 1645
|
| 639 |
-
},
|
| 640 |
-
{
|
| 641 |
-
"epoch": 48.0,
|
| 642 |
-
"eval_gen_len": 67.66666666666667,
|
| 643 |
-
"eval_loss": 0.045833244919776917,
|
| 644 |
-
"eval_rouge1": 87.6074,
|
| 645 |
-
"eval_rouge2": 87.1494,
|
| 646 |
-
"eval_rougeL": 87.6861,
|
| 647 |
-
"eval_rougeLsum": 87.6103,
|
| 648 |
-
"eval_runtime": 3.2729,
|
| 649 |
-
"eval_samples_per_second": 21.082,
|
| 650 |
-
"eval_steps_per_second": 2.75,
|
| 651 |
-
"step": 1680
|
| 652 |
-
},
|
| 653 |
-
{
|
| 654 |
-
"epoch": 49.0,
|
| 655 |
-
"eval_gen_len": 68.34782608695652,
|
| 656 |
-
"eval_loss": 0.045867208391427994,
|
| 657 |
-
"eval_rouge1": 87.1522,
|
| 658 |
-
"eval_rouge2": 86.6031,
|
| 659 |
-
"eval_rougeL": 87.1206,
|
| 660 |
-
"eval_rougeLsum": 87.0701,
|
| 661 |
-
"eval_runtime": 3.2833,
|
| 662 |
-
"eval_samples_per_second": 21.016,
|
| 663 |
-
"eval_steps_per_second": 2.741,
|
| 664 |
-
"step": 1715
|
| 665 |
-
},
|
| 666 |
-
{
|
| 667 |
-
"epoch": 50.0,
|
| 668 |
-
"eval_gen_len": 68.34782608695652,
|
| 669 |
-
"eval_loss": 0.04586370289325714,
|
| 670 |
-
"eval_rouge1": 87.1522,
|
| 671 |
-
"eval_rouge2": 86.6031,
|
| 672 |
-
"eval_rougeL": 87.1206,
|
| 673 |
-
"eval_rougeLsum": 87.0701,
|
| 674 |
-
"eval_runtime": 3.2773,
|
| 675 |
-
"eval_samples_per_second": 21.054,
|
| 676 |
-
"eval_steps_per_second": 2.746,
|
| 677 |
-
"step": 1750
|
| 678 |
-
},
|
| 679 |
-
{
|
| 680 |
-
"epoch": 50.0,
|
| 681 |
-
"step": 1750,
|
| 682 |
-
"total_flos": 3735433720627200.0,
|
| 683 |
-
"train_loss": 0.08541564777919225,
|
| 684 |
-
"train_runtime": 358.6661,
|
| 685 |
-
"train_samples_per_second": 38.476,
|
| 686 |
-
"train_steps_per_second": 4.879
|
| 687 |
}
|
| 688 |
],
|
| 689 |
"logging_steps": 500,
|
| 690 |
-
"max_steps":
|
| 691 |
"num_input_tokens_seen": 0,
|
| 692 |
-
"num_train_epochs":
|
| 693 |
"save_steps": 500,
|
| 694 |
-
"total_flos":
|
| 695 |
-
"train_batch_size":
|
| 696 |
"trial_name": null,
|
| 697 |
"trial_params": null
|
| 698 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 5.0,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 345,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
| 10 |
"log_history": [
|
| 11 |
{
|
| 12 |
"epoch": 1.0,
|
| 13 |
+
"eval_gen_len": 49.08695652173913,
|
| 14 |
+
"eval_loss": 0.2411632537841797,
|
| 15 |
+
"eval_rouge1": 74.9533,
|
| 16 |
+
"eval_rouge2": 71.1831,
|
| 17 |
+
"eval_rougeL": 74.2512,
|
| 18 |
+
"eval_rougeLsum": 74.5914,
|
| 19 |
+
"eval_runtime": 9.2355,
|
| 20 |
+
"eval_samples_per_second": 7.471,
|
| 21 |
+
"eval_steps_per_second": 1.949,
|
| 22 |
+
"step": 69
|
| 23 |
},
|
| 24 |
{
|
| 25 |
"epoch": 2.0,
|
| 26 |
+
"eval_gen_len": 88.17391304347827,
|
| 27 |
+
"eval_loss": 0.08010436594486237,
|
| 28 |
+
"eval_rouge1": 78.7144,
|
| 29 |
+
"eval_rouge2": 77.7186,
|
| 30 |
+
"eval_rougeL": 78.6962,
|
| 31 |
+
"eval_rougeLsum": 78.6452,
|
| 32 |
+
"eval_runtime": 11.7911,
|
| 33 |
+
"eval_samples_per_second": 5.852,
|
| 34 |
+
"eval_steps_per_second": 1.527,
|
| 35 |
+
"step": 138
|
| 36 |
},
|
| 37 |
{
|
| 38 |
"epoch": 3.0,
|
| 39 |
+
"eval_gen_len": 73.0,
|
| 40 |
+
"eval_loss": 0.08717019110918045,
|
| 41 |
+
"eval_rouge1": 83.0112,
|
| 42 |
+
"eval_rouge2": 82.1689,
|
| 43 |
+
"eval_rougeL": 82.8847,
|
| 44 |
+
"eval_rougeLsum": 82.9534,
|
| 45 |
+
"eval_runtime": 10.9663,
|
| 46 |
+
"eval_samples_per_second": 6.292,
|
| 47 |
+
"eval_steps_per_second": 1.641,
|
| 48 |
+
"step": 207
|
| 49 |
},
|
| 50 |
{
|
| 51 |
"epoch": 4.0,
|
| 52 |
+
"eval_gen_len": 60.88405797101449,
|
| 53 |
+
"eval_loss": 0.06106267869472504,
|
| 54 |
+
"eval_rouge1": 86.2191,
|
| 55 |
+
"eval_rouge2": 85.8311,
|
| 56 |
+
"eval_rougeL": 86.308,
|
| 57 |
+
"eval_rougeLsum": 86.4542,
|
| 58 |
+
"eval_runtime": 9.6061,
|
| 59 |
+
"eval_samples_per_second": 7.183,
|
| 60 |
+
"eval_steps_per_second": 1.874,
|
| 61 |
+
"step": 276
|
| 62 |
},
|
| 63 |
{
|
| 64 |
"epoch": 5.0,
|
| 65 |
+
"eval_gen_len": 62.05797101449275,
|
| 66 |
+
"eval_loss": 0.0359114333987236,
|
| 67 |
+
"eval_rouge1": 84.8601,
|
| 68 |
+
"eval_rouge2": 84.2185,
|
| 69 |
+
"eval_rougeL": 84.7842,
|
| 70 |
+
"eval_rougeLsum": 84.8657,
|
| 71 |
+
"eval_runtime": 9.6516,
|
| 72 |
+
"eval_samples_per_second": 7.149,
|
| 73 |
+
"eval_steps_per_second": 1.865,
|
| 74 |
+
"step": 345
|
| 75 |
},
|
| 76 |
{
|
| 77 |
+
"epoch": 5.0,
|
| 78 |
+
"step": 345,
|
| 79 |
+
"total_flos": 1680723777945600.0,
|
| 80 |
+
"train_loss": 0.16054312664529552,
|
| 81 |
+
"train_runtime": 120.7301,
|
| 82 |
+
"train_samples_per_second": 11.43,
|
| 83 |
+
"train_steps_per_second": 2.858
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 84 |
}
|
| 85 |
],
|
| 86 |
"logging_steps": 500,
|
| 87 |
+
"max_steps": 345,
|
| 88 |
"num_input_tokens_seen": 0,
|
| 89 |
+
"num_train_epochs": 5,
|
| 90 |
"save_steps": 500,
|
| 91 |
+
"total_flos": 1680723777945600.0,
|
| 92 |
+
"train_batch_size": 4,
|
| 93 |
"trial_name": null,
|
| 94 |
"trial_params": null
|
| 95 |
}
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4984
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e025e4018a9890f32b5c68a2e1bb60ff4238740a0a6ef6e06af05e57c789d285
|
| 3 |
size 4984
|