ratishsp commited on
Commit ·
8b0bf1c
1
Parent(s): ce946f4
initial commit
Browse files- README.md +121 -1
- added_tokens.json +3 -0
- all_results.json +18 -0
- config.json +54 -0
- eval_results.json +13 -0
- merges.txt +0 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +51 -0
- tokenizer.json +0 -0
- tokenizer_config.json +65 -0
- train_results.json +8 -0
- trainer_state.json +2064 -0
- training_args.bin +3 -0
- vocab.json +0 -0
README.md
CHANGED
|
@@ -1,3 +1,123 @@
|
|
| 1 |
---
|
| 2 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
+
tags:
|
| 3 |
+
- generated_from_trainer
|
| 4 |
+
datasets:
|
| 5 |
+
- multi_news
|
| 6 |
+
metrics:
|
| 7 |
+
- rouge
|
| 8 |
+
model-index:
|
| 9 |
+
- name: Centrum-multinews
|
| 10 |
+
results:
|
| 11 |
+
- task:
|
| 12 |
+
name: Summarization
|
| 13 |
+
type: summarization
|
| 14 |
+
dataset:
|
| 15 |
+
name: multi_news
|
| 16 |
+
type: multi_news
|
| 17 |
+
args: default
|
| 18 |
+
metrics:
|
| 19 |
+
- name: Rouge1
|
| 20 |
+
type: rouge
|
| 21 |
+
value: 46.2987
|
| 22 |
---
|
| 23 |
+
|
| 24 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 25 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 26 |
+
|
| 27 |
+
# Centrum-multinews
|
| 28 |
+
|
| 29 |
+
This model is a fine-tuned version of [Centrum](https://huggingface.co/ratishsp/Centrum) on the multi_news dataset.
|
| 30 |
+
It achieves the following results on the evaluation set:
|
| 31 |
+
- Loss: 3.2740
|
| 32 |
+
- Rouge1: 46.2987
|
| 33 |
+
- Rouge2: 18.4863
|
| 34 |
+
- Rougel: 24.2428
|
| 35 |
+
- Rougelsum: 42.5102
|
| 36 |
+
- Gen Len: 308.6606
|
| 37 |
+
|
| 38 |
+
## Model description
|
| 39 |
+
|
| 40 |
+
More information needed
|
| 41 |
+
|
| 42 |
+
## Intended uses & limitations
|
| 43 |
+
|
| 44 |
+
More information needed
|
| 45 |
+
|
| 46 |
+
## Training and evaluation data
|
| 47 |
+
|
| 48 |
+
More information needed
|
| 49 |
+
|
| 50 |
+
## Training procedure
|
| 51 |
+
|
| 52 |
+
### Training hyperparameters
|
| 53 |
+
|
| 54 |
+
The following hyperparameters were used during training:
|
| 55 |
+
- learning_rate: 3e-05
|
| 56 |
+
- train_batch_size: 1
|
| 57 |
+
- eval_batch_size: 4
|
| 58 |
+
- seed: 42
|
| 59 |
+
- distributed_type: multi-GPU
|
| 60 |
+
- num_devices: 4
|
| 61 |
+
- gradient_accumulation_steps: 4
|
| 62 |
+
- total_train_batch_size: 16
|
| 63 |
+
- total_eval_batch_size: 16
|
| 64 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 65 |
+
- lr_scheduler_type: linear
|
| 66 |
+
- lr_scheduler_warmup_steps: 2500
|
| 67 |
+
- training_steps: 25000
|
| 68 |
+
- mixed_precision_training: Native AMP
|
| 69 |
+
- label_smoothing_factor: 0.1
|
| 70 |
+
|
| 71 |
+
### Training results
|
| 72 |
+
|
| 73 |
+
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|
| 74 |
+
|:-------------:|:-----:|:-----:|:---------------:|:-------:|:-------:|:-------:|:---------:|:--------:|
|
| 75 |
+
| 3.2702 | 1.78 | 5000 | 3.2853 | 44.0203 | 16.6061 | 23.3846 | 40.3853 | 277.1855 |
|
| 76 |
+
| 3.2762 | 1.96 | 5500 | 3.2853 | 44.725 | 16.9262 | 23.475 | 41.0003 | 288.4173 |
|
| 77 |
+
| 3.2114 | 2.14 | 6000 | 3.2857 | 44.6456 | 17.0245 | 23.7328 | 40.9131 | 257.2761 |
|
| 78 |
+
| 3.1981 | 2.31 | 6500 | 3.2817 | 44.7869 | 17.0849 | 23.8372 | 41.0669 | 254.8618 |
|
| 79 |
+
| 3.2298 | 2.49 | 7000 | 3.2802 | 45.2657 | 17.2618 | 23.8204 | 41.5807 | 263.0854 |
|
| 80 |
+
| 3.2167 | 2.67 | 7500 | 3.2773 | 44.9516 | 17.0538 | 23.7894 | 41.1673 | 244.6939 |
|
| 81 |
+
| 3.2069 | 2.85 | 8000 | 3.2712 | 45.2153 | 17.2766 | 23.9883 | 41.4558 | 245.4036 |
|
| 82 |
+
| 3.1822 | 3.02 | 8500 | 3.2786 | 45.4747 | 17.6754 | 24.1878 | 41.7304 | 254.6624 |
|
| 83 |
+
| 3.1529 | 3.2 | 9000 | 3.2740 | 44.9033 | 17.1386 | 23.8511 | 41.177 | 246.0157 |
|
| 84 |
+
| 3.1407 | 3.38 | 9500 | 3.2704 | 45.1045 | 17.2335 | 23.9124 | 41.3243 | 243.4922 |
|
| 85 |
+
| 3.1376 | 3.56 | 10000 | 3.2721 | 45.2694 | 17.4797 | 24.1072 | 41.5441 | 243.8396 |
|
| 86 |
+
| 3.1545 | 3.74 | 10500 | 3.2720 | 45.3105 | 17.6338 | 24.1547 | 41.5731 | 231.1805 |
|
| 87 |
+
| 3.1307 | 3.91 | 11000 | 3.2684 | 45.4309 | 17.2665 | 23.8954 | 41.6518 | 250.1039 |
|
| 88 |
+
| 3.1022 | 4.09 | 11500 | 3.2719 | 45.1959 | 17.4017 | 24.056 | 41.5363 | 242.5923 |
|
| 89 |
+
| 3.1139 | 4.27 | 12000 | 3.2711 | 45.3864 | 17.4653 | 24.028 | 41.6797 | 240.5701 |
|
| 90 |
+
| 3.0978 | 4.45 | 12500 | 3.2722 | 45.5694 | 17.501 | 24.1452 | 41.7894 | 232.1149 |
|
| 91 |
+
| 3.1082 | 4.63 | 13000 | 3.2687 | 45.504 | 17.5137 | 24.1067 | 41.7686 | 245.1845 |
|
| 92 |
+
| 3.1059 | 4.8 | 13500 | 3.2686 | 45.3603 | 17.1619 | 23.8655 | 41.5953 | 248.6327 |
|
| 93 |
+
| 3.1141 | 4.98 | 14000 | 3.2658 | 45.2741 | 17.3814 | 24.0377 | 41.5263 | 234.0194 |
|
| 94 |
+
| 3.0294 | 5.16 | 14500 | 3.2716 | 45.7203 | 17.5962 | 24.1367 | 41.9119 | 244.4207 |
|
| 95 |
+
| 3.0613 | 5.34 | 15000 | 3.2697 | 45.775 | 17.6959 | 24.1867 | 42.0018 | 242.0381 |
|
| 96 |
+
| 3.0549 | 5.52 | 15500 | 3.2703 | 45.8193 | 17.686 | 24.1997 | 42.0109 | 242.5493 |
|
| 97 |
+
| 3.0725 | 5.69 | 16000 | 3.2655 | 45.3515 | 17.3438 | 24.0586 | 41.6126 | 240.2812 |
|
| 98 |
+
| 3.0728 | 5.87 | 16500 | 3.2671 | 45.6791 | 17.5028 | 24.0691 | 41.9219 | 250.455 |
|
| 99 |
+
| 3.0142 | 6.05 | 17000 | 3.2708 | 46.0287 | 17.8079 | 24.2916 | 42.2369 | 245.6204 |
|
| 100 |
+
| 3.0312 | 6.23 | 17500 | 3.2701 | 45.5731 | 17.5404 | 24.0925 | 41.7584 | 236.2234 |
|
| 101 |
+
| 3.0231 | 6.41 | 18000 | 3.2719 | 46.1094 | 17.7117 | 24.1117 | 42.2882 | 260.1686 |
|
| 102 |
+
| 3.0414 | 6.58 | 18500 | 3.2703 | 45.9178 | 17.6987 | 24.1882 | 42.1382 | 245.0961 |
|
| 103 |
+
| 3.0434 | 6.76 | 19000 | 3.2715 | 46.0129 | 17.7545 | 24.2235 | 42.245 | 247.8225 |
|
| 104 |
+
| 3.0456 | 6.94 | 19500 | 3.2682 | 45.8634 | 17.6462 | 24.1366 | 42.1194 | 256.9835 |
|
| 105 |
+
| 3.0188 | 7.12 | 20000 | 3.2752 | 45.8366 | 17.6771 | 24.165 | 42.0438 | 240.1866 |
|
| 106 |
+
| 3.0227 | 7.3 | 20500 | 3.2722 | 46.0509 | 17.8248 | 24.2389 | 42.2681 | 245.8337 |
|
| 107 |
+
| 2.9895 | 7.47 | 21000 | 3.2726 | 45.7896 | 17.5833 | 24.1226 | 42.016 | 243.867 |
|
| 108 |
+
| 3.0146 | 7.65 | 21500 | 3.2693 | 46.0179 | 17.6952 | 24.2204 | 42.2436 | 244.0598 |
|
| 109 |
+
| 3.014 | 7.83 | 22000 | 3.2708 | 46.0704 | 17.75 | 24.2308 | 42.2591 | 240.4804 |
|
| 110 |
+
| 3.0427 | 8.01 | 22500 | 3.2734 | 46.0662 | 17.7231 | 24.1915 | 42.2227 | 242.4203 |
|
| 111 |
+
| 2.9835 | 8.19 | 23000 | 3.2740 | 46.165 | 17.8947 | 24.366 | 42.3521 | 236.6266 |
|
| 112 |
+
| 2.987 | 8.36 | 23500 | 3.2719 | 45.9025 | 17.7625 | 24.2432 | 42.1257 | 238.479 |
|
| 113 |
+
| 2.9922 | 8.54 | 24000 | 3.2731 | 46.1971 | 17.7962 | 24.2279 | 42.3853 | 245.2081 |
|
| 114 |
+
| 2.9788 | 8.72 | 24500 | 3.2718 | 46.0806 | 17.8417 | 24.3261 | 42.264 | 240.1747 |
|
| 115 |
+
| 2.9878 | 8.9 | 25000 | 3.2715 | 46.0618 | 17.7725 | 24.2234 | 42.2574 | 242.5598 |
|
| 116 |
+
|
| 117 |
+
|
| 118 |
+
### Framework versions
|
| 119 |
+
|
| 120 |
+
- Transformers 4.20.0.dev0
|
| 121 |
+
- Pytorch 1.11.0
|
| 122 |
+
- Datasets 2.2.2
|
| 123 |
+
- Tokenizers 0.12.1
|
added_tokens.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<doc-sep>": 50265
|
| 3 |
+
}
|
all_results.json
ADDED
|
@@ -0,0 +1,18 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 8.9,
|
| 3 |
+
"eval_gen_len": 308.6606,
|
| 4 |
+
"eval_loss": 3.273963212966919,
|
| 5 |
+
"eval_rouge1": 46.2987,
|
| 6 |
+
"eval_rouge2": 18.4863,
|
| 7 |
+
"eval_rougeL": 24.2428,
|
| 8 |
+
"eval_rougeLsum": 42.5102,
|
| 9 |
+
"eval_runtime": 1836.4721,
|
| 10 |
+
"eval_samples": 5622,
|
| 11 |
+
"eval_samples_per_second": 3.061,
|
| 12 |
+
"eval_steps_per_second": 0.192,
|
| 13 |
+
"train_loss": 3.1441598370170594,
|
| 14 |
+
"train_runtime": 61182.0827,
|
| 15 |
+
"train_samples": 44972,
|
| 16 |
+
"train_samples_per_second": 6.538,
|
| 17 |
+
"train_steps_per_second": 0.409
|
| 18 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,54 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "Centrum-multinews",
|
| 3 |
+
"activation_dropout": 0.0,
|
| 4 |
+
"activation_function": "gelu",
|
| 5 |
+
"architectures": [
|
| 6 |
+
"LEDForConditionalGeneration"
|
| 7 |
+
],
|
| 8 |
+
"attention_dropout": 0.0,
|
| 9 |
+
"attention_window": [
|
| 10 |
+
512,
|
| 11 |
+
512,
|
| 12 |
+
512,
|
| 13 |
+
512,
|
| 14 |
+
512,
|
| 15 |
+
512
|
| 16 |
+
],
|
| 17 |
+
"bos_token_id": 0,
|
| 18 |
+
"classif_dropout": 0.0,
|
| 19 |
+
"classifier_dropout": 0.0,
|
| 20 |
+
"d_model": 768,
|
| 21 |
+
"decoder_attention_heads": 12,
|
| 22 |
+
"decoder_ffn_dim": 3072,
|
| 23 |
+
"decoder_layerdrop": 0.0,
|
| 24 |
+
"decoder_layers": 6,
|
| 25 |
+
"decoder_start_token_id": 2,
|
| 26 |
+
"dropout": 0.1,
|
| 27 |
+
"encoder_attention_heads": 12,
|
| 28 |
+
"encoder_ffn_dim": 3072,
|
| 29 |
+
"encoder_layerdrop": 0.0,
|
| 30 |
+
"encoder_layers": 6,
|
| 31 |
+
"eos_token_id": 2,
|
| 32 |
+
"gradient_checkpointing": false,
|
| 33 |
+
"id2label": {
|
| 34 |
+
"0": "LABEL_0",
|
| 35 |
+
"1": "LABEL_1",
|
| 36 |
+
"2": "LABEL_2"
|
| 37 |
+
},
|
| 38 |
+
"init_std": 0.02,
|
| 39 |
+
"is_encoder_decoder": true,
|
| 40 |
+
"label2id": {
|
| 41 |
+
"LABEL_0": 0,
|
| 42 |
+
"LABEL_1": 1,
|
| 43 |
+
"LABEL_2": 2
|
| 44 |
+
},
|
| 45 |
+
"max_decoder_position_embeddings": 1024,
|
| 46 |
+
"max_encoder_position_embeddings": 4096,
|
| 47 |
+
"model_type": "led",
|
| 48 |
+
"num_hidden_layers": 6,
|
| 49 |
+
"pad_token_id": 1,
|
| 50 |
+
"torch_dtype": "float32",
|
| 51 |
+
"transformers_version": "4.20.0.dev0",
|
| 52 |
+
"use_cache": true,
|
| 53 |
+
"vocab_size": 50266
|
| 54 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 8.9,
|
| 3 |
+
"eval_gen_len": 308.6606,
|
| 4 |
+
"eval_loss": 3.273963212966919,
|
| 5 |
+
"eval_rouge1": 46.2987,
|
| 6 |
+
"eval_rouge2": 18.4863,
|
| 7 |
+
"eval_rougeL": 24.2428,
|
| 8 |
+
"eval_rougeLsum": 42.5102,
|
| 9 |
+
"eval_runtime": 1836.4721,
|
| 10 |
+
"eval_samples": 5622,
|
| 11 |
+
"eval_samples_per_second": 3.061,
|
| 12 |
+
"eval_steps_per_second": 0.192
|
| 13 |
+
}
|
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:e421000729982147d363c96eec0402cb75ea96e03b6a253c9b24dc54e419cb42
|
| 3 |
+
size 609932849
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": true,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"cls_token": {
|
| 10 |
+
"content": "<s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": true,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"eos_token": {
|
| 17 |
+
"content": "</s>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": true,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"mask_token": {
|
| 24 |
+
"content": "<mask>",
|
| 25 |
+
"lstrip": true,
|
| 26 |
+
"normalized": true,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"pad_token": {
|
| 31 |
+
"content": "<pad>",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": true,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
},
|
| 37 |
+
"sep_token": {
|
| 38 |
+
"content": "</s>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": true,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false
|
| 43 |
+
},
|
| 44 |
+
"unk_token": {
|
| 45 |
+
"content": "<unk>",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": true,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false
|
| 50 |
+
}
|
| 51 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,65 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"bos_token": {
|
| 4 |
+
"__type": "AddedToken",
|
| 5 |
+
"content": "<s>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": true,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false
|
| 10 |
+
},
|
| 11 |
+
"cls_token": {
|
| 12 |
+
"__type": "AddedToken",
|
| 13 |
+
"content": "<s>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": true,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false
|
| 18 |
+
},
|
| 19 |
+
"eos_token": {
|
| 20 |
+
"__type": "AddedToken",
|
| 21 |
+
"content": "</s>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": true,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false
|
| 26 |
+
},
|
| 27 |
+
"errors": "replace",
|
| 28 |
+
"mask_token": {
|
| 29 |
+
"__type": "AddedToken",
|
| 30 |
+
"content": "<mask>",
|
| 31 |
+
"lstrip": true,
|
| 32 |
+
"normalized": true,
|
| 33 |
+
"rstrip": false,
|
| 34 |
+
"single_word": false
|
| 35 |
+
},
|
| 36 |
+
"model_max_length": 16384,
|
| 37 |
+
"name_or_path": "/home/hpcpudu1/rds/hpc-work/data/pretrain-mds/led_pretrain/ver2/gen_model/Centrum_pretrain_base_batch_16_21-7-22.1",
|
| 38 |
+
"pad_token": {
|
| 39 |
+
"__type": "AddedToken",
|
| 40 |
+
"content": "<pad>",
|
| 41 |
+
"lstrip": false,
|
| 42 |
+
"normalized": true,
|
| 43 |
+
"rstrip": false,
|
| 44 |
+
"single_word": false
|
| 45 |
+
},
|
| 46 |
+
"sep_token": {
|
| 47 |
+
"__type": "AddedToken",
|
| 48 |
+
"content": "</s>",
|
| 49 |
+
"lstrip": false,
|
| 50 |
+
"normalized": true,
|
| 51 |
+
"rstrip": false,
|
| 52 |
+
"single_word": false
|
| 53 |
+
},
|
| 54 |
+
"special_tokens_map_file": "/home/hpcpudu1/.cache/huggingface/transformers/05da652a7fca41c1c18027c1201e473217bb373e370d1283e3de49d5880cbf0c.cb2244924ab24d706b02fd7fcedaea4531566537687a539ebb94db511fd122a0",
|
| 55 |
+
"tokenizer_class": "LEDTokenizer",
|
| 56 |
+
"trim_offsets": true,
|
| 57 |
+
"unk_token": {
|
| 58 |
+
"__type": "AddedToken",
|
| 59 |
+
"content": "<unk>",
|
| 60 |
+
"lstrip": false,
|
| 61 |
+
"normalized": true,
|
| 62 |
+
"rstrip": false,
|
| 63 |
+
"single_word": false
|
| 64 |
+
}
|
| 65 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 8.9,
|
| 3 |
+
"train_loss": 3.1441598370170594,
|
| 4 |
+
"train_runtime": 61182.0827,
|
| 5 |
+
"train_samples": 44972,
|
| 6 |
+
"train_samples_per_second": 6.538,
|
| 7 |
+
"train_steps_per_second": 0.409
|
| 8 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,2064 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 24.366,
|
| 3 |
+
"best_model_checkpoint": "/home/hpcpudu1/rds/hpc-work/data/pretrain-mds/led_pretrain/ver2/gen_model/Centrum_base_multinews_23-7-22.2/checkpoint-23000",
|
| 4 |
+
"epoch": 8.896557858222895,
|
| 5 |
+
"global_step": 25000,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.0,
|
| 12 |
+
"learning_rate": 1.2000000000000002e-08,
|
| 13 |
+
"loss": 3.7881,
|
| 14 |
+
"step": 1
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.04,
|
| 18 |
+
"learning_rate": 1.2000000000000002e-06,
|
| 19 |
+
"loss": 3.5568,
|
| 20 |
+
"step": 100
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.07,
|
| 24 |
+
"learning_rate": 2.4000000000000003e-06,
|
| 25 |
+
"loss": 3.5213,
|
| 26 |
+
"step": 200
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.11,
|
| 30 |
+
"learning_rate": 3.6e-06,
|
| 31 |
+
"loss": 3.49,
|
| 32 |
+
"step": 300
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.14,
|
| 36 |
+
"learning_rate": 4.800000000000001e-06,
|
| 37 |
+
"loss": 3.4612,
|
| 38 |
+
"step": 400
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.18,
|
| 42 |
+
"learning_rate": 6e-06,
|
| 43 |
+
"loss": 3.4476,
|
| 44 |
+
"step": 500
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.21,
|
| 48 |
+
"learning_rate": 7.2e-06,
|
| 49 |
+
"loss": 3.4241,
|
| 50 |
+
"step": 600
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.25,
|
| 54 |
+
"learning_rate": 8.400000000000001e-06,
|
| 55 |
+
"loss": 3.4164,
|
| 56 |
+
"step": 700
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.28,
|
| 60 |
+
"learning_rate": 9.600000000000001e-06,
|
| 61 |
+
"loss": 3.4208,
|
| 62 |
+
"step": 800
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.32,
|
| 66 |
+
"learning_rate": 1.08e-05,
|
| 67 |
+
"loss": 3.4008,
|
| 68 |
+
"step": 900
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.36,
|
| 72 |
+
"learning_rate": 1.2e-05,
|
| 73 |
+
"loss": 3.4391,
|
| 74 |
+
"step": 1000
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.39,
|
| 78 |
+
"learning_rate": 1.32e-05,
|
| 79 |
+
"loss": 3.3908,
|
| 80 |
+
"step": 1100
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.43,
|
| 84 |
+
"learning_rate": 1.44e-05,
|
| 85 |
+
"loss": 3.3961,
|
| 86 |
+
"step": 1200
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.46,
|
| 90 |
+
"learning_rate": 1.56e-05,
|
| 91 |
+
"loss": 3.4042,
|
| 92 |
+
"step": 1300
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 0.5,
|
| 96 |
+
"learning_rate": 1.6800000000000002e-05,
|
| 97 |
+
"loss": 3.3847,
|
| 98 |
+
"step": 1400
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.53,
|
| 102 |
+
"learning_rate": 1.8e-05,
|
| 103 |
+
"loss": 3.3763,
|
| 104 |
+
"step": 1500
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 0.57,
|
| 108 |
+
"learning_rate": 1.9200000000000003e-05,
|
| 109 |
+
"loss": 3.3873,
|
| 110 |
+
"step": 1600
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 0.6,
|
| 114 |
+
"learning_rate": 2.04e-05,
|
| 115 |
+
"loss": 3.3817,
|
| 116 |
+
"step": 1700
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.64,
|
| 120 |
+
"learning_rate": 2.16e-05,
|
| 121 |
+
"loss": 3.363,
|
| 122 |
+
"step": 1800
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.68,
|
| 126 |
+
"learning_rate": 2.2800000000000002e-05,
|
| 127 |
+
"loss": 3.3631,
|
| 128 |
+
"step": 1900
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.71,
|
| 132 |
+
"learning_rate": 2.4e-05,
|
| 133 |
+
"loss": 3.3734,
|
| 134 |
+
"step": 2000
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 0.75,
|
| 138 |
+
"learning_rate": 2.52e-05,
|
| 139 |
+
"loss": 3.3414,
|
| 140 |
+
"step": 2100
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 0.78,
|
| 144 |
+
"learning_rate": 2.64e-05,
|
| 145 |
+
"loss": 3.384,
|
| 146 |
+
"step": 2200
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 0.82,
|
| 150 |
+
"learning_rate": 2.7600000000000003e-05,
|
| 151 |
+
"loss": 3.3718,
|
| 152 |
+
"step": 2300
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 0.85,
|
| 156 |
+
"learning_rate": 2.88e-05,
|
| 157 |
+
"loss": 3.3669,
|
| 158 |
+
"step": 2400
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 0.89,
|
| 162 |
+
"learning_rate": 3e-05,
|
| 163 |
+
"loss": 3.3649,
|
| 164 |
+
"step": 2500
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.93,
|
| 168 |
+
"learning_rate": 2.9866666666666666e-05,
|
| 169 |
+
"loss": 3.3537,
|
| 170 |
+
"step": 2600
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.96,
|
| 174 |
+
"learning_rate": 2.9733333333333336e-05,
|
| 175 |
+
"loss": 3.393,
|
| 176 |
+
"step": 2700
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 1.0,
|
| 180 |
+
"learning_rate": 2.96e-05,
|
| 181 |
+
"loss": 3.3729,
|
| 182 |
+
"step": 2800
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 1.03,
|
| 186 |
+
"learning_rate": 2.9466666666666667e-05,
|
| 187 |
+
"loss": 3.3593,
|
| 188 |
+
"step": 2900
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 1.07,
|
| 192 |
+
"learning_rate": 2.9333333333333333e-05,
|
| 193 |
+
"loss": 3.3256,
|
| 194 |
+
"step": 3000
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 1.1,
|
| 198 |
+
"learning_rate": 2.92e-05,
|
| 199 |
+
"loss": 3.2975,
|
| 200 |
+
"step": 3100
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 1.14,
|
| 204 |
+
"learning_rate": 2.9066666666666667e-05,
|
| 205 |
+
"loss": 3.3259,
|
| 206 |
+
"step": 3200
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 1.17,
|
| 210 |
+
"learning_rate": 2.8933333333333333e-05,
|
| 211 |
+
"loss": 3.3079,
|
| 212 |
+
"step": 3300
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 1.21,
|
| 216 |
+
"learning_rate": 2.88e-05,
|
| 217 |
+
"loss": 3.302,
|
| 218 |
+
"step": 3400
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 1.25,
|
| 222 |
+
"learning_rate": 2.8666666666666668e-05,
|
| 223 |
+
"loss": 3.2971,
|
| 224 |
+
"step": 3500
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 1.28,
|
| 228 |
+
"learning_rate": 2.8533333333333333e-05,
|
| 229 |
+
"loss": 3.3297,
|
| 230 |
+
"step": 3600
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 1.32,
|
| 234 |
+
"learning_rate": 2.84e-05,
|
| 235 |
+
"loss": 3.3068,
|
| 236 |
+
"step": 3700
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 1.35,
|
| 240 |
+
"learning_rate": 2.8268e-05,
|
| 241 |
+
"loss": 3.31,
|
| 242 |
+
"step": 3800
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 1.39,
|
| 246 |
+
"learning_rate": 2.8134666666666667e-05,
|
| 247 |
+
"loss": 3.2908,
|
| 248 |
+
"step": 3900
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 1.42,
|
| 252 |
+
"learning_rate": 2.8001333333333332e-05,
|
| 253 |
+
"loss": 3.2954,
|
| 254 |
+
"step": 4000
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 1.46,
|
| 258 |
+
"learning_rate": 2.7868e-05,
|
| 259 |
+
"loss": 3.3029,
|
| 260 |
+
"step": 4100
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 1.49,
|
| 264 |
+
"learning_rate": 2.7734666666666667e-05,
|
| 265 |
+
"loss": 3.3064,
|
| 266 |
+
"step": 4200
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 1.53,
|
| 270 |
+
"learning_rate": 2.7601333333333333e-05,
|
| 271 |
+
"loss": 3.2857,
|
| 272 |
+
"step": 4300
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 1.57,
|
| 276 |
+
"learning_rate": 2.7468e-05,
|
| 277 |
+
"loss": 3.2781,
|
| 278 |
+
"step": 4400
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 1.6,
|
| 282 |
+
"learning_rate": 2.7334666666666668e-05,
|
| 283 |
+
"loss": 3.3019,
|
| 284 |
+
"step": 4500
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 1.64,
|
| 288 |
+
"learning_rate": 2.7201333333333333e-05,
|
| 289 |
+
"loss": 3.2978,
|
| 290 |
+
"step": 4600
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 1.67,
|
| 294 |
+
"learning_rate": 2.7068e-05,
|
| 295 |
+
"loss": 3.3186,
|
| 296 |
+
"step": 4700
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 1.71,
|
| 300 |
+
"learning_rate": 2.6934666666666665e-05,
|
| 301 |
+
"loss": 3.2843,
|
| 302 |
+
"step": 4800
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 1.74,
|
| 306 |
+
"learning_rate": 2.6801333333333334e-05,
|
| 307 |
+
"loss": 3.2863,
|
| 308 |
+
"step": 4900
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 1.78,
|
| 312 |
+
"learning_rate": 2.6668000000000003e-05,
|
| 313 |
+
"loss": 3.2702,
|
| 314 |
+
"step": 5000
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 1.78,
|
| 318 |
+
"eval_gen_len": 277.1855,
|
| 319 |
+
"eval_loss": 3.2853293418884277,
|
| 320 |
+
"eval_rouge1": 44.0203,
|
| 321 |
+
"eval_rouge2": 16.6061,
|
| 322 |
+
"eval_rougeL": 23.3846,
|
| 323 |
+
"eval_rougeLsum": 40.3853,
|
| 324 |
+
"eval_runtime": 1402.4156,
|
| 325 |
+
"eval_samples_per_second": 4.009,
|
| 326 |
+
"eval_steps_per_second": 0.251,
|
| 327 |
+
"step": 5000
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 1.81,
|
| 331 |
+
"learning_rate": 2.653466666666667e-05,
|
| 332 |
+
"loss": 3.3022,
|
| 333 |
+
"step": 5100
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 1.85,
|
| 337 |
+
"learning_rate": 2.6401333333333334e-05,
|
| 338 |
+
"loss": 3.29,
|
| 339 |
+
"step": 5200
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 1.89,
|
| 343 |
+
"learning_rate": 2.6268000000000003e-05,
|
| 344 |
+
"loss": 3.2893,
|
| 345 |
+
"step": 5300
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 1.92,
|
| 349 |
+
"learning_rate": 2.613466666666667e-05,
|
| 350 |
+
"loss": 3.2849,
|
| 351 |
+
"step": 5400
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 1.96,
|
| 355 |
+
"learning_rate": 2.6001333333333335e-05,
|
| 356 |
+
"loss": 3.2762,
|
| 357 |
+
"step": 5500
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 1.96,
|
| 361 |
+
"eval_gen_len": 288.4173,
|
| 362 |
+
"eval_loss": 3.2852535247802734,
|
| 363 |
+
"eval_rouge1": 44.725,
|
| 364 |
+
"eval_rouge2": 16.9262,
|
| 365 |
+
"eval_rougeL": 23.475,
|
| 366 |
+
"eval_rougeLsum": 41.0003,
|
| 367 |
+
"eval_runtime": 1344.5644,
|
| 368 |
+
"eval_samples_per_second": 4.181,
|
| 369 |
+
"eval_steps_per_second": 0.262,
|
| 370 |
+
"step": 5500
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"epoch": 1.99,
|
| 374 |
+
"learning_rate": 2.5868e-05,
|
| 375 |
+
"loss": 3.2937,
|
| 376 |
+
"step": 5600
|
| 377 |
+
},
|
| 378 |
+
{
|
| 379 |
+
"epoch": 2.03,
|
| 380 |
+
"learning_rate": 2.573466666666667e-05,
|
| 381 |
+
"loss": 3.2614,
|
| 382 |
+
"step": 5700
|
| 383 |
+
},
|
| 384 |
+
{
|
| 385 |
+
"epoch": 2.06,
|
| 386 |
+
"learning_rate": 2.5601333333333335e-05,
|
| 387 |
+
"loss": 3.1995,
|
| 388 |
+
"step": 5800
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 2.1,
|
| 392 |
+
"learning_rate": 2.5468e-05,
|
| 393 |
+
"loss": 3.2162,
|
| 394 |
+
"step": 5900
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 2.14,
|
| 398 |
+
"learning_rate": 2.5334666666666666e-05,
|
| 399 |
+
"loss": 3.2114,
|
| 400 |
+
"step": 6000
|
| 401 |
+
},
|
| 402 |
+
{
|
| 403 |
+
"epoch": 2.14,
|
| 404 |
+
"eval_gen_len": 257.2761,
|
| 405 |
+
"eval_loss": 3.2857086658477783,
|
| 406 |
+
"eval_rouge1": 44.6456,
|
| 407 |
+
"eval_rouge2": 17.0245,
|
| 408 |
+
"eval_rougeL": 23.7328,
|
| 409 |
+
"eval_rougeLsum": 40.9131,
|
| 410 |
+
"eval_runtime": 1239.4823,
|
| 411 |
+
"eval_samples_per_second": 4.536,
|
| 412 |
+
"eval_steps_per_second": 0.284,
|
| 413 |
+
"step": 6000
|
| 414 |
+
},
|
| 415 |
+
{
|
| 416 |
+
"epoch": 2.17,
|
| 417 |
+
"learning_rate": 2.5201333333333336e-05,
|
| 418 |
+
"loss": 3.202,
|
| 419 |
+
"step": 6100
|
| 420 |
+
},
|
| 421 |
+
{
|
| 422 |
+
"epoch": 2.21,
|
| 423 |
+
"learning_rate": 2.5068e-05,
|
| 424 |
+
"loss": 3.2089,
|
| 425 |
+
"step": 6200
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 2.24,
|
| 429 |
+
"learning_rate": 2.4934666666666667e-05,
|
| 430 |
+
"loss": 3.2109,
|
| 431 |
+
"step": 6300
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 2.28,
|
| 435 |
+
"learning_rate": 2.4801333333333333e-05,
|
| 436 |
+
"loss": 3.2073,
|
| 437 |
+
"step": 6400
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 2.31,
|
| 441 |
+
"learning_rate": 2.4668e-05,
|
| 442 |
+
"loss": 3.1981,
|
| 443 |
+
"step": 6500
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 2.31,
|
| 447 |
+
"eval_gen_len": 254.8618,
|
| 448 |
+
"eval_loss": 3.2817349433898926,
|
| 449 |
+
"eval_rouge1": 44.7869,
|
| 450 |
+
"eval_rouge2": 17.0849,
|
| 451 |
+
"eval_rougeL": 23.8372,
|
| 452 |
+
"eval_rougeLsum": 41.0669,
|
| 453 |
+
"eval_runtime": 1197.7293,
|
| 454 |
+
"eval_samples_per_second": 4.694,
|
| 455 |
+
"eval_steps_per_second": 0.294,
|
| 456 |
+
"step": 6500
|
| 457 |
+
},
|
| 458 |
+
{
|
| 459 |
+
"epoch": 2.35,
|
| 460 |
+
"learning_rate": 2.4534666666666667e-05,
|
| 461 |
+
"loss": 3.2258,
|
| 462 |
+
"step": 6600
|
| 463 |
+
},
|
| 464 |
+
{
|
| 465 |
+
"epoch": 2.38,
|
| 466 |
+
"learning_rate": 2.4401333333333333e-05,
|
| 467 |
+
"loss": 3.2252,
|
| 468 |
+
"step": 6700
|
| 469 |
+
},
|
| 470 |
+
{
|
| 471 |
+
"epoch": 2.42,
|
| 472 |
+
"learning_rate": 2.4268e-05,
|
| 473 |
+
"loss": 3.2252,
|
| 474 |
+
"step": 6800
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 2.46,
|
| 478 |
+
"learning_rate": 2.4134666666666668e-05,
|
| 479 |
+
"loss": 3.2218,
|
| 480 |
+
"step": 6900
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 2.49,
|
| 484 |
+
"learning_rate": 2.4001333333333333e-05,
|
| 485 |
+
"loss": 3.2298,
|
| 486 |
+
"step": 7000
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 2.49,
|
| 490 |
+
"eval_gen_len": 263.0854,
|
| 491 |
+
"eval_loss": 3.2801525592803955,
|
| 492 |
+
"eval_rouge1": 45.2657,
|
| 493 |
+
"eval_rouge2": 17.2618,
|
| 494 |
+
"eval_rougeL": 23.8204,
|
| 495 |
+
"eval_rougeLsum": 41.5807,
|
| 496 |
+
"eval_runtime": 1199.3644,
|
| 497 |
+
"eval_samples_per_second": 4.687,
|
| 498 |
+
"eval_steps_per_second": 0.293,
|
| 499 |
+
"step": 7000
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 2.53,
|
| 503 |
+
"learning_rate": 2.3868e-05,
|
| 504 |
+
"loss": 3.206,
|
| 505 |
+
"step": 7100
|
| 506 |
+
},
|
| 507 |
+
{
|
| 508 |
+
"epoch": 2.56,
|
| 509 |
+
"learning_rate": 2.3734666666666665e-05,
|
| 510 |
+
"loss": 3.2062,
|
| 511 |
+
"step": 7200
|
| 512 |
+
},
|
| 513 |
+
{
|
| 514 |
+
"epoch": 2.6,
|
| 515 |
+
"learning_rate": 2.3601333333333334e-05,
|
| 516 |
+
"loss": 3.2241,
|
| 517 |
+
"step": 7300
|
| 518 |
+
},
|
| 519 |
+
{
|
| 520 |
+
"epoch": 2.63,
|
| 521 |
+
"learning_rate": 2.3468e-05,
|
| 522 |
+
"loss": 3.2116,
|
| 523 |
+
"step": 7400
|
| 524 |
+
},
|
| 525 |
+
{
|
| 526 |
+
"epoch": 2.67,
|
| 527 |
+
"learning_rate": 2.3334666666666665e-05,
|
| 528 |
+
"loss": 3.2167,
|
| 529 |
+
"step": 7500
|
| 530 |
+
},
|
| 531 |
+
{
|
| 532 |
+
"epoch": 2.67,
|
| 533 |
+
"eval_gen_len": 244.6939,
|
| 534 |
+
"eval_loss": 3.2773149013519287,
|
| 535 |
+
"eval_rouge1": 44.9516,
|
| 536 |
+
"eval_rouge2": 17.0538,
|
| 537 |
+
"eval_rougeL": 23.7894,
|
| 538 |
+
"eval_rougeLsum": 41.1673,
|
| 539 |
+
"eval_runtime": 1137.295,
|
| 540 |
+
"eval_samples_per_second": 4.943,
|
| 541 |
+
"eval_steps_per_second": 0.31,
|
| 542 |
+
"step": 7500
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 2.7,
|
| 546 |
+
"learning_rate": 2.3201333333333334e-05,
|
| 547 |
+
"loss": 3.219,
|
| 548 |
+
"step": 7600
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 2.74,
|
| 552 |
+
"learning_rate": 2.3068e-05,
|
| 553 |
+
"loss": 3.2057,
|
| 554 |
+
"step": 7700
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 2.78,
|
| 558 |
+
"learning_rate": 2.2936e-05,
|
| 559 |
+
"loss": 3.2029,
|
| 560 |
+
"step": 7800
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 2.81,
|
| 564 |
+
"learning_rate": 2.2802666666666668e-05,
|
| 565 |
+
"loss": 3.2395,
|
| 566 |
+
"step": 7900
|
| 567 |
+
},
|
| 568 |
+
{
|
| 569 |
+
"epoch": 2.85,
|
| 570 |
+
"learning_rate": 2.2669333333333333e-05,
|
| 571 |
+
"loss": 3.2069,
|
| 572 |
+
"step": 8000
|
| 573 |
+
},
|
| 574 |
+
{
|
| 575 |
+
"epoch": 2.85,
|
| 576 |
+
"eval_gen_len": 245.4036,
|
| 577 |
+
"eval_loss": 3.2712182998657227,
|
| 578 |
+
"eval_rouge1": 45.2153,
|
| 579 |
+
"eval_rouge2": 17.2766,
|
| 580 |
+
"eval_rougeL": 23.9883,
|
| 581 |
+
"eval_rougeLsum": 41.4558,
|
| 582 |
+
"eval_runtime": 1117.2186,
|
| 583 |
+
"eval_samples_per_second": 5.032,
|
| 584 |
+
"eval_steps_per_second": 0.315,
|
| 585 |
+
"step": 8000
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 2.88,
|
| 589 |
+
"learning_rate": 2.2536e-05,
|
| 590 |
+
"loss": 3.2034,
|
| 591 |
+
"step": 8100
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 2.92,
|
| 595 |
+
"learning_rate": 2.2402666666666665e-05,
|
| 596 |
+
"loss": 3.2163,
|
| 597 |
+
"step": 8200
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 2.95,
|
| 601 |
+
"learning_rate": 2.2269333333333334e-05,
|
| 602 |
+
"loss": 3.2158,
|
| 603 |
+
"step": 8300
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 2.99,
|
| 607 |
+
"learning_rate": 2.2136e-05,
|
| 608 |
+
"loss": 3.2205,
|
| 609 |
+
"step": 8400
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 3.02,
|
| 613 |
+
"learning_rate": 2.2002666666666665e-05,
|
| 614 |
+
"loss": 3.1822,
|
| 615 |
+
"step": 8500
|
| 616 |
+
},
|
| 617 |
+
{
|
| 618 |
+
"epoch": 3.02,
|
| 619 |
+
"eval_gen_len": 254.6624,
|
| 620 |
+
"eval_loss": 3.2785804271698,
|
| 621 |
+
"eval_rouge1": 45.4747,
|
| 622 |
+
"eval_rouge2": 17.6754,
|
| 623 |
+
"eval_rougeL": 24.1878,
|
| 624 |
+
"eval_rougeLsum": 41.7304,
|
| 625 |
+
"eval_runtime": 1171.0921,
|
| 626 |
+
"eval_samples_per_second": 4.801,
|
| 627 |
+
"eval_steps_per_second": 0.301,
|
| 628 |
+
"step": 8500
|
| 629 |
+
},
|
| 630 |
+
{
|
| 631 |
+
"epoch": 3.06,
|
| 632 |
+
"learning_rate": 2.186933333333333e-05,
|
| 633 |
+
"loss": 3.1397,
|
| 634 |
+
"step": 8600
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 3.1,
|
| 638 |
+
"learning_rate": 2.1736e-05,
|
| 639 |
+
"loss": 3.1659,
|
| 640 |
+
"step": 8700
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 3.13,
|
| 644 |
+
"learning_rate": 2.1602666666666666e-05,
|
| 645 |
+
"loss": 3.1318,
|
| 646 |
+
"step": 8800
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 3.17,
|
| 650 |
+
"learning_rate": 2.1469333333333335e-05,
|
| 651 |
+
"loss": 3.162,
|
| 652 |
+
"step": 8900
|
| 653 |
+
},
|
| 654 |
+
{
|
| 655 |
+
"epoch": 3.2,
|
| 656 |
+
"learning_rate": 2.1336000000000004e-05,
|
| 657 |
+
"loss": 3.1529,
|
| 658 |
+
"step": 9000
|
| 659 |
+
},
|
| 660 |
+
{
|
| 661 |
+
"epoch": 3.2,
|
| 662 |
+
"eval_gen_len": 246.0157,
|
| 663 |
+
"eval_loss": 3.2740354537963867,
|
| 664 |
+
"eval_rouge1": 44.9033,
|
| 665 |
+
"eval_rouge2": 17.1386,
|
| 666 |
+
"eval_rougeL": 23.8511,
|
| 667 |
+
"eval_rougeLsum": 41.177,
|
| 668 |
+
"eval_runtime": 1185.3803,
|
| 669 |
+
"eval_samples_per_second": 4.743,
|
| 670 |
+
"eval_steps_per_second": 0.297,
|
| 671 |
+
"step": 9000
|
| 672 |
+
},
|
| 673 |
+
{
|
| 674 |
+
"epoch": 3.24,
|
| 675 |
+
"learning_rate": 2.120266666666667e-05,
|
| 676 |
+
"loss": 3.1241,
|
| 677 |
+
"step": 9100
|
| 678 |
+
},
|
| 679 |
+
{
|
| 680 |
+
"epoch": 3.27,
|
| 681 |
+
"learning_rate": 2.1069333333333335e-05,
|
| 682 |
+
"loss": 3.1537,
|
| 683 |
+
"step": 9200
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 3.31,
|
| 687 |
+
"learning_rate": 2.0936e-05,
|
| 688 |
+
"loss": 3.1589,
|
| 689 |
+
"step": 9300
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 3.35,
|
| 693 |
+
"learning_rate": 2.080266666666667e-05,
|
| 694 |
+
"loss": 3.1415,
|
| 695 |
+
"step": 9400
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 3.38,
|
| 699 |
+
"learning_rate": 2.0669333333333336e-05,
|
| 700 |
+
"loss": 3.1407,
|
| 701 |
+
"step": 9500
|
| 702 |
+
},
|
| 703 |
+
{
|
| 704 |
+
"epoch": 3.38,
|
| 705 |
+
"eval_gen_len": 243.4922,
|
| 706 |
+
"eval_loss": 3.270354986190796,
|
| 707 |
+
"eval_rouge1": 45.1045,
|
| 708 |
+
"eval_rouge2": 17.2335,
|
| 709 |
+
"eval_rougeL": 23.9124,
|
| 710 |
+
"eval_rougeLsum": 41.3243,
|
| 711 |
+
"eval_runtime": 1159.3428,
|
| 712 |
+
"eval_samples_per_second": 4.849,
|
| 713 |
+
"eval_steps_per_second": 0.304,
|
| 714 |
+
"step": 9500
|
| 715 |
+
},
|
| 716 |
+
{
|
| 717 |
+
"epoch": 3.42,
|
| 718 |
+
"learning_rate": 2.0536e-05,
|
| 719 |
+
"loss": 3.149,
|
| 720 |
+
"step": 9600
|
| 721 |
+
},
|
| 722 |
+
{
|
| 723 |
+
"epoch": 3.45,
|
| 724 |
+
"learning_rate": 2.0402666666666667e-05,
|
| 725 |
+
"loss": 3.1539,
|
| 726 |
+
"step": 9700
|
| 727 |
+
},
|
| 728 |
+
{
|
| 729 |
+
"epoch": 3.49,
|
| 730 |
+
"learning_rate": 2.027066666666667e-05,
|
| 731 |
+
"loss": 3.1539,
|
| 732 |
+
"step": 9800
|
| 733 |
+
},
|
| 734 |
+
{
|
| 735 |
+
"epoch": 3.52,
|
| 736 |
+
"learning_rate": 2.0137333333333335e-05,
|
| 737 |
+
"loss": 3.158,
|
| 738 |
+
"step": 9900
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 3.56,
|
| 742 |
+
"learning_rate": 2.0004e-05,
|
| 743 |
+
"loss": 3.1376,
|
| 744 |
+
"step": 10000
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 3.56,
|
| 748 |
+
"eval_gen_len": 243.8396,
|
| 749 |
+
"eval_loss": 3.272122621536255,
|
| 750 |
+
"eval_rouge1": 45.2694,
|
| 751 |
+
"eval_rouge2": 17.4797,
|
| 752 |
+
"eval_rougeL": 24.1072,
|
| 753 |
+
"eval_rougeLsum": 41.5441,
|
| 754 |
+
"eval_runtime": 1143.3015,
|
| 755 |
+
"eval_samples_per_second": 4.917,
|
| 756 |
+
"eval_steps_per_second": 0.308,
|
| 757 |
+
"step": 10000
|
| 758 |
+
},
|
| 759 |
+
{
|
| 760 |
+
"epoch": 3.59,
|
| 761 |
+
"learning_rate": 1.987066666666667e-05,
|
| 762 |
+
"loss": 3.1475,
|
| 763 |
+
"step": 10100
|
| 764 |
+
},
|
| 765 |
+
{
|
| 766 |
+
"epoch": 3.63,
|
| 767 |
+
"learning_rate": 1.9737333333333335e-05,
|
| 768 |
+
"loss": 3.1553,
|
| 769 |
+
"step": 10200
|
| 770 |
+
},
|
| 771 |
+
{
|
| 772 |
+
"epoch": 3.67,
|
| 773 |
+
"learning_rate": 1.9604e-05,
|
| 774 |
+
"loss": 3.1589,
|
| 775 |
+
"step": 10300
|
| 776 |
+
},
|
| 777 |
+
{
|
| 778 |
+
"epoch": 3.7,
|
| 779 |
+
"learning_rate": 1.9470666666666666e-05,
|
| 780 |
+
"loss": 3.1712,
|
| 781 |
+
"step": 10400
|
| 782 |
+
},
|
| 783 |
+
{
|
| 784 |
+
"epoch": 3.74,
|
| 785 |
+
"learning_rate": 1.9337333333333335e-05,
|
| 786 |
+
"loss": 3.1545,
|
| 787 |
+
"step": 10500
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"epoch": 3.74,
|
| 791 |
+
"eval_gen_len": 231.1805,
|
| 792 |
+
"eval_loss": 3.271965503692627,
|
| 793 |
+
"eval_rouge1": 45.3105,
|
| 794 |
+
"eval_rouge2": 17.6338,
|
| 795 |
+
"eval_rougeL": 24.1547,
|
| 796 |
+
"eval_rougeLsum": 41.5731,
|
| 797 |
+
"eval_runtime": 1051.5864,
|
| 798 |
+
"eval_samples_per_second": 5.346,
|
| 799 |
+
"eval_steps_per_second": 0.335,
|
| 800 |
+
"step": 10500
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 3.77,
|
| 804 |
+
"learning_rate": 1.9204e-05,
|
| 805 |
+
"loss": 3.1598,
|
| 806 |
+
"step": 10600
|
| 807 |
+
},
|
| 808 |
+
{
|
| 809 |
+
"epoch": 3.81,
|
| 810 |
+
"learning_rate": 1.9070666666666667e-05,
|
| 811 |
+
"loss": 3.1684,
|
| 812 |
+
"step": 10700
|
| 813 |
+
},
|
| 814 |
+
{
|
| 815 |
+
"epoch": 3.84,
|
| 816 |
+
"learning_rate": 1.8937333333333336e-05,
|
| 817 |
+
"loss": 3.1703,
|
| 818 |
+
"step": 10800
|
| 819 |
+
},
|
| 820 |
+
{
|
| 821 |
+
"epoch": 3.88,
|
| 822 |
+
"learning_rate": 1.8804e-05,
|
| 823 |
+
"loss": 3.1506,
|
| 824 |
+
"step": 10900
|
| 825 |
+
},
|
| 826 |
+
{
|
| 827 |
+
"epoch": 3.91,
|
| 828 |
+
"learning_rate": 1.8670666666666667e-05,
|
| 829 |
+
"loss": 3.1307,
|
| 830 |
+
"step": 11000
|
| 831 |
+
},
|
| 832 |
+
{
|
| 833 |
+
"epoch": 3.91,
|
| 834 |
+
"eval_gen_len": 250.1039,
|
| 835 |
+
"eval_loss": 3.268434524536133,
|
| 836 |
+
"eval_rouge1": 45.4309,
|
| 837 |
+
"eval_rouge2": 17.2665,
|
| 838 |
+
"eval_rougeL": 23.8954,
|
| 839 |
+
"eval_rougeLsum": 41.6518,
|
| 840 |
+
"eval_runtime": 1131.5203,
|
| 841 |
+
"eval_samples_per_second": 4.969,
|
| 842 |
+
"eval_steps_per_second": 0.311,
|
| 843 |
+
"step": 11000
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 3.95,
|
| 847 |
+
"learning_rate": 1.8537333333333333e-05,
|
| 848 |
+
"loss": 3.1651,
|
| 849 |
+
"step": 11100
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 3.99,
|
| 853 |
+
"learning_rate": 1.8404000000000002e-05,
|
| 854 |
+
"loss": 3.1617,
|
| 855 |
+
"step": 11200
|
| 856 |
+
},
|
| 857 |
+
{
|
| 858 |
+
"epoch": 4.02,
|
| 859 |
+
"learning_rate": 1.8270666666666668e-05,
|
| 860 |
+
"loss": 3.1417,
|
| 861 |
+
"step": 11300
|
| 862 |
+
},
|
| 863 |
+
{
|
| 864 |
+
"epoch": 4.06,
|
| 865 |
+
"learning_rate": 1.8137333333333333e-05,
|
| 866 |
+
"loss": 3.0753,
|
| 867 |
+
"step": 11400
|
| 868 |
+
},
|
| 869 |
+
{
|
| 870 |
+
"epoch": 4.09,
|
| 871 |
+
"learning_rate": 1.8004e-05,
|
| 872 |
+
"loss": 3.1022,
|
| 873 |
+
"step": 11500
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 4.09,
|
| 877 |
+
"eval_gen_len": 242.5923,
|
| 878 |
+
"eval_loss": 3.271904468536377,
|
| 879 |
+
"eval_rouge1": 45.1959,
|
| 880 |
+
"eval_rouge2": 17.4017,
|
| 881 |
+
"eval_rougeL": 24.056,
|
| 882 |
+
"eval_rougeLsum": 41.5363,
|
| 883 |
+
"eval_runtime": 1125.9262,
|
| 884 |
+
"eval_samples_per_second": 4.993,
|
| 885 |
+
"eval_steps_per_second": 0.313,
|
| 886 |
+
"step": 11500
|
| 887 |
+
},
|
| 888 |
+
{
|
| 889 |
+
"epoch": 4.13,
|
| 890 |
+
"learning_rate": 1.7870666666666668e-05,
|
| 891 |
+
"loss": 3.0868,
|
| 892 |
+
"step": 11600
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 4.16,
|
| 896 |
+
"learning_rate": 1.7737333333333334e-05,
|
| 897 |
+
"loss": 3.1109,
|
| 898 |
+
"step": 11700
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 4.2,
|
| 902 |
+
"learning_rate": 1.7605333333333332e-05,
|
| 903 |
+
"loss": 3.0823,
|
| 904 |
+
"step": 11800
|
| 905 |
+
},
|
| 906 |
+
{
|
| 907 |
+
"epoch": 4.23,
|
| 908 |
+
"learning_rate": 1.7472e-05,
|
| 909 |
+
"loss": 3.0932,
|
| 910 |
+
"step": 11900
|
| 911 |
+
},
|
| 912 |
+
{
|
| 913 |
+
"epoch": 4.27,
|
| 914 |
+
"learning_rate": 1.7338666666666667e-05,
|
| 915 |
+
"loss": 3.1139,
|
| 916 |
+
"step": 12000
|
| 917 |
+
},
|
| 918 |
+
{
|
| 919 |
+
"epoch": 4.27,
|
| 920 |
+
"eval_gen_len": 240.5701,
|
| 921 |
+
"eval_loss": 3.27105712890625,
|
| 922 |
+
"eval_rouge1": 45.3864,
|
| 923 |
+
"eval_rouge2": 17.4653,
|
| 924 |
+
"eval_rougeL": 24.028,
|
| 925 |
+
"eval_rougeLsum": 41.6797,
|
| 926 |
+
"eval_runtime": 1097.9204,
|
| 927 |
+
"eval_samples_per_second": 5.121,
|
| 928 |
+
"eval_steps_per_second": 0.321,
|
| 929 |
+
"step": 12000
|
| 930 |
+
},
|
| 931 |
+
{
|
| 932 |
+
"epoch": 4.31,
|
| 933 |
+
"learning_rate": 1.7205333333333333e-05,
|
| 934 |
+
"loss": 3.1077,
|
| 935 |
+
"step": 12100
|
| 936 |
+
},
|
| 937 |
+
{
|
| 938 |
+
"epoch": 4.34,
|
| 939 |
+
"learning_rate": 1.7072000000000002e-05,
|
| 940 |
+
"loss": 3.1018,
|
| 941 |
+
"step": 12200
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 4.38,
|
| 945 |
+
"learning_rate": 1.6938666666666668e-05,
|
| 946 |
+
"loss": 3.1089,
|
| 947 |
+
"step": 12300
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 4.41,
|
| 951 |
+
"learning_rate": 1.6805333333333333e-05,
|
| 952 |
+
"loss": 3.0964,
|
| 953 |
+
"step": 12400
|
| 954 |
+
},
|
| 955 |
+
{
|
| 956 |
+
"epoch": 4.45,
|
| 957 |
+
"learning_rate": 1.6672e-05,
|
| 958 |
+
"loss": 3.0978,
|
| 959 |
+
"step": 12500
|
| 960 |
+
},
|
| 961 |
+
{
|
| 962 |
+
"epoch": 4.45,
|
| 963 |
+
"eval_gen_len": 232.1149,
|
| 964 |
+
"eval_loss": 3.2721784114837646,
|
| 965 |
+
"eval_rouge1": 45.5694,
|
| 966 |
+
"eval_rouge2": 17.501,
|
| 967 |
+
"eval_rougeL": 24.1452,
|
| 968 |
+
"eval_rougeLsum": 41.7894,
|
| 969 |
+
"eval_runtime": 1018.4617,
|
| 970 |
+
"eval_samples_per_second": 5.52,
|
| 971 |
+
"eval_steps_per_second": 0.346,
|
| 972 |
+
"step": 12500
|
| 973 |
+
},
|
| 974 |
+
{
|
| 975 |
+
"epoch": 4.48,
|
| 976 |
+
"learning_rate": 1.6538666666666668e-05,
|
| 977 |
+
"loss": 3.0998,
|
| 978 |
+
"step": 12600
|
| 979 |
+
},
|
| 980 |
+
{
|
| 981 |
+
"epoch": 4.52,
|
| 982 |
+
"learning_rate": 1.6405333333333334e-05,
|
| 983 |
+
"loss": 3.1115,
|
| 984 |
+
"step": 12700
|
| 985 |
+
},
|
| 986 |
+
{
|
| 987 |
+
"epoch": 4.56,
|
| 988 |
+
"learning_rate": 1.6272e-05,
|
| 989 |
+
"loss": 3.1083,
|
| 990 |
+
"step": 12800
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 4.59,
|
| 994 |
+
"learning_rate": 1.6138666666666665e-05,
|
| 995 |
+
"loss": 3.1112,
|
| 996 |
+
"step": 12900
|
| 997 |
+
},
|
| 998 |
+
{
|
| 999 |
+
"epoch": 4.63,
|
| 1000 |
+
"learning_rate": 1.6005333333333334e-05,
|
| 1001 |
+
"loss": 3.1082,
|
| 1002 |
+
"step": 13000
|
| 1003 |
+
},
|
| 1004 |
+
{
|
| 1005 |
+
"epoch": 4.63,
|
| 1006 |
+
"eval_gen_len": 245.1845,
|
| 1007 |
+
"eval_loss": 3.2687015533447266,
|
| 1008 |
+
"eval_rouge1": 45.504,
|
| 1009 |
+
"eval_rouge2": 17.5137,
|
| 1010 |
+
"eval_rougeL": 24.1067,
|
| 1011 |
+
"eval_rougeLsum": 41.7686,
|
| 1012 |
+
"eval_runtime": 1129.9664,
|
| 1013 |
+
"eval_samples_per_second": 4.975,
|
| 1014 |
+
"eval_steps_per_second": 0.312,
|
| 1015 |
+
"step": 13000
|
| 1016 |
+
},
|
| 1017 |
+
{
|
| 1018 |
+
"epoch": 4.66,
|
| 1019 |
+
"learning_rate": 1.5872e-05,
|
| 1020 |
+
"loss": 3.0868,
|
| 1021 |
+
"step": 13100
|
| 1022 |
+
},
|
| 1023 |
+
{
|
| 1024 |
+
"epoch": 4.7,
|
| 1025 |
+
"learning_rate": 1.5738666666666666e-05,
|
| 1026 |
+
"loss": 3.1087,
|
| 1027 |
+
"step": 13200
|
| 1028 |
+
},
|
| 1029 |
+
{
|
| 1030 |
+
"epoch": 4.73,
|
| 1031 |
+
"learning_rate": 1.5606666666666667e-05,
|
| 1032 |
+
"loss": 3.1035,
|
| 1033 |
+
"step": 13300
|
| 1034 |
+
},
|
| 1035 |
+
{
|
| 1036 |
+
"epoch": 4.77,
|
| 1037 |
+
"learning_rate": 1.5473333333333333e-05,
|
| 1038 |
+
"loss": 3.1254,
|
| 1039 |
+
"step": 13400
|
| 1040 |
+
},
|
| 1041 |
+
{
|
| 1042 |
+
"epoch": 4.8,
|
| 1043 |
+
"learning_rate": 1.534e-05,
|
| 1044 |
+
"loss": 3.1059,
|
| 1045 |
+
"step": 13500
|
| 1046 |
+
},
|
| 1047 |
+
{
|
| 1048 |
+
"epoch": 4.8,
|
| 1049 |
+
"eval_gen_len": 248.6327,
|
| 1050 |
+
"eval_loss": 3.268646717071533,
|
| 1051 |
+
"eval_rouge1": 45.3603,
|
| 1052 |
+
"eval_rouge2": 17.1619,
|
| 1053 |
+
"eval_rougeL": 23.8655,
|
| 1054 |
+
"eval_rougeLsum": 41.5953,
|
| 1055 |
+
"eval_runtime": 1136.3791,
|
| 1056 |
+
"eval_samples_per_second": 4.947,
|
| 1057 |
+
"eval_steps_per_second": 0.31,
|
| 1058 |
+
"step": 13500
|
| 1059 |
+
},
|
| 1060 |
+
{
|
| 1061 |
+
"epoch": 4.84,
|
| 1062 |
+
"learning_rate": 1.5206666666666668e-05,
|
| 1063 |
+
"loss": 3.1107,
|
| 1064 |
+
"step": 13600
|
| 1065 |
+
},
|
| 1066 |
+
{
|
| 1067 |
+
"epoch": 4.88,
|
| 1068 |
+
"learning_rate": 1.5073333333333335e-05,
|
| 1069 |
+
"loss": 3.1008,
|
| 1070 |
+
"step": 13700
|
| 1071 |
+
},
|
| 1072 |
+
{
|
| 1073 |
+
"epoch": 4.91,
|
| 1074 |
+
"learning_rate": 1.4940000000000001e-05,
|
| 1075 |
+
"loss": 3.1116,
|
| 1076 |
+
"step": 13800
|
| 1077 |
+
},
|
| 1078 |
+
{
|
| 1079 |
+
"epoch": 4.95,
|
| 1080 |
+
"learning_rate": 1.4806666666666668e-05,
|
| 1081 |
+
"loss": 3.1173,
|
| 1082 |
+
"step": 13900
|
| 1083 |
+
},
|
| 1084 |
+
{
|
| 1085 |
+
"epoch": 4.98,
|
| 1086 |
+
"learning_rate": 1.4673333333333334e-05,
|
| 1087 |
+
"loss": 3.1141,
|
| 1088 |
+
"step": 14000
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 4.98,
|
| 1092 |
+
"eval_gen_len": 234.0194,
|
| 1093 |
+
"eval_loss": 3.265822410583496,
|
| 1094 |
+
"eval_rouge1": 45.2741,
|
| 1095 |
+
"eval_rouge2": 17.3814,
|
| 1096 |
+
"eval_rougeL": 24.0377,
|
| 1097 |
+
"eval_rougeLsum": 41.5263,
|
| 1098 |
+
"eval_runtime": 1076.885,
|
| 1099 |
+
"eval_samples_per_second": 5.221,
|
| 1100 |
+
"eval_steps_per_second": 0.327,
|
| 1101 |
+
"step": 14000
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 5.02,
|
| 1105 |
+
"learning_rate": 1.4540000000000001e-05,
|
| 1106 |
+
"loss": 3.0773,
|
| 1107 |
+
"step": 14100
|
| 1108 |
+
},
|
| 1109 |
+
{
|
| 1110 |
+
"epoch": 5.05,
|
| 1111 |
+
"learning_rate": 1.4406666666666667e-05,
|
| 1112 |
+
"loss": 3.0749,
|
| 1113 |
+
"step": 14200
|
| 1114 |
+
},
|
| 1115 |
+
{
|
| 1116 |
+
"epoch": 5.09,
|
| 1117 |
+
"learning_rate": 1.4273333333333334e-05,
|
| 1118 |
+
"loss": 3.0473,
|
| 1119 |
+
"step": 14300
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 5.12,
|
| 1123 |
+
"learning_rate": 1.414e-05,
|
| 1124 |
+
"loss": 3.0415,
|
| 1125 |
+
"step": 14400
|
| 1126 |
+
},
|
| 1127 |
+
{
|
| 1128 |
+
"epoch": 5.16,
|
| 1129 |
+
"learning_rate": 1.4006666666666668e-05,
|
| 1130 |
+
"loss": 3.0294,
|
| 1131 |
+
"step": 14500
|
| 1132 |
+
},
|
| 1133 |
+
{
|
| 1134 |
+
"epoch": 5.16,
|
| 1135 |
+
"eval_gen_len": 244.4207,
|
| 1136 |
+
"eval_loss": 3.2715883255004883,
|
| 1137 |
+
"eval_rouge1": 45.7203,
|
| 1138 |
+
"eval_rouge2": 17.5962,
|
| 1139 |
+
"eval_rougeL": 24.1367,
|
| 1140 |
+
"eval_rougeLsum": 41.9119,
|
| 1141 |
+
"eval_runtime": 1108.4185,
|
| 1142 |
+
"eval_samples_per_second": 5.072,
|
| 1143 |
+
"eval_steps_per_second": 0.318,
|
| 1144 |
+
"step": 14500
|
| 1145 |
+
},
|
| 1146 |
+
{
|
| 1147 |
+
"epoch": 5.2,
|
| 1148 |
+
"learning_rate": 1.3873333333333333e-05,
|
| 1149 |
+
"loss": 3.068,
|
| 1150 |
+
"step": 14600
|
| 1151 |
+
},
|
| 1152 |
+
{
|
| 1153 |
+
"epoch": 5.23,
|
| 1154 |
+
"learning_rate": 1.374e-05,
|
| 1155 |
+
"loss": 3.0561,
|
| 1156 |
+
"step": 14700
|
| 1157 |
+
},
|
| 1158 |
+
{
|
| 1159 |
+
"epoch": 5.27,
|
| 1160 |
+
"learning_rate": 1.3606666666666666e-05,
|
| 1161 |
+
"loss": 3.0738,
|
| 1162 |
+
"step": 14800
|
| 1163 |
+
},
|
| 1164 |
+
{
|
| 1165 |
+
"epoch": 5.3,
|
| 1166 |
+
"learning_rate": 1.3473333333333334e-05,
|
| 1167 |
+
"loss": 3.0854,
|
| 1168 |
+
"step": 14900
|
| 1169 |
+
},
|
| 1170 |
+
{
|
| 1171 |
+
"epoch": 5.34,
|
| 1172 |
+
"learning_rate": 1.334e-05,
|
| 1173 |
+
"loss": 3.0613,
|
| 1174 |
+
"step": 15000
|
| 1175 |
+
},
|
| 1176 |
+
{
|
| 1177 |
+
"epoch": 5.34,
|
| 1178 |
+
"eval_gen_len": 242.0381,
|
| 1179 |
+
"eval_loss": 3.26971435546875,
|
| 1180 |
+
"eval_rouge1": 45.775,
|
| 1181 |
+
"eval_rouge2": 17.6959,
|
| 1182 |
+
"eval_rougeL": 24.1867,
|
| 1183 |
+
"eval_rougeLsum": 42.0018,
|
| 1184 |
+
"eval_runtime": 1110.4898,
|
| 1185 |
+
"eval_samples_per_second": 5.063,
|
| 1186 |
+
"eval_steps_per_second": 0.317,
|
| 1187 |
+
"step": 15000
|
| 1188 |
+
},
|
| 1189 |
+
{
|
| 1190 |
+
"epoch": 5.37,
|
| 1191 |
+
"learning_rate": 1.3206666666666667e-05,
|
| 1192 |
+
"loss": 3.0704,
|
| 1193 |
+
"step": 15100
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"epoch": 5.41,
|
| 1197 |
+
"learning_rate": 1.3073333333333334e-05,
|
| 1198 |
+
"loss": 3.0419,
|
| 1199 |
+
"step": 15200
|
| 1200 |
+
},
|
| 1201 |
+
{
|
| 1202 |
+
"epoch": 5.44,
|
| 1203 |
+
"learning_rate": 1.2940000000000001e-05,
|
| 1204 |
+
"loss": 3.0748,
|
| 1205 |
+
"step": 15300
|
| 1206 |
+
},
|
| 1207 |
+
{
|
| 1208 |
+
"epoch": 5.48,
|
| 1209 |
+
"learning_rate": 1.2806666666666667e-05,
|
| 1210 |
+
"loss": 3.0509,
|
| 1211 |
+
"step": 15400
|
| 1212 |
+
},
|
| 1213 |
+
{
|
| 1214 |
+
"epoch": 5.52,
|
| 1215 |
+
"learning_rate": 1.2673333333333335e-05,
|
| 1216 |
+
"loss": 3.0549,
|
| 1217 |
+
"step": 15500
|
| 1218 |
+
},
|
| 1219 |
+
{
|
| 1220 |
+
"epoch": 5.52,
|
| 1221 |
+
"eval_gen_len": 242.5493,
|
| 1222 |
+
"eval_loss": 3.2702813148498535,
|
| 1223 |
+
"eval_rouge1": 45.8193,
|
| 1224 |
+
"eval_rouge2": 17.686,
|
| 1225 |
+
"eval_rougeL": 24.1997,
|
| 1226 |
+
"eval_rougeLsum": 42.0109,
|
| 1227 |
+
"eval_runtime": 1089.9866,
|
| 1228 |
+
"eval_samples_per_second": 5.158,
|
| 1229 |
+
"eval_steps_per_second": 0.323,
|
| 1230 |
+
"step": 15500
|
| 1231 |
+
},
|
| 1232 |
+
{
|
| 1233 |
+
"epoch": 5.55,
|
| 1234 |
+
"learning_rate": 1.254e-05,
|
| 1235 |
+
"loss": 3.0902,
|
| 1236 |
+
"step": 15600
|
| 1237 |
+
},
|
| 1238 |
+
{
|
| 1239 |
+
"epoch": 5.59,
|
| 1240 |
+
"learning_rate": 1.2406666666666668e-05,
|
| 1241 |
+
"loss": 3.0697,
|
| 1242 |
+
"step": 15700
|
| 1243 |
+
},
|
| 1244 |
+
{
|
| 1245 |
+
"epoch": 5.62,
|
| 1246 |
+
"learning_rate": 1.2273333333333333e-05,
|
| 1247 |
+
"loss": 3.0793,
|
| 1248 |
+
"step": 15800
|
| 1249 |
+
},
|
| 1250 |
+
{
|
| 1251 |
+
"epoch": 5.66,
|
| 1252 |
+
"learning_rate": 1.214e-05,
|
| 1253 |
+
"loss": 3.076,
|
| 1254 |
+
"step": 15900
|
| 1255 |
+
},
|
| 1256 |
+
{
|
| 1257 |
+
"epoch": 5.69,
|
| 1258 |
+
"learning_rate": 1.2006666666666666e-05,
|
| 1259 |
+
"loss": 3.0725,
|
| 1260 |
+
"step": 16000
|
| 1261 |
+
},
|
| 1262 |
+
{
|
| 1263 |
+
"epoch": 5.69,
|
| 1264 |
+
"eval_gen_len": 240.2812,
|
| 1265 |
+
"eval_loss": 3.2654964923858643,
|
| 1266 |
+
"eval_rouge1": 45.3515,
|
| 1267 |
+
"eval_rouge2": 17.3438,
|
| 1268 |
+
"eval_rougeL": 24.0586,
|
| 1269 |
+
"eval_rougeLsum": 41.6126,
|
| 1270 |
+
"eval_runtime": 1107.0741,
|
| 1271 |
+
"eval_samples_per_second": 5.078,
|
| 1272 |
+
"eval_steps_per_second": 0.318,
|
| 1273 |
+
"step": 16000
|
| 1274 |
+
},
|
| 1275 |
+
{
|
| 1276 |
+
"epoch": 5.73,
|
| 1277 |
+
"learning_rate": 1.1873333333333334e-05,
|
| 1278 |
+
"loss": 3.0904,
|
| 1279 |
+
"step": 16100
|
| 1280 |
+
},
|
| 1281 |
+
{
|
| 1282 |
+
"epoch": 5.76,
|
| 1283 |
+
"learning_rate": 1.174e-05,
|
| 1284 |
+
"loss": 3.082,
|
| 1285 |
+
"step": 16200
|
| 1286 |
+
},
|
| 1287 |
+
{
|
| 1288 |
+
"epoch": 5.8,
|
| 1289 |
+
"learning_rate": 1.1608000000000001e-05,
|
| 1290 |
+
"loss": 3.0543,
|
| 1291 |
+
"step": 16300
|
| 1292 |
+
},
|
| 1293 |
+
{
|
| 1294 |
+
"epoch": 5.84,
|
| 1295 |
+
"learning_rate": 1.1474666666666667e-05,
|
| 1296 |
+
"loss": 3.0445,
|
| 1297 |
+
"step": 16400
|
| 1298 |
+
},
|
| 1299 |
+
{
|
| 1300 |
+
"epoch": 5.87,
|
| 1301 |
+
"learning_rate": 1.1341333333333334e-05,
|
| 1302 |
+
"loss": 3.0728,
|
| 1303 |
+
"step": 16500
|
| 1304 |
+
},
|
| 1305 |
+
{
|
| 1306 |
+
"epoch": 5.87,
|
| 1307 |
+
"eval_gen_len": 250.455,
|
| 1308 |
+
"eval_loss": 3.2671351432800293,
|
| 1309 |
+
"eval_rouge1": 45.6791,
|
| 1310 |
+
"eval_rouge2": 17.5028,
|
| 1311 |
+
"eval_rougeL": 24.0691,
|
| 1312 |
+
"eval_rougeLsum": 41.9219,
|
| 1313 |
+
"eval_runtime": 1163.6259,
|
| 1314 |
+
"eval_samples_per_second": 4.831,
|
| 1315 |
+
"eval_steps_per_second": 0.303,
|
| 1316 |
+
"step": 16500
|
| 1317 |
+
},
|
| 1318 |
+
{
|
| 1319 |
+
"epoch": 5.91,
|
| 1320 |
+
"learning_rate": 1.1208e-05,
|
| 1321 |
+
"loss": 3.0764,
|
| 1322 |
+
"step": 16600
|
| 1323 |
+
},
|
| 1324 |
+
{
|
| 1325 |
+
"epoch": 5.94,
|
| 1326 |
+
"learning_rate": 1.1074666666666667e-05,
|
| 1327 |
+
"loss": 3.0822,
|
| 1328 |
+
"step": 16700
|
| 1329 |
+
},
|
| 1330 |
+
{
|
| 1331 |
+
"epoch": 5.98,
|
| 1332 |
+
"learning_rate": 1.0941333333333333e-05,
|
| 1333 |
+
"loss": 3.0452,
|
| 1334 |
+
"step": 16800
|
| 1335 |
+
},
|
| 1336 |
+
{
|
| 1337 |
+
"epoch": 6.01,
|
| 1338 |
+
"learning_rate": 1.0808e-05,
|
| 1339 |
+
"loss": 3.0631,
|
| 1340 |
+
"step": 16900
|
| 1341 |
+
},
|
| 1342 |
+
{
|
| 1343 |
+
"epoch": 6.05,
|
| 1344 |
+
"learning_rate": 1.0674666666666666e-05,
|
| 1345 |
+
"loss": 3.0142,
|
| 1346 |
+
"step": 17000
|
| 1347 |
+
},
|
| 1348 |
+
{
|
| 1349 |
+
"epoch": 6.05,
|
| 1350 |
+
"eval_gen_len": 245.6204,
|
| 1351 |
+
"eval_loss": 3.270817279815674,
|
| 1352 |
+
"eval_rouge1": 46.0287,
|
| 1353 |
+
"eval_rouge2": 17.8079,
|
| 1354 |
+
"eval_rougeL": 24.2916,
|
| 1355 |
+
"eval_rougeLsum": 42.2369,
|
| 1356 |
+
"eval_runtime": 1077.587,
|
| 1357 |
+
"eval_samples_per_second": 5.217,
|
| 1358 |
+
"eval_steps_per_second": 0.327,
|
| 1359 |
+
"step": 17000
|
| 1360 |
+
},
|
| 1361 |
+
{
|
| 1362 |
+
"epoch": 6.09,
|
| 1363 |
+
"learning_rate": 1.0541333333333334e-05,
|
| 1364 |
+
"loss": 3.0106,
|
| 1365 |
+
"step": 17100
|
| 1366 |
+
},
|
| 1367 |
+
{
|
| 1368 |
+
"epoch": 6.12,
|
| 1369 |
+
"learning_rate": 1.0408e-05,
|
| 1370 |
+
"loss": 3.0208,
|
| 1371 |
+
"step": 17200
|
| 1372 |
+
},
|
| 1373 |
+
{
|
| 1374 |
+
"epoch": 6.16,
|
| 1375 |
+
"learning_rate": 1.0274666666666667e-05,
|
| 1376 |
+
"loss": 3.0455,
|
| 1377 |
+
"step": 17300
|
| 1378 |
+
},
|
| 1379 |
+
{
|
| 1380 |
+
"epoch": 6.19,
|
| 1381 |
+
"learning_rate": 1.0141333333333332e-05,
|
| 1382 |
+
"loss": 3.0404,
|
| 1383 |
+
"step": 17400
|
| 1384 |
+
},
|
| 1385 |
+
{
|
| 1386 |
+
"epoch": 6.23,
|
| 1387 |
+
"learning_rate": 1.0008e-05,
|
| 1388 |
+
"loss": 3.0312,
|
| 1389 |
+
"step": 17500
|
| 1390 |
+
},
|
| 1391 |
+
{
|
| 1392 |
+
"epoch": 6.23,
|
| 1393 |
+
"eval_gen_len": 236.2234,
|
| 1394 |
+
"eval_loss": 3.270146608352661,
|
| 1395 |
+
"eval_rouge1": 45.5731,
|
| 1396 |
+
"eval_rouge2": 17.5404,
|
| 1397 |
+
"eval_rougeL": 24.0925,
|
| 1398 |
+
"eval_rougeLsum": 41.7584,
|
| 1399 |
+
"eval_runtime": 1079.8219,
|
| 1400 |
+
"eval_samples_per_second": 5.206,
|
| 1401 |
+
"eval_steps_per_second": 0.326,
|
| 1402 |
+
"step": 17500
|
| 1403 |
+
},
|
| 1404 |
+
{
|
| 1405 |
+
"epoch": 6.26,
|
| 1406 |
+
"learning_rate": 9.874666666666667e-06,
|
| 1407 |
+
"loss": 3.033,
|
| 1408 |
+
"step": 17600
|
| 1409 |
+
},
|
| 1410 |
+
{
|
| 1411 |
+
"epoch": 6.3,
|
| 1412 |
+
"learning_rate": 9.741333333333334e-06,
|
| 1413 |
+
"loss": 3.045,
|
| 1414 |
+
"step": 17700
|
| 1415 |
+
},
|
| 1416 |
+
{
|
| 1417 |
+
"epoch": 6.33,
|
| 1418 |
+
"learning_rate": 9.608e-06,
|
| 1419 |
+
"loss": 3.0339,
|
| 1420 |
+
"step": 17800
|
| 1421 |
+
},
|
| 1422 |
+
{
|
| 1423 |
+
"epoch": 6.37,
|
| 1424 |
+
"learning_rate": 9.474666666666668e-06,
|
| 1425 |
+
"loss": 3.034,
|
| 1426 |
+
"step": 17900
|
| 1427 |
+
},
|
| 1428 |
+
{
|
| 1429 |
+
"epoch": 6.41,
|
| 1430 |
+
"learning_rate": 9.341333333333333e-06,
|
| 1431 |
+
"loss": 3.0231,
|
| 1432 |
+
"step": 18000
|
| 1433 |
+
},
|
| 1434 |
+
{
|
| 1435 |
+
"epoch": 6.41,
|
| 1436 |
+
"eval_gen_len": 260.1686,
|
| 1437 |
+
"eval_loss": 3.271860361099243,
|
| 1438 |
+
"eval_rouge1": 46.1094,
|
| 1439 |
+
"eval_rouge2": 17.7117,
|
| 1440 |
+
"eval_rougeL": 24.1117,
|
| 1441 |
+
"eval_rougeLsum": 42.2882,
|
| 1442 |
+
"eval_runtime": 1163.8918,
|
| 1443 |
+
"eval_samples_per_second": 4.83,
|
| 1444 |
+
"eval_steps_per_second": 0.302,
|
| 1445 |
+
"step": 18000
|
| 1446 |
+
},
|
| 1447 |
+
{
|
| 1448 |
+
"epoch": 6.44,
|
| 1449 |
+
"learning_rate": 9.208e-06,
|
| 1450 |
+
"loss": 3.0454,
|
| 1451 |
+
"step": 18100
|
| 1452 |
+
},
|
| 1453 |
+
{
|
| 1454 |
+
"epoch": 6.48,
|
| 1455 |
+
"learning_rate": 9.074666666666666e-06,
|
| 1456 |
+
"loss": 3.0343,
|
| 1457 |
+
"step": 18200
|
| 1458 |
+
},
|
| 1459 |
+
{
|
| 1460 |
+
"epoch": 6.51,
|
| 1461 |
+
"learning_rate": 8.941333333333334e-06,
|
| 1462 |
+
"loss": 3.0386,
|
| 1463 |
+
"step": 18300
|
| 1464 |
+
},
|
| 1465 |
+
{
|
| 1466 |
+
"epoch": 6.55,
|
| 1467 |
+
"learning_rate": 8.808000000000001e-06,
|
| 1468 |
+
"loss": 3.0429,
|
| 1469 |
+
"step": 18400
|
| 1470 |
+
},
|
| 1471 |
+
{
|
| 1472 |
+
"epoch": 6.58,
|
| 1473 |
+
"learning_rate": 8.674666666666667e-06,
|
| 1474 |
+
"loss": 3.0414,
|
| 1475 |
+
"step": 18500
|
| 1476 |
+
},
|
| 1477 |
+
{
|
| 1478 |
+
"epoch": 6.58,
|
| 1479 |
+
"eval_gen_len": 245.0961,
|
| 1480 |
+
"eval_loss": 3.2702643871307373,
|
| 1481 |
+
"eval_rouge1": 45.9178,
|
| 1482 |
+
"eval_rouge2": 17.6987,
|
| 1483 |
+
"eval_rougeL": 24.1882,
|
| 1484 |
+
"eval_rougeLsum": 42.1382,
|
| 1485 |
+
"eval_runtime": 1111.098,
|
| 1486 |
+
"eval_samples_per_second": 5.06,
|
| 1487 |
+
"eval_steps_per_second": 0.317,
|
| 1488 |
+
"step": 18500
|
| 1489 |
+
},
|
| 1490 |
+
{
|
| 1491 |
+
"epoch": 6.62,
|
| 1492 |
+
"learning_rate": 8.541333333333334e-06,
|
| 1493 |
+
"loss": 3.0242,
|
| 1494 |
+
"step": 18600
|
| 1495 |
+
},
|
| 1496 |
+
{
|
| 1497 |
+
"epoch": 6.65,
|
| 1498 |
+
"learning_rate": 8.408e-06,
|
| 1499 |
+
"loss": 3.0449,
|
| 1500 |
+
"step": 18700
|
| 1501 |
+
},
|
| 1502 |
+
{
|
| 1503 |
+
"epoch": 6.69,
|
| 1504 |
+
"learning_rate": 8.274666666666667e-06,
|
| 1505 |
+
"loss": 3.0392,
|
| 1506 |
+
"step": 18800
|
| 1507 |
+
},
|
| 1508 |
+
{
|
| 1509 |
+
"epoch": 6.73,
|
| 1510 |
+
"learning_rate": 8.141333333333333e-06,
|
| 1511 |
+
"loss": 3.0336,
|
| 1512 |
+
"step": 18900
|
| 1513 |
+
},
|
| 1514 |
+
{
|
| 1515 |
+
"epoch": 6.76,
|
| 1516 |
+
"learning_rate": 8.008e-06,
|
| 1517 |
+
"loss": 3.0434,
|
| 1518 |
+
"step": 19000
|
| 1519 |
+
},
|
| 1520 |
+
{
|
| 1521 |
+
"epoch": 6.76,
|
| 1522 |
+
"eval_gen_len": 247.8225,
|
| 1523 |
+
"eval_loss": 3.2714767456054688,
|
| 1524 |
+
"eval_rouge1": 46.0129,
|
| 1525 |
+
"eval_rouge2": 17.7545,
|
| 1526 |
+
"eval_rougeL": 24.2235,
|
| 1527 |
+
"eval_rougeLsum": 42.245,
|
| 1528 |
+
"eval_runtime": 1091.4396,
|
| 1529 |
+
"eval_samples_per_second": 5.151,
|
| 1530 |
+
"eval_steps_per_second": 0.323,
|
| 1531 |
+
"step": 19000
|
| 1532 |
+
},
|
| 1533 |
+
{
|
| 1534 |
+
"epoch": 6.8,
|
| 1535 |
+
"learning_rate": 7.874666666666666e-06,
|
| 1536 |
+
"loss": 3.0021,
|
| 1537 |
+
"step": 19100
|
| 1538 |
+
},
|
| 1539 |
+
{
|
| 1540 |
+
"epoch": 6.83,
|
| 1541 |
+
"learning_rate": 7.741333333333335e-06,
|
| 1542 |
+
"loss": 3.0498,
|
| 1543 |
+
"step": 19200
|
| 1544 |
+
},
|
| 1545 |
+
{
|
| 1546 |
+
"epoch": 6.87,
|
| 1547 |
+
"learning_rate": 7.608e-06,
|
| 1548 |
+
"loss": 3.0314,
|
| 1549 |
+
"step": 19300
|
| 1550 |
+
},
|
| 1551 |
+
{
|
| 1552 |
+
"epoch": 6.9,
|
| 1553 |
+
"learning_rate": 7.476e-06,
|
| 1554 |
+
"loss": 3.0437,
|
| 1555 |
+
"step": 19400
|
| 1556 |
+
},
|
| 1557 |
+
{
|
| 1558 |
+
"epoch": 6.94,
|
| 1559 |
+
"learning_rate": 7.342666666666667e-06,
|
| 1560 |
+
"loss": 3.0456,
|
| 1561 |
+
"step": 19500
|
| 1562 |
+
},
|
| 1563 |
+
{
|
| 1564 |
+
"epoch": 6.94,
|
| 1565 |
+
"eval_gen_len": 256.9835,
|
| 1566 |
+
"eval_loss": 3.2681996822357178,
|
| 1567 |
+
"eval_rouge1": 45.8634,
|
| 1568 |
+
"eval_rouge2": 17.6462,
|
| 1569 |
+
"eval_rougeL": 24.1366,
|
| 1570 |
+
"eval_rougeLsum": 42.1194,
|
| 1571 |
+
"eval_runtime": 1174.1005,
|
| 1572 |
+
"eval_samples_per_second": 4.788,
|
| 1573 |
+
"eval_steps_per_second": 0.3,
|
| 1574 |
+
"step": 19500
|
| 1575 |
+
},
|
| 1576 |
+
{
|
| 1577 |
+
"epoch": 6.97,
|
| 1578 |
+
"learning_rate": 7.209333333333334e-06,
|
| 1579 |
+
"loss": 3.0172,
|
| 1580 |
+
"step": 19600
|
| 1581 |
+
},
|
| 1582 |
+
{
|
| 1583 |
+
"epoch": 7.01,
|
| 1584 |
+
"learning_rate": 7.077333333333333e-06,
|
| 1585 |
+
"loss": 3.0364,
|
| 1586 |
+
"step": 19700
|
| 1587 |
+
},
|
| 1588 |
+
{
|
| 1589 |
+
"epoch": 7.05,
|
| 1590 |
+
"learning_rate": 6.944e-06,
|
| 1591 |
+
"loss": 3.0109,
|
| 1592 |
+
"step": 19800
|
| 1593 |
+
},
|
| 1594 |
+
{
|
| 1595 |
+
"epoch": 7.08,
|
| 1596 |
+
"learning_rate": 6.8106666666666665e-06,
|
| 1597 |
+
"loss": 2.998,
|
| 1598 |
+
"step": 19900
|
| 1599 |
+
},
|
| 1600 |
+
{
|
| 1601 |
+
"epoch": 7.12,
|
| 1602 |
+
"learning_rate": 6.677333333333334e-06,
|
| 1603 |
+
"loss": 3.0188,
|
| 1604 |
+
"step": 20000
|
| 1605 |
+
},
|
| 1606 |
+
{
|
| 1607 |
+
"epoch": 7.12,
|
| 1608 |
+
"eval_gen_len": 240.1866,
|
| 1609 |
+
"eval_loss": 3.2752106189727783,
|
| 1610 |
+
"eval_rouge1": 45.8366,
|
| 1611 |
+
"eval_rouge2": 17.6771,
|
| 1612 |
+
"eval_rougeL": 24.165,
|
| 1613 |
+
"eval_rougeLsum": 42.0438,
|
| 1614 |
+
"eval_runtime": 1085.4389,
|
| 1615 |
+
"eval_samples_per_second": 5.179,
|
| 1616 |
+
"eval_steps_per_second": 0.324,
|
| 1617 |
+
"step": 20000
|
| 1618 |
+
},
|
| 1619 |
+
{
|
| 1620 |
+
"epoch": 7.15,
|
| 1621 |
+
"learning_rate": 6.544e-06,
|
| 1622 |
+
"loss": 3.0119,
|
| 1623 |
+
"step": 20100
|
| 1624 |
+
},
|
| 1625 |
+
{
|
| 1626 |
+
"epoch": 7.19,
|
| 1627 |
+
"learning_rate": 6.410666666666667e-06,
|
| 1628 |
+
"loss": 3.0091,
|
| 1629 |
+
"step": 20200
|
| 1630 |
+
},
|
| 1631 |
+
{
|
| 1632 |
+
"epoch": 7.22,
|
| 1633 |
+
"learning_rate": 6.2773333333333334e-06,
|
| 1634 |
+
"loss": 3.0077,
|
| 1635 |
+
"step": 20300
|
| 1636 |
+
},
|
| 1637 |
+
{
|
| 1638 |
+
"epoch": 7.26,
|
| 1639 |
+
"learning_rate": 6.144000000000001e-06,
|
| 1640 |
+
"loss": 2.9942,
|
| 1641 |
+
"step": 20400
|
| 1642 |
+
},
|
| 1643 |
+
{
|
| 1644 |
+
"epoch": 7.3,
|
| 1645 |
+
"learning_rate": 6.010666666666667e-06,
|
| 1646 |
+
"loss": 3.0227,
|
| 1647 |
+
"step": 20500
|
| 1648 |
+
},
|
| 1649 |
+
{
|
| 1650 |
+
"epoch": 7.3,
|
| 1651 |
+
"eval_gen_len": 245.8337,
|
| 1652 |
+
"eval_loss": 3.2722229957580566,
|
| 1653 |
+
"eval_rouge1": 46.0509,
|
| 1654 |
+
"eval_rouge2": 17.8248,
|
| 1655 |
+
"eval_rougeL": 24.2389,
|
| 1656 |
+
"eval_rougeLsum": 42.2681,
|
| 1657 |
+
"eval_runtime": 1093.3258,
|
| 1658 |
+
"eval_samples_per_second": 5.142,
|
| 1659 |
+
"eval_steps_per_second": 0.322,
|
| 1660 |
+
"step": 20500
|
| 1661 |
+
},
|
| 1662 |
+
{
|
| 1663 |
+
"epoch": 7.33,
|
| 1664 |
+
"learning_rate": 5.877333333333334e-06,
|
| 1665 |
+
"loss": 2.9996,
|
| 1666 |
+
"step": 20600
|
| 1667 |
+
},
|
| 1668 |
+
{
|
| 1669 |
+
"epoch": 7.37,
|
| 1670 |
+
"learning_rate": 5.744e-06,
|
| 1671 |
+
"loss": 3.0046,
|
| 1672 |
+
"step": 20700
|
| 1673 |
+
},
|
| 1674 |
+
{
|
| 1675 |
+
"epoch": 7.4,
|
| 1676 |
+
"learning_rate": 5.610666666666667e-06,
|
| 1677 |
+
"loss": 3.0018,
|
| 1678 |
+
"step": 20800
|
| 1679 |
+
},
|
| 1680 |
+
{
|
| 1681 |
+
"epoch": 7.44,
|
| 1682 |
+
"learning_rate": 5.4773333333333335e-06,
|
| 1683 |
+
"loss": 3.0096,
|
| 1684 |
+
"step": 20900
|
| 1685 |
+
},
|
| 1686 |
+
{
|
| 1687 |
+
"epoch": 7.47,
|
| 1688 |
+
"learning_rate": 5.344e-06,
|
| 1689 |
+
"loss": 2.9895,
|
| 1690 |
+
"step": 21000
|
| 1691 |
+
},
|
| 1692 |
+
{
|
| 1693 |
+
"epoch": 7.47,
|
| 1694 |
+
"eval_gen_len": 243.867,
|
| 1695 |
+
"eval_loss": 3.2725987434387207,
|
| 1696 |
+
"eval_rouge1": 45.7896,
|
| 1697 |
+
"eval_rouge2": 17.5833,
|
| 1698 |
+
"eval_rougeL": 24.1226,
|
| 1699 |
+
"eval_rougeLsum": 42.016,
|
| 1700 |
+
"eval_runtime": 1110.8794,
|
| 1701 |
+
"eval_samples_per_second": 5.061,
|
| 1702 |
+
"eval_steps_per_second": 0.317,
|
| 1703 |
+
"step": 21000
|
| 1704 |
+
},
|
| 1705 |
+
{
|
| 1706 |
+
"epoch": 7.51,
|
| 1707 |
+
"learning_rate": 5.2106666666666665e-06,
|
| 1708 |
+
"loss": 3.0186,
|
| 1709 |
+
"step": 21100
|
| 1710 |
+
},
|
| 1711 |
+
{
|
| 1712 |
+
"epoch": 7.54,
|
| 1713 |
+
"learning_rate": 5.077333333333334e-06,
|
| 1714 |
+
"loss": 3.0337,
|
| 1715 |
+
"step": 21200
|
| 1716 |
+
},
|
| 1717 |
+
{
|
| 1718 |
+
"epoch": 7.58,
|
| 1719 |
+
"learning_rate": 4.9440000000000004e-06,
|
| 1720 |
+
"loss": 3.0136,
|
| 1721 |
+
"step": 21300
|
| 1722 |
+
},
|
| 1723 |
+
{
|
| 1724 |
+
"epoch": 7.62,
|
| 1725 |
+
"learning_rate": 4.810666666666667e-06,
|
| 1726 |
+
"loss": 3.0109,
|
| 1727 |
+
"step": 21400
|
| 1728 |
+
},
|
| 1729 |
+
{
|
| 1730 |
+
"epoch": 7.65,
|
| 1731 |
+
"learning_rate": 4.6773333333333335e-06,
|
| 1732 |
+
"loss": 3.0146,
|
| 1733 |
+
"step": 21500
|
| 1734 |
+
},
|
| 1735 |
+
{
|
| 1736 |
+
"epoch": 7.65,
|
| 1737 |
+
"eval_gen_len": 244.0598,
|
| 1738 |
+
"eval_loss": 3.269317865371704,
|
| 1739 |
+
"eval_rouge1": 46.0179,
|
| 1740 |
+
"eval_rouge2": 17.6952,
|
| 1741 |
+
"eval_rougeL": 24.2204,
|
| 1742 |
+
"eval_rougeLsum": 42.2436,
|
| 1743 |
+
"eval_runtime": 1075.6479,
|
| 1744 |
+
"eval_samples_per_second": 5.227,
|
| 1745 |
+
"eval_steps_per_second": 0.327,
|
| 1746 |
+
"step": 21500
|
| 1747 |
+
},
|
| 1748 |
+
{
|
| 1749 |
+
"epoch": 7.69,
|
| 1750 |
+
"learning_rate": 4.544e-06,
|
| 1751 |
+
"loss": 3.0195,
|
| 1752 |
+
"step": 21600
|
| 1753 |
+
},
|
| 1754 |
+
{
|
| 1755 |
+
"epoch": 7.72,
|
| 1756 |
+
"learning_rate": 4.4106666666666666e-06,
|
| 1757 |
+
"loss": 3.0103,
|
| 1758 |
+
"step": 21700
|
| 1759 |
+
},
|
| 1760 |
+
{
|
| 1761 |
+
"epoch": 7.76,
|
| 1762 |
+
"learning_rate": 4.277333333333333e-06,
|
| 1763 |
+
"loss": 3.0117,
|
| 1764 |
+
"step": 21800
|
| 1765 |
+
},
|
| 1766 |
+
{
|
| 1767 |
+
"epoch": 7.79,
|
| 1768 |
+
"learning_rate": 4.144e-06,
|
| 1769 |
+
"loss": 3.0012,
|
| 1770 |
+
"step": 21900
|
| 1771 |
+
},
|
| 1772 |
+
{
|
| 1773 |
+
"epoch": 7.83,
|
| 1774 |
+
"learning_rate": 4.010666666666667e-06,
|
| 1775 |
+
"loss": 3.014,
|
| 1776 |
+
"step": 22000
|
| 1777 |
+
},
|
| 1778 |
+
{
|
| 1779 |
+
"epoch": 7.83,
|
| 1780 |
+
"eval_gen_len": 240.4804,
|
| 1781 |
+
"eval_loss": 3.2708346843719482,
|
| 1782 |
+
"eval_rouge1": 46.0704,
|
| 1783 |
+
"eval_rouge2": 17.75,
|
| 1784 |
+
"eval_rougeL": 24.2308,
|
| 1785 |
+
"eval_rougeLsum": 42.2591,
|
| 1786 |
+
"eval_runtime": 1055.0456,
|
| 1787 |
+
"eval_samples_per_second": 5.329,
|
| 1788 |
+
"eval_steps_per_second": 0.334,
|
| 1789 |
+
"step": 22000
|
| 1790 |
+
},
|
| 1791 |
+
{
|
| 1792 |
+
"epoch": 7.86,
|
| 1793 |
+
"learning_rate": 3.8773333333333335e-06,
|
| 1794 |
+
"loss": 3.001,
|
| 1795 |
+
"step": 22100
|
| 1796 |
+
},
|
| 1797 |
+
{
|
| 1798 |
+
"epoch": 7.9,
|
| 1799 |
+
"learning_rate": 3.744e-06,
|
| 1800 |
+
"loss": 3.0133,
|
| 1801 |
+
"step": 22200
|
| 1802 |
+
},
|
| 1803 |
+
{
|
| 1804 |
+
"epoch": 7.94,
|
| 1805 |
+
"learning_rate": 3.6106666666666666e-06,
|
| 1806 |
+
"loss": 3.0007,
|
| 1807 |
+
"step": 22300
|
| 1808 |
+
},
|
| 1809 |
+
{
|
| 1810 |
+
"epoch": 7.97,
|
| 1811 |
+
"learning_rate": 3.4773333333333336e-06,
|
| 1812 |
+
"loss": 3.0189,
|
| 1813 |
+
"step": 22400
|
| 1814 |
+
},
|
| 1815 |
+
{
|
| 1816 |
+
"epoch": 8.01,
|
| 1817 |
+
"learning_rate": 3.344e-06,
|
| 1818 |
+
"loss": 3.0427,
|
| 1819 |
+
"step": 22500
|
| 1820 |
+
},
|
| 1821 |
+
{
|
| 1822 |
+
"epoch": 8.01,
|
| 1823 |
+
"eval_gen_len": 242.4203,
|
| 1824 |
+
"eval_loss": 3.27339243888855,
|
| 1825 |
+
"eval_rouge1": 46.0662,
|
| 1826 |
+
"eval_rouge2": 17.7231,
|
| 1827 |
+
"eval_rougeL": 24.1915,
|
| 1828 |
+
"eval_rougeLsum": 42.2227,
|
| 1829 |
+
"eval_runtime": 1083.3051,
|
| 1830 |
+
"eval_samples_per_second": 5.19,
|
| 1831 |
+
"eval_steps_per_second": 0.325,
|
| 1832 |
+
"step": 22500
|
| 1833 |
+
},
|
| 1834 |
+
{
|
| 1835 |
+
"epoch": 8.04,
|
| 1836 |
+
"learning_rate": 3.210666666666667e-06,
|
| 1837 |
+
"loss": 2.995,
|
| 1838 |
+
"step": 22600
|
| 1839 |
+
},
|
| 1840 |
+
{
|
| 1841 |
+
"epoch": 8.08,
|
| 1842 |
+
"learning_rate": 3.0773333333333336e-06,
|
| 1843 |
+
"loss": 2.9946,
|
| 1844 |
+
"step": 22700
|
| 1845 |
+
},
|
| 1846 |
+
{
|
| 1847 |
+
"epoch": 8.11,
|
| 1848 |
+
"learning_rate": 2.944e-06,
|
| 1849 |
+
"loss": 3.0003,
|
| 1850 |
+
"step": 22800
|
| 1851 |
+
},
|
| 1852 |
+
{
|
| 1853 |
+
"epoch": 8.15,
|
| 1854 |
+
"learning_rate": 2.8106666666666666e-06,
|
| 1855 |
+
"loss": 2.9959,
|
| 1856 |
+
"step": 22900
|
| 1857 |
+
},
|
| 1858 |
+
{
|
| 1859 |
+
"epoch": 8.19,
|
| 1860 |
+
"learning_rate": 2.6773333333333336e-06,
|
| 1861 |
+
"loss": 2.9835,
|
| 1862 |
+
"step": 23000
|
| 1863 |
+
},
|
| 1864 |
+
{
|
| 1865 |
+
"epoch": 8.19,
|
| 1866 |
+
"eval_gen_len": 236.6266,
|
| 1867 |
+
"eval_loss": 3.273963212966919,
|
| 1868 |
+
"eval_rouge1": 46.165,
|
| 1869 |
+
"eval_rouge2": 17.8947,
|
| 1870 |
+
"eval_rougeL": 24.366,
|
| 1871 |
+
"eval_rougeLsum": 42.3521,
|
| 1872 |
+
"eval_runtime": 1047.6593,
|
| 1873 |
+
"eval_samples_per_second": 5.366,
|
| 1874 |
+
"eval_steps_per_second": 0.336,
|
| 1875 |
+
"step": 23000
|
| 1876 |
+
},
|
| 1877 |
+
{
|
| 1878 |
+
"epoch": 8.22,
|
| 1879 |
+
"learning_rate": 2.544e-06,
|
| 1880 |
+
"loss": 2.9922,
|
| 1881 |
+
"step": 23100
|
| 1882 |
+
},
|
| 1883 |
+
{
|
| 1884 |
+
"epoch": 8.26,
|
| 1885 |
+
"learning_rate": 2.4106666666666667e-06,
|
| 1886 |
+
"loss": 2.9937,
|
| 1887 |
+
"step": 23200
|
| 1888 |
+
},
|
| 1889 |
+
{
|
| 1890 |
+
"epoch": 8.29,
|
| 1891 |
+
"learning_rate": 2.277333333333333e-06,
|
| 1892 |
+
"loss": 2.9933,
|
| 1893 |
+
"step": 23300
|
| 1894 |
+
},
|
| 1895 |
+
{
|
| 1896 |
+
"epoch": 8.33,
|
| 1897 |
+
"learning_rate": 2.144e-06,
|
| 1898 |
+
"loss": 2.9921,
|
| 1899 |
+
"step": 23400
|
| 1900 |
+
},
|
| 1901 |
+
{
|
| 1902 |
+
"epoch": 8.36,
|
| 1903 |
+
"learning_rate": 2.0106666666666667e-06,
|
| 1904 |
+
"loss": 2.987,
|
| 1905 |
+
"step": 23500
|
| 1906 |
+
},
|
| 1907 |
+
{
|
| 1908 |
+
"epoch": 8.36,
|
| 1909 |
+
"eval_gen_len": 238.479,
|
| 1910 |
+
"eval_loss": 3.2719457149505615,
|
| 1911 |
+
"eval_rouge1": 45.9025,
|
| 1912 |
+
"eval_rouge2": 17.7625,
|
| 1913 |
+
"eval_rougeL": 24.2432,
|
| 1914 |
+
"eval_rougeLsum": 42.1257,
|
| 1915 |
+
"eval_runtime": 1104.1087,
|
| 1916 |
+
"eval_samples_per_second": 5.092,
|
| 1917 |
+
"eval_steps_per_second": 0.319,
|
| 1918 |
+
"step": 23500
|
| 1919 |
+
},
|
| 1920 |
+
{
|
| 1921 |
+
"epoch": 8.4,
|
| 1922 |
+
"learning_rate": 1.8773333333333332e-06,
|
| 1923 |
+
"loss": 2.9925,
|
| 1924 |
+
"step": 23600
|
| 1925 |
+
},
|
| 1926 |
+
{
|
| 1927 |
+
"epoch": 8.43,
|
| 1928 |
+
"learning_rate": 1.7440000000000002e-06,
|
| 1929 |
+
"loss": 2.9924,
|
| 1930 |
+
"step": 23700
|
| 1931 |
+
},
|
| 1932 |
+
{
|
| 1933 |
+
"epoch": 8.47,
|
| 1934 |
+
"learning_rate": 1.6106666666666667e-06,
|
| 1935 |
+
"loss": 3.0224,
|
| 1936 |
+
"step": 23800
|
| 1937 |
+
},
|
| 1938 |
+
{
|
| 1939 |
+
"epoch": 8.51,
|
| 1940 |
+
"learning_rate": 1.4773333333333334e-06,
|
| 1941 |
+
"loss": 3.0137,
|
| 1942 |
+
"step": 23900
|
| 1943 |
+
},
|
| 1944 |
+
{
|
| 1945 |
+
"epoch": 8.54,
|
| 1946 |
+
"learning_rate": 1.344e-06,
|
| 1947 |
+
"loss": 2.9922,
|
| 1948 |
+
"step": 24000
|
| 1949 |
+
},
|
| 1950 |
+
{
|
| 1951 |
+
"epoch": 8.54,
|
| 1952 |
+
"eval_gen_len": 245.2081,
|
| 1953 |
+
"eval_loss": 3.2731070518493652,
|
| 1954 |
+
"eval_rouge1": 46.1971,
|
| 1955 |
+
"eval_rouge2": 17.7962,
|
| 1956 |
+
"eval_rougeL": 24.2279,
|
| 1957 |
+
"eval_rougeLsum": 42.3853,
|
| 1958 |
+
"eval_runtime": 1087.3894,
|
| 1959 |
+
"eval_samples_per_second": 5.17,
|
| 1960 |
+
"eval_steps_per_second": 0.324,
|
| 1961 |
+
"step": 24000
|
| 1962 |
+
},
|
| 1963 |
+
{
|
| 1964 |
+
"epoch": 8.58,
|
| 1965 |
+
"learning_rate": 1.2106666666666667e-06,
|
| 1966 |
+
"loss": 2.9974,
|
| 1967 |
+
"step": 24100
|
| 1968 |
+
},
|
| 1969 |
+
{
|
| 1970 |
+
"epoch": 8.61,
|
| 1971 |
+
"learning_rate": 1.0773333333333332e-06,
|
| 1972 |
+
"loss": 2.9955,
|
| 1973 |
+
"step": 24200
|
| 1974 |
+
},
|
| 1975 |
+
{
|
| 1976 |
+
"epoch": 8.65,
|
| 1977 |
+
"learning_rate": 9.44e-07,
|
| 1978 |
+
"loss": 2.9914,
|
| 1979 |
+
"step": 24300
|
| 1980 |
+
},
|
| 1981 |
+
{
|
| 1982 |
+
"epoch": 8.68,
|
| 1983 |
+
"learning_rate": 8.106666666666667e-07,
|
| 1984 |
+
"loss": 2.9803,
|
| 1985 |
+
"step": 24400
|
| 1986 |
+
},
|
| 1987 |
+
{
|
| 1988 |
+
"epoch": 8.72,
|
| 1989 |
+
"learning_rate": 6.773333333333334e-07,
|
| 1990 |
+
"loss": 2.9788,
|
| 1991 |
+
"step": 24500
|
| 1992 |
+
},
|
| 1993 |
+
{
|
| 1994 |
+
"epoch": 8.72,
|
| 1995 |
+
"eval_gen_len": 240.1747,
|
| 1996 |
+
"eval_loss": 3.2718217372894287,
|
| 1997 |
+
"eval_rouge1": 46.0806,
|
| 1998 |
+
"eval_rouge2": 17.8417,
|
| 1999 |
+
"eval_rougeL": 24.3261,
|
| 2000 |
+
"eval_rougeLsum": 42.264,
|
| 2001 |
+
"eval_runtime": 1088.0734,
|
| 2002 |
+
"eval_samples_per_second": 5.167,
|
| 2003 |
+
"eval_steps_per_second": 0.324,
|
| 2004 |
+
"step": 24500
|
| 2005 |
+
},
|
| 2006 |
+
{
|
| 2007 |
+
"epoch": 8.75,
|
| 2008 |
+
"learning_rate": 5.44e-07,
|
| 2009 |
+
"loss": 3.001,
|
| 2010 |
+
"step": 24600
|
| 2011 |
+
},
|
| 2012 |
+
{
|
| 2013 |
+
"epoch": 8.79,
|
| 2014 |
+
"learning_rate": 4.106666666666667e-07,
|
| 2015 |
+
"loss": 2.9962,
|
| 2016 |
+
"step": 24700
|
| 2017 |
+
},
|
| 2018 |
+
{
|
| 2019 |
+
"epoch": 8.83,
|
| 2020 |
+
"learning_rate": 2.7733333333333333e-07,
|
| 2021 |
+
"loss": 2.9987,
|
| 2022 |
+
"step": 24800
|
| 2023 |
+
},
|
| 2024 |
+
{
|
| 2025 |
+
"epoch": 8.86,
|
| 2026 |
+
"learning_rate": 1.44e-07,
|
| 2027 |
+
"loss": 2.9703,
|
| 2028 |
+
"step": 24900
|
| 2029 |
+
},
|
| 2030 |
+
{
|
| 2031 |
+
"epoch": 8.9,
|
| 2032 |
+
"learning_rate": 1.0666666666666668e-08,
|
| 2033 |
+
"loss": 2.9878,
|
| 2034 |
+
"step": 25000
|
| 2035 |
+
},
|
| 2036 |
+
{
|
| 2037 |
+
"epoch": 8.9,
|
| 2038 |
+
"eval_gen_len": 242.5598,
|
| 2039 |
+
"eval_loss": 3.2715346813201904,
|
| 2040 |
+
"eval_rouge1": 46.0618,
|
| 2041 |
+
"eval_rouge2": 17.7725,
|
| 2042 |
+
"eval_rougeL": 24.2234,
|
| 2043 |
+
"eval_rougeLsum": 42.2574,
|
| 2044 |
+
"eval_runtime": 1097.8453,
|
| 2045 |
+
"eval_samples_per_second": 5.121,
|
| 2046 |
+
"eval_steps_per_second": 0.321,
|
| 2047 |
+
"step": 25000
|
| 2048 |
+
},
|
| 2049 |
+
{
|
| 2050 |
+
"epoch": 8.9,
|
| 2051 |
+
"step": 25000,
|
| 2052 |
+
"total_flos": 5.0265269514797056e+17,
|
| 2053 |
+
"train_loss": 3.1441598370170594,
|
| 2054 |
+
"train_runtime": 61182.0827,
|
| 2055 |
+
"train_samples_per_second": 6.538,
|
| 2056 |
+
"train_steps_per_second": 0.409
|
| 2057 |
+
}
|
| 2058 |
+
],
|
| 2059 |
+
"max_steps": 25000,
|
| 2060 |
+
"num_train_epochs": 9,
|
| 2061 |
+
"total_flos": 5.0265269514797056e+17,
|
| 2062 |
+
"trial_name": null,
|
| 2063 |
+
"trial_params": null
|
| 2064 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a26637dd6829cdcfa499a6b04e5f8f0ce5d170dea7ba86bd9a7fce0863d6ab4f
|
| 3 |
+
size 3439
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|