gsarti commited on
Commit
e11ee6c
1 Parent(s): b01f976

Initial commit

Browse files
README.md CHANGED
@@ -1,3 +1,103 @@
1
  ---
2
- license: apache-2.0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
+ license: mit
3
+ tags:
4
+ - generated_from_trainer
5
+ datasets:
6
+ - it5/datasets
7
+ metrics:
8
+ - rouge
9
+ model-index:
10
+ - name: it5-efficient-small-el32-fst-f2i-0.0003
11
+ results:
12
+ - task:
13
+ name: Summarization
14
+ type: summarization
15
+ dataset:
16
+ name: it5/datasets fst
17
+ type: it5/datasets
18
+ args: fst
19
+ metrics:
20
+ - name: Rouge1
21
+ type: rouge
22
+ value: 56.585
23
  ---
24
+
25
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
26
+ should probably proofread and complete it, then remove this comment. -->
27
+
28
+ # it5-efficient-small-el32-fst-f2i-0.0003
29
+
30
+ This model is a fine-tuned version of [stefan-it/it5-efficient-small-el32](https://huggingface.co/stefan-it/it5-efficient-small-el32) on the it5/datasets fst dataset.
31
+ It achieves the following results on the evaluation set:
32
+ - Loss: 2.2160
33
+ - Rouge1: 56.585
34
+ - Rouge2: 36.9335
35
+ - Rougel: 53.7782
36
+ - Rougelsum: 53.7779
37
+ - Gen Len: 13.0891
38
+
39
+ ## Model description
40
+
41
+ More information needed
42
+
43
+ ## Intended uses & limitations
44
+
45
+ More information needed
46
+
47
+ ## Training and evaluation data
48
+
49
+ More information needed
50
+
51
+ ## Training procedure
52
+
53
+ ### Training hyperparameters
54
+
55
+ The following hyperparameters were used during training:
56
+ - learning_rate: 0.0003
57
+ - train_batch_size: 8
58
+ - eval_batch_size: 8
59
+ - seed: 42
60
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
61
+ - lr_scheduler_type: linear
62
+ - num_epochs: 10.0
63
+
64
+ ### Training results
65
+
66
+ | Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
67
+ |:-------------:|:-----:|:------:|:---------------:|:-------:|:-------:|:-------:|:---------:|:-------:|
68
+ | 2.9377 | 0.35 | 5000 | 2.5157 | 54.6148 | 35.1518 | 51.8908 | 51.8957 | 12.8717 |
69
+ | 2.803 | 0.7 | 10000 | 2.4086 | 55.641 | 36.1214 | 52.8683 | 52.8572 | 12.7513 |
70
+ | 2.5483 | 1.05 | 15000 | 2.3420 | 55.6604 | 36.0085 | 52.9599 | 52.9433 | 12.7754 |
71
+ | 2.4978 | 1.39 | 20000 | 2.3145 | 56.204 | 36.5896 | 53.338 | 53.3351 | 12.8804 |
72
+ | 2.5383 | 1.74 | 25000 | 2.2697 | 56.1356 | 36.6963 | 53.3579 | 53.3664 | 12.795 |
73
+ | 2.3368 | 2.09 | 30000 | 2.2603 | 56.0271 | 36.4249 | 53.3113 | 53.3272 | 12.7478 |
74
+ | 2.371 | 2.44 | 35000 | 2.2328 | 56.5041 | 36.8718 | 53.8064 | 53.7995 | 12.8243 |
75
+ | 2.3567 | 2.79 | 40000 | 2.2079 | 56.5318 | 36.9437 | 53.8359 | 53.8254 | 12.6851 |
76
+ | 2.1753 | 3.14 | 45000 | 2.2168 | 56.3831 | 36.8896 | 53.6542 | 53.6708 | 12.67 |
77
+ | 2.2069 | 3.48 | 50000 | 2.2055 | 56.7171 | 37.1665 | 53.9299 | 53.9259 | 12.8014 |
78
+ | 2.2396 | 3.83 | 55000 | 2.1801 | 56.936 | 37.5465 | 54.1064 | 54.1125 | 12.7989 |
79
+ | 2.0657 | 4.18 | 60000 | 2.1915 | 56.6312 | 37.1618 | 53.8646 | 53.8791 | 12.6987 |
80
+ | 2.0806 | 4.53 | 65000 | 2.1809 | 56.6599 | 37.1282 | 53.8838 | 53.8781 | 12.715 |
81
+ | 2.0933 | 4.88 | 70000 | 2.1771 | 56.5891 | 36.9461 | 53.8058 | 53.8087 | 12.6593 |
82
+ | 1.9949 | 5.23 | 75000 | 2.1932 | 56.4956 | 36.9679 | 53.7634 | 53.7731 | 12.6723 |
83
+ | 1.9954 | 5.57 | 80000 | 2.1813 | 56.4827 | 36.8319 | 53.6397 | 53.6399 | 12.6599 |
84
+ | 1.9912 | 5.92 | 85000 | 2.1755 | 56.6723 | 37.0432 | 53.8339 | 53.8233 | 12.7534 |
85
+ | 1.9068 | 6.27 | 90000 | 2.1849 | 56.6574 | 37.0691 | 53.9029 | 53.892 | 12.7037 |
86
+ | 1.9173 | 6.62 | 95000 | 2.1787 | 56.5701 | 36.861 | 53.6855 | 53.6699 | 12.6467 |
87
+ | 1.9131 | 6.97 | 100000 | 2.1862 | 56.7175 | 37.0749 | 53.8761 | 53.8794 | 12.7072 |
88
+ | 1.8164 | 7.32 | 105000 | 2.1999 | 56.6104 | 37.0809 | 53.8098 | 53.8216 | 12.6364 |
89
+ | 1.8489 | 7.66 | 110000 | 2.1945 | 56.6645 | 37.1267 | 53.9009 | 53.9008 | 12.5741 |
90
+ | 1.82 | 8.01 | 115000 | 2.2075 | 56.6075 | 37.0359 | 53.8792 | 53.8833 | 12.6428 |
91
+ | 1.772 | 8.36 | 120000 | 2.2067 | 56.4716 | 36.8675 | 53.6826 | 53.6742 | 12.6591 |
92
+ | 1.7795 | 8.71 | 125000 | 2.2056 | 56.4112 | 36.9011 | 53.6554 | 53.6495 | 12.608 |
93
+ | 1.72 | 9.06 | 130000 | 2.2197 | 56.4735 | 36.9255 | 53.6592 | 53.6463 | 12.6758 |
94
+ | 1.7174 | 9.41 | 135000 | 2.2169 | 56.4209 | 36.8139 | 53.5778 | 53.5685 | 12.6568 |
95
+ | 1.7466 | 9.75 | 140000 | 2.2165 | 56.3715 | 36.767 | 53.555 | 53.5468 | 12.6416 |
96
+
97
+
98
+ ### Framework versions
99
+
100
+ - Transformers 4.15.0
101
+ - Pytorch 1.10.0+cu102
102
+ - Datasets 1.17.0
103
+ - Tokenizers 0.10.3
all_results.json ADDED
@@ -0,0 +1,18 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 10.0,
3
+ "eval_gen_len": 13.0891,
4
+ "eval_loss": 2.216015100479126,
5
+ "eval_rouge1": 56.585,
6
+ "eval_rouge2": 36.9335,
7
+ "eval_rougeL": 53.7782,
8
+ "eval_rougeLsum": 53.7779,
9
+ "eval_runtime": 130.6991,
10
+ "eval_samples": 4849,
11
+ "eval_samples_per_second": 37.1,
12
+ "eval_steps_per_second": 4.644,
13
+ "train_loss": 2.137477010615576,
14
+ "train_runtime": 24602.576,
15
+ "train_samples": 114830,
16
+ "train_samples_per_second": 46.674,
17
+ "train_steps_per_second": 5.834
18
+ }
config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": ".",
3
+ "architectures": [
4
+ "T5ForConditionalGeneration"
5
+ ],
6
+ "d_ff": 2048,
7
+ "d_kv": 64,
8
+ "d_model": 512,
9
+ "decoder_start_token_id": 0,
10
+ "dropout_rate": 0.1,
11
+ "eos_token_id": 1,
12
+ "feed_forward_proj": "relu",
13
+ "initializer_factor": 1.0,
14
+ "is_encoder_decoder": true,
15
+ "layer_norm_epsilon": 1e-06,
16
+ "model_type": "t5",
17
+ "n_positions": 512,
18
+ "num_decoder_layers": 6,
19
+ "num_heads": 8,
20
+ "num_layers": 32,
21
+ "output_past": true,
22
+ "pad_token_id": 0,
23
+ "relative_attention_max_distance": 128,
24
+ "relative_attention_num_buckets": 32,
25
+ "torch_dtype": "float32",
26
+ "transformers_version": "4.15.0",
27
+ "use_cache": true,
28
+ "vocab_size": 32100
29
+ }
eval_results.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 10.0,
3
+ "eval_gen_len": 13.0891,
4
+ "eval_loss": 2.216015100479126,
5
+ "eval_rouge1": 56.585,
6
+ "eval_rouge2": 36.9335,
7
+ "eval_rougeL": 53.7782,
8
+ "eval_rougeLsum": 53.7779,
9
+ "eval_runtime": 130.6991,
10
+ "eval_samples": 4849,
11
+ "eval_samples_per_second": 37.1,
12
+ "eval_steps_per_second": 4.644
13
+ }
events.out.tfevents.1650990572.pg-gpu10.21629.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed3879438e614261786121577c8f834356660a1b1583d73894f02091c9136126
3
+ size 575
flax_model.msgpack ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:28498691275cf13116fde642f4ca19cbd3922087cec9cebc490ba20b938ededd
3
+ size 569246164
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf7dfe92ee95be47bb037cff6176bf7e4b5858e3ff15d60eea10ab38cabaeaf5
3
+ size 569387035
special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "additional_special_tokens": ["<extra_id_0>", "<extra_id_1>", "<extra_id_2>", "<extra_id_3>", "<extra_id_4>", "<extra_id_5>", "<extra_id_6>", "<extra_id_7>", "<extra_id_8>", "<extra_id_9>", "<extra_id_10>", "<extra_id_11>", "<extra_id_12>", "<extra_id_13>", "<extra_id_14>", "<extra_id_15>", "<extra_id_16>", "<extra_id_17>", "<extra_id_18>", "<extra_id_19>", "<extra_id_20>", "<extra_id_21>", "<extra_id_22>", "<extra_id_23>", "<extra_id_24>", "<extra_id_25>", "<extra_id_26>", "<extra_id_27>", "<extra_id_28>", "<extra_id_29>", "<extra_id_30>", "<extra_id_31>", "<extra_id_32>", "<extra_id_33>", "<extra_id_34>", "<extra_id_35>", "<extra_id_36>", "<extra_id_37>", "<extra_id_38>", "<extra_id_39>", "<extra_id_40>", "<extra_id_41>", "<extra_id_42>", "<extra_id_43>", "<extra_id_44>", "<extra_id_45>", "<extra_id_46>", "<extra_id_47>", "<extra_id_48>", "<extra_id_49>", "<extra_id_50>", "<extra_id_51>", "<extra_id_52>", "<extra_id_53>", "<extra_id_54>", "<extra_id_55>", "<extra_id_56>", "<extra_id_57>", "<extra_id_58>", "<extra_id_59>", "<extra_id_60>", "<extra_id_61>", "<extra_id_62>", "<extra_id_63>", "<extra_id_64>", "<extra_id_65>", "<extra_id_66>", "<extra_id_67>", "<extra_id_68>", "<extra_id_69>", "<extra_id_70>", "<extra_id_71>", "<extra_id_72>", "<extra_id_73>", "<extra_id_74>", "<extra_id_75>", "<extra_id_76>", "<extra_id_77>", "<extra_id_78>", "<extra_id_79>", "<extra_id_80>", "<extra_id_81>", "<extra_id_82>", "<extra_id_83>", "<extra_id_84>", "<extra_id_85>", "<extra_id_86>", "<extra_id_87>", "<extra_id_88>", "<extra_id_89>", "<extra_id_90>", "<extra_id_91>", "<extra_id_92>", "<extra_id_93>", "<extra_id_94>", "<extra_id_95>", "<extra_id_96>", "<extra_id_97>", "<extra_id_98>", "<extra_id_99>"]}
spiece.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2dffd01fc009b7e92d98eddff8853983e271b41302ed0d363000e8581df12000
3
+ size 817200
tf_model.h5 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:34af5ad7f47c17bdd8839e7c18e80027dc97b166da413fdd3c6009db94f8d5ae
3
+ size 569947488
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "extra_ids": 100, "additional_special_tokens": ["<extra_id_0>", "<extra_id_1>", "<extra_id_2>", "<extra_id_3>", "<extra_id_4>", "<extra_id_5>", "<extra_id_6>", "<extra_id_7>", "<extra_id_8>", "<extra_id_9>", "<extra_id_10>", "<extra_id_11>", "<extra_id_12>", "<extra_id_13>", "<extra_id_14>", "<extra_id_15>", "<extra_id_16>", "<extra_id_17>", "<extra_id_18>", "<extra_id_19>", "<extra_id_20>", "<extra_id_21>", "<extra_id_22>", "<extra_id_23>", "<extra_id_24>", "<extra_id_25>", "<extra_id_26>", "<extra_id_27>", "<extra_id_28>", "<extra_id_29>", "<extra_id_30>", "<extra_id_31>", "<extra_id_32>", "<extra_id_33>", "<extra_id_34>", "<extra_id_35>", "<extra_id_36>", "<extra_id_37>", "<extra_id_38>", "<extra_id_39>", "<extra_id_40>", "<extra_id_41>", "<extra_id_42>", "<extra_id_43>", "<extra_id_44>", "<extra_id_45>", "<extra_id_46>", "<extra_id_47>", "<extra_id_48>", "<extra_id_49>", "<extra_id_50>", "<extra_id_51>", "<extra_id_52>", "<extra_id_53>", "<extra_id_54>", "<extra_id_55>", "<extra_id_56>", "<extra_id_57>", "<extra_id_58>", "<extra_id_59>", "<extra_id_60>", "<extra_id_61>", "<extra_id_62>", "<extra_id_63>", "<extra_id_64>", "<extra_id_65>", "<extra_id_66>", "<extra_id_67>", "<extra_id_68>", "<extra_id_69>", "<extra_id_70>", "<extra_id_71>", "<extra_id_72>", "<extra_id_73>", "<extra_id_74>", "<extra_id_75>", "<extra_id_76>", "<extra_id_77>", "<extra_id_78>", "<extra_id_79>", "<extra_id_80>", "<extra_id_81>", "<extra_id_82>", "<extra_id_83>", "<extra_id_84>", "<extra_id_85>", "<extra_id_86>", "<extra_id_87>", "<extra_id_88>", "<extra_id_89>", "<extra_id_90>", "<extra_id_91>", "<extra_id_92>", "<extra_id_93>", "<extra_id_94>", "<extra_id_95>", "<extra_id_96>", "<extra_id_97>", "<extra_id_98>", "<extra_id_99>"], "special_tokens_map_file": null, "name_or_path": "stefan-it/it5-efficient-small-el32", "sp_model_kwargs": {}, "tokenizer_class": "T5Tokenizer"}
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 10.0,
3
+ "train_loss": 2.137477010615576,
4
+ "train_runtime": 24602.576,
5
+ "train_samples": 114830,
6
+ "train_samples_per_second": 46.674,
7
+ "train_steps_per_second": 5.834
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,2111 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 10.0,
5
+ "global_step": 143540,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.03,
12
+ "learning_rate": 0.00029895499512331056,
13
+ "loss": 4.0695,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 0.07,
18
+ "learning_rate": 0.00029790999024662115,
19
+ "loss": 3.433,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 0.1,
24
+ "learning_rate": 0.0002968649853699317,
25
+ "loss": 3.198,
26
+ "step": 1500
27
+ },
28
+ {
29
+ "epoch": 0.14,
30
+ "learning_rate": 0.00029581998049324227,
31
+ "loss": 3.1807,
32
+ "step": 2000
33
+ },
34
+ {
35
+ "epoch": 0.17,
36
+ "learning_rate": 0.00029477497561655286,
37
+ "loss": 3.0421,
38
+ "step": 2500
39
+ },
40
+ {
41
+ "epoch": 0.21,
42
+ "learning_rate": 0.00029372997073986344,
43
+ "loss": 3.0883,
44
+ "step": 3000
45
+ },
46
+ {
47
+ "epoch": 0.24,
48
+ "learning_rate": 0.00029268496586317403,
49
+ "loss": 3.0714,
50
+ "step": 3500
51
+ },
52
+ {
53
+ "epoch": 0.28,
54
+ "learning_rate": 0.00029163996098648457,
55
+ "loss": 2.979,
56
+ "step": 4000
57
+ },
58
+ {
59
+ "epoch": 0.31,
60
+ "learning_rate": 0.00029059495610979515,
61
+ "loss": 2.9596,
62
+ "step": 4500
63
+ },
64
+ {
65
+ "epoch": 0.35,
66
+ "learning_rate": 0.00028954995123310574,
67
+ "loss": 2.9377,
68
+ "step": 5000
69
+ },
70
+ {
71
+ "epoch": 0.35,
72
+ "eval_gen_len": 12.8717,
73
+ "eval_loss": 2.5157084465026855,
74
+ "eval_rouge1": 54.6148,
75
+ "eval_rouge2": 35.1518,
76
+ "eval_rougeL": 51.8908,
77
+ "eval_rougeLsum": 51.8957,
78
+ "eval_runtime": 122.2396,
79
+ "eval_samples_per_second": 39.668,
80
+ "eval_steps_per_second": 4.966,
81
+ "step": 5000
82
+ },
83
+ {
84
+ "epoch": 0.38,
85
+ "learning_rate": 0.0002885049463564163,
86
+ "loss": 2.9158,
87
+ "step": 5500
88
+ },
89
+ {
90
+ "epoch": 0.42,
91
+ "learning_rate": 0.0002874599414797269,
92
+ "loss": 2.9109,
93
+ "step": 6000
94
+ },
95
+ {
96
+ "epoch": 0.45,
97
+ "learning_rate": 0.00028641493660303745,
98
+ "loss": 2.857,
99
+ "step": 6500
100
+ },
101
+ {
102
+ "epoch": 0.49,
103
+ "learning_rate": 0.00028536993172634804,
104
+ "loss": 2.9129,
105
+ "step": 7000
106
+ },
107
+ {
108
+ "epoch": 0.52,
109
+ "learning_rate": 0.0002843249268496586,
110
+ "loss": 2.8741,
111
+ "step": 7500
112
+ },
113
+ {
114
+ "epoch": 0.56,
115
+ "learning_rate": 0.00028327992197296916,
116
+ "loss": 2.8337,
117
+ "step": 8000
118
+ },
119
+ {
120
+ "epoch": 0.59,
121
+ "learning_rate": 0.00028223491709627975,
122
+ "loss": 2.7539,
123
+ "step": 8500
124
+ },
125
+ {
126
+ "epoch": 0.63,
127
+ "learning_rate": 0.00028118991221959033,
128
+ "loss": 2.8348,
129
+ "step": 9000
130
+ },
131
+ {
132
+ "epoch": 0.66,
133
+ "learning_rate": 0.0002801449073429009,
134
+ "loss": 2.8118,
135
+ "step": 9500
136
+ },
137
+ {
138
+ "epoch": 0.7,
139
+ "learning_rate": 0.0002790999024662115,
140
+ "loss": 2.803,
141
+ "step": 10000
142
+ },
143
+ {
144
+ "epoch": 0.7,
145
+ "eval_gen_len": 12.7513,
146
+ "eval_loss": 2.4086406230926514,
147
+ "eval_rouge1": 55.641,
148
+ "eval_rouge2": 36.1214,
149
+ "eval_rougeL": 52.8683,
150
+ "eval_rougeLsum": 52.8572,
151
+ "eval_runtime": 124.3863,
152
+ "eval_samples_per_second": 38.983,
153
+ "eval_steps_per_second": 4.88,
154
+ "step": 10000
155
+ },
156
+ {
157
+ "epoch": 0.73,
158
+ "learning_rate": 0.00027805489758952204,
159
+ "loss": 2.7639,
160
+ "step": 10500
161
+ },
162
+ {
163
+ "epoch": 0.77,
164
+ "learning_rate": 0.00027700989271283263,
165
+ "loss": 2.7668,
166
+ "step": 11000
167
+ },
168
+ {
169
+ "epoch": 0.8,
170
+ "learning_rate": 0.0002759648878361432,
171
+ "loss": 2.7692,
172
+ "step": 11500
173
+ },
174
+ {
175
+ "epoch": 0.84,
176
+ "learning_rate": 0.0002749198829594538,
177
+ "loss": 2.7589,
178
+ "step": 12000
179
+ },
180
+ {
181
+ "epoch": 0.87,
182
+ "learning_rate": 0.00027387487808276434,
183
+ "loss": 2.7104,
184
+ "step": 12500
185
+ },
186
+ {
187
+ "epoch": 0.91,
188
+ "learning_rate": 0.0002728298732060749,
189
+ "loss": 2.7085,
190
+ "step": 13000
191
+ },
192
+ {
193
+ "epoch": 0.94,
194
+ "learning_rate": 0.0002717848683293855,
195
+ "loss": 2.734,
196
+ "step": 13500
197
+ },
198
+ {
199
+ "epoch": 0.98,
200
+ "learning_rate": 0.0002707398634526961,
201
+ "loss": 2.7221,
202
+ "step": 14000
203
+ },
204
+ {
205
+ "epoch": 1.01,
206
+ "learning_rate": 0.0002696948585760067,
207
+ "loss": 2.6748,
208
+ "step": 14500
209
+ },
210
+ {
211
+ "epoch": 1.05,
212
+ "learning_rate": 0.0002686498536993172,
213
+ "loss": 2.5483,
214
+ "step": 15000
215
+ },
216
+ {
217
+ "epoch": 1.05,
218
+ "eval_gen_len": 12.7754,
219
+ "eval_loss": 2.341980218887329,
220
+ "eval_rouge1": 55.6604,
221
+ "eval_rouge2": 36.0085,
222
+ "eval_rougeL": 52.9599,
223
+ "eval_rougeLsum": 52.9433,
224
+ "eval_runtime": 121.3998,
225
+ "eval_samples_per_second": 39.942,
226
+ "eval_steps_per_second": 5.0,
227
+ "step": 15000
228
+ },
229
+ {
230
+ "epoch": 1.08,
231
+ "learning_rate": 0.0002676048488226278,
232
+ "loss": 2.5811,
233
+ "step": 15500
234
+ },
235
+ {
236
+ "epoch": 1.11,
237
+ "learning_rate": 0.0002665598439459384,
238
+ "loss": 2.5846,
239
+ "step": 16000
240
+ },
241
+ {
242
+ "epoch": 1.15,
243
+ "learning_rate": 0.00026551483906924893,
244
+ "loss": 2.543,
245
+ "step": 16500
246
+ },
247
+ {
248
+ "epoch": 1.18,
249
+ "learning_rate": 0.00026446983419255957,
250
+ "loss": 2.5682,
251
+ "step": 17000
252
+ },
253
+ {
254
+ "epoch": 1.22,
255
+ "learning_rate": 0.0002634248293158701,
256
+ "loss": 2.5234,
257
+ "step": 17500
258
+ },
259
+ {
260
+ "epoch": 1.25,
261
+ "learning_rate": 0.0002623798244391807,
262
+ "loss": 2.5756,
263
+ "step": 18000
264
+ },
265
+ {
266
+ "epoch": 1.29,
267
+ "learning_rate": 0.0002613348195624913,
268
+ "loss": 2.5471,
269
+ "step": 18500
270
+ },
271
+ {
272
+ "epoch": 1.32,
273
+ "learning_rate": 0.0002602898146858018,
274
+ "loss": 2.5657,
275
+ "step": 19000
276
+ },
277
+ {
278
+ "epoch": 1.36,
279
+ "learning_rate": 0.00025924480980911245,
280
+ "loss": 2.536,
281
+ "step": 19500
282
+ },
283
+ {
284
+ "epoch": 1.39,
285
+ "learning_rate": 0.000258199804932423,
286
+ "loss": 2.4978,
287
+ "step": 20000
288
+ },
289
+ {
290
+ "epoch": 1.39,
291
+ "eval_gen_len": 12.8804,
292
+ "eval_loss": 2.314547061920166,
293
+ "eval_rouge1": 56.204,
294
+ "eval_rouge2": 36.5896,
295
+ "eval_rougeL": 53.338,
296
+ "eval_rougeLsum": 53.3351,
297
+ "eval_runtime": 117.8229,
298
+ "eval_samples_per_second": 41.155,
299
+ "eval_steps_per_second": 5.152,
300
+ "step": 20000
301
+ },
302
+ {
303
+ "epoch": 1.43,
304
+ "learning_rate": 0.0002571548000557336,
305
+ "loss": 2.5415,
306
+ "step": 20500
307
+ },
308
+ {
309
+ "epoch": 1.46,
310
+ "learning_rate": 0.00025610979517904416,
311
+ "loss": 2.5634,
312
+ "step": 21000
313
+ },
314
+ {
315
+ "epoch": 1.5,
316
+ "learning_rate": 0.0002550647903023547,
317
+ "loss": 2.5392,
318
+ "step": 21500
319
+ },
320
+ {
321
+ "epoch": 1.53,
322
+ "learning_rate": 0.00025401978542566534,
323
+ "loss": 2.567,
324
+ "step": 22000
325
+ },
326
+ {
327
+ "epoch": 1.57,
328
+ "learning_rate": 0.00025297478054897587,
329
+ "loss": 2.5332,
330
+ "step": 22500
331
+ },
332
+ {
333
+ "epoch": 1.6,
334
+ "learning_rate": 0.00025192977567228646,
335
+ "loss": 2.5615,
336
+ "step": 23000
337
+ },
338
+ {
339
+ "epoch": 1.64,
340
+ "learning_rate": 0.00025088477079559705,
341
+ "loss": 2.5275,
342
+ "step": 23500
343
+ },
344
+ {
345
+ "epoch": 1.67,
346
+ "learning_rate": 0.0002498397659189076,
347
+ "loss": 2.5342,
348
+ "step": 24000
349
+ },
350
+ {
351
+ "epoch": 1.71,
352
+ "learning_rate": 0.00024879476104221817,
353
+ "loss": 2.5248,
354
+ "step": 24500
355
+ },
356
+ {
357
+ "epoch": 1.74,
358
+ "learning_rate": 0.00024774975616552875,
359
+ "loss": 2.5383,
360
+ "step": 25000
361
+ },
362
+ {
363
+ "epoch": 1.74,
364
+ "eval_gen_len": 12.795,
365
+ "eval_loss": 2.2696738243103027,
366
+ "eval_rouge1": 56.1356,
367
+ "eval_rouge2": 36.6963,
368
+ "eval_rougeL": 53.3579,
369
+ "eval_rougeLsum": 53.3664,
370
+ "eval_runtime": 123.3173,
371
+ "eval_samples_per_second": 39.321,
372
+ "eval_steps_per_second": 4.922,
373
+ "step": 25000
374
+ },
375
+ {
376
+ "epoch": 1.78,
377
+ "learning_rate": 0.00024670475128883934,
378
+ "loss": 2.4931,
379
+ "step": 25500
380
+ },
381
+ {
382
+ "epoch": 1.81,
383
+ "learning_rate": 0.00024565974641214993,
384
+ "loss": 2.4933,
385
+ "step": 26000
386
+ },
387
+ {
388
+ "epoch": 1.85,
389
+ "learning_rate": 0.00024461474153546046,
390
+ "loss": 2.5195,
391
+ "step": 26500
392
+ },
393
+ {
394
+ "epoch": 1.88,
395
+ "learning_rate": 0.00024356973665877105,
396
+ "loss": 2.5158,
397
+ "step": 27000
398
+ },
399
+ {
400
+ "epoch": 1.92,
401
+ "learning_rate": 0.00024252473178208164,
402
+ "loss": 2.5311,
403
+ "step": 27500
404
+ },
405
+ {
406
+ "epoch": 1.95,
407
+ "learning_rate": 0.0002414797269053922,
408
+ "loss": 2.5037,
409
+ "step": 28000
410
+ },
411
+ {
412
+ "epoch": 1.99,
413
+ "learning_rate": 0.00024043472202870276,
414
+ "loss": 2.5134,
415
+ "step": 28500
416
+ },
417
+ {
418
+ "epoch": 2.02,
419
+ "learning_rate": 0.00023938971715201337,
420
+ "loss": 2.4096,
421
+ "step": 29000
422
+ },
423
+ {
424
+ "epoch": 2.06,
425
+ "learning_rate": 0.00023834471227532393,
426
+ "loss": 2.3211,
427
+ "step": 29500
428
+ },
429
+ {
430
+ "epoch": 2.09,
431
+ "learning_rate": 0.00023729970739863452,
432
+ "loss": 2.3368,
433
+ "step": 30000
434
+ },
435
+ {
436
+ "epoch": 2.09,
437
+ "eval_gen_len": 12.7478,
438
+ "eval_loss": 2.260253667831421,
439
+ "eval_rouge1": 56.0271,
440
+ "eval_rouge2": 36.4249,
441
+ "eval_rougeL": 53.3113,
442
+ "eval_rougeLsum": 53.3272,
443
+ "eval_runtime": 122.3509,
444
+ "eval_samples_per_second": 39.632,
445
+ "eval_steps_per_second": 4.961,
446
+ "step": 30000
447
+ },
448
+ {
449
+ "epoch": 2.12,
450
+ "learning_rate": 0.00023625470252194508,
451
+ "loss": 2.3855,
452
+ "step": 30500
453
+ },
454
+ {
455
+ "epoch": 2.16,
456
+ "learning_rate": 0.00023520969764525564,
457
+ "loss": 2.3562,
458
+ "step": 31000
459
+ },
460
+ {
461
+ "epoch": 2.19,
462
+ "learning_rate": 0.00023416469276856623,
463
+ "loss": 2.345,
464
+ "step": 31500
465
+ },
466
+ {
467
+ "epoch": 2.23,
468
+ "learning_rate": 0.00023311968789187682,
469
+ "loss": 2.371,
470
+ "step": 32000
471
+ },
472
+ {
473
+ "epoch": 2.26,
474
+ "learning_rate": 0.00023207468301518738,
475
+ "loss": 2.3653,
476
+ "step": 32500
477
+ },
478
+ {
479
+ "epoch": 2.3,
480
+ "learning_rate": 0.00023102967813849797,
481
+ "loss": 2.3069,
482
+ "step": 33000
483
+ },
484
+ {
485
+ "epoch": 2.33,
486
+ "learning_rate": 0.00022998467326180853,
487
+ "loss": 2.3499,
488
+ "step": 33500
489
+ },
490
+ {
491
+ "epoch": 2.37,
492
+ "learning_rate": 0.0002289396683851191,
493
+ "loss": 2.3479,
494
+ "step": 34000
495
+ },
496
+ {
497
+ "epoch": 2.4,
498
+ "learning_rate": 0.00022789466350842967,
499
+ "loss": 2.3473,
500
+ "step": 34500
501
+ },
502
+ {
503
+ "epoch": 2.44,
504
+ "learning_rate": 0.00022684965863174026,
505
+ "loss": 2.371,
506
+ "step": 35000
507
+ },
508
+ {
509
+ "epoch": 2.44,
510
+ "eval_gen_len": 12.8243,
511
+ "eval_loss": 2.2327780723571777,
512
+ "eval_rouge1": 56.5041,
513
+ "eval_rouge2": 36.8718,
514
+ "eval_rougeL": 53.8064,
515
+ "eval_rougeLsum": 53.7995,
516
+ "eval_runtime": 122.1132,
517
+ "eval_samples_per_second": 39.709,
518
+ "eval_steps_per_second": 4.971,
519
+ "step": 35000
520
+ },
521
+ {
522
+ "epoch": 2.47,
523
+ "learning_rate": 0.00022580465375505085,
524
+ "loss": 2.3728,
525
+ "step": 35500
526
+ },
527
+ {
528
+ "epoch": 2.51,
529
+ "learning_rate": 0.0002247596488783614,
530
+ "loss": 2.3489,
531
+ "step": 36000
532
+ },
533
+ {
534
+ "epoch": 2.54,
535
+ "learning_rate": 0.00022371464400167197,
536
+ "loss": 2.4012,
537
+ "step": 36500
538
+ },
539
+ {
540
+ "epoch": 2.58,
541
+ "learning_rate": 0.00022266963912498256,
542
+ "loss": 2.3648,
543
+ "step": 37000
544
+ },
545
+ {
546
+ "epoch": 2.61,
547
+ "learning_rate": 0.00022162463424829312,
548
+ "loss": 2.3887,
549
+ "step": 37500
550
+ },
551
+ {
552
+ "epoch": 2.65,
553
+ "learning_rate": 0.00022057962937160373,
554
+ "loss": 2.3375,
555
+ "step": 38000
556
+ },
557
+ {
558
+ "epoch": 2.68,
559
+ "learning_rate": 0.0002195346244949143,
560
+ "loss": 2.3742,
561
+ "step": 38500
562
+ },
563
+ {
564
+ "epoch": 2.72,
565
+ "learning_rate": 0.00021848961961822485,
566
+ "loss": 2.3393,
567
+ "step": 39000
568
+ },
569
+ {
570
+ "epoch": 2.75,
571
+ "learning_rate": 0.00021744461474153544,
572
+ "loss": 2.327,
573
+ "step": 39500
574
+ },
575
+ {
576
+ "epoch": 2.79,
577
+ "learning_rate": 0.000216399609864846,
578
+ "loss": 2.3567,
579
+ "step": 40000
580
+ },
581
+ {
582
+ "epoch": 2.79,
583
+ "eval_gen_len": 12.6851,
584
+ "eval_loss": 2.207930088043213,
585
+ "eval_rouge1": 56.5318,
586
+ "eval_rouge2": 36.9437,
587
+ "eval_rougeL": 53.8359,
588
+ "eval_rougeLsum": 53.8254,
589
+ "eval_runtime": 117.7084,
590
+ "eval_samples_per_second": 41.195,
591
+ "eval_steps_per_second": 5.157,
592
+ "step": 40000
593
+ },
594
+ {
595
+ "epoch": 2.82,
596
+ "learning_rate": 0.0002153546049881566,
597
+ "loss": 2.3582,
598
+ "step": 40500
599
+ },
600
+ {
601
+ "epoch": 2.86,
602
+ "learning_rate": 0.00021430960011146718,
603
+ "loss": 2.3617,
604
+ "step": 41000
605
+ },
606
+ {
607
+ "epoch": 2.89,
608
+ "learning_rate": 0.00021326459523477774,
609
+ "loss": 2.3521,
610
+ "step": 41500
611
+ },
612
+ {
613
+ "epoch": 2.93,
614
+ "learning_rate": 0.00021221959035808832,
615
+ "loss": 2.3396,
616
+ "step": 42000
617
+ },
618
+ {
619
+ "epoch": 2.96,
620
+ "learning_rate": 0.00021117458548139888,
621
+ "loss": 2.3598,
622
+ "step": 42500
623
+ },
624
+ {
625
+ "epoch": 3.0,
626
+ "learning_rate": 0.00021012958060470945,
627
+ "loss": 2.3396,
628
+ "step": 43000
629
+ },
630
+ {
631
+ "epoch": 3.03,
632
+ "learning_rate": 0.00020908457572802006,
633
+ "loss": 2.1784,
634
+ "step": 43500
635
+ },
636
+ {
637
+ "epoch": 3.07,
638
+ "learning_rate": 0.00020803957085133062,
639
+ "loss": 2.2141,
640
+ "step": 44000
641
+ },
642
+ {
643
+ "epoch": 3.1,
644
+ "learning_rate": 0.0002069945659746412,
645
+ "loss": 2.2108,
646
+ "step": 44500
647
+ },
648
+ {
649
+ "epoch": 3.14,
650
+ "learning_rate": 0.00020594956109795177,
651
+ "loss": 2.1753,
652
+ "step": 45000
653
+ },
654
+ {
655
+ "epoch": 3.14,
656
+ "eval_gen_len": 12.67,
657
+ "eval_loss": 2.216768980026245,
658
+ "eval_rouge1": 56.3831,
659
+ "eval_rouge2": 36.8896,
660
+ "eval_rougeL": 53.6542,
661
+ "eval_rougeLsum": 53.6708,
662
+ "eval_runtime": 116.3323,
663
+ "eval_samples_per_second": 41.682,
664
+ "eval_steps_per_second": 5.218,
665
+ "step": 45000
666
+ },
667
+ {
668
+ "epoch": 3.17,
669
+ "learning_rate": 0.00020490455622126233,
670
+ "loss": 2.1618,
671
+ "step": 45500
672
+ },
673
+ {
674
+ "epoch": 3.2,
675
+ "learning_rate": 0.00020385955134457294,
676
+ "loss": 2.205,
677
+ "step": 46000
678
+ },
679
+ {
680
+ "epoch": 3.24,
681
+ "learning_rate": 0.0002028145464678835,
682
+ "loss": 2.2087,
683
+ "step": 46500
684
+ },
685
+ {
686
+ "epoch": 3.27,
687
+ "learning_rate": 0.00020176954159119406,
688
+ "loss": 2.1862,
689
+ "step": 47000
690
+ },
691
+ {
692
+ "epoch": 3.31,
693
+ "learning_rate": 0.00020072453671450465,
694
+ "loss": 2.1947,
695
+ "step": 47500
696
+ },
697
+ {
698
+ "epoch": 3.34,
699
+ "learning_rate": 0.0001996795318378152,
700
+ "loss": 2.203,
701
+ "step": 48000
702
+ },
703
+ {
704
+ "epoch": 3.38,
705
+ "learning_rate": 0.00019863452696112583,
706
+ "loss": 2.2225,
707
+ "step": 48500
708
+ },
709
+ {
710
+ "epoch": 3.41,
711
+ "learning_rate": 0.0001975895220844364,
712
+ "loss": 2.2253,
713
+ "step": 49000
714
+ },
715
+ {
716
+ "epoch": 3.45,
717
+ "learning_rate": 0.00019654451720774695,
718
+ "loss": 2.2147,
719
+ "step": 49500
720
+ },
721
+ {
722
+ "epoch": 3.48,
723
+ "learning_rate": 0.00019549951233105754,
724
+ "loss": 2.2069,
725
+ "step": 50000
726
+ },
727
+ {
728
+ "epoch": 3.48,
729
+ "eval_gen_len": 12.8014,
730
+ "eval_loss": 2.2055139541625977,
731
+ "eval_rouge1": 56.7171,
732
+ "eval_rouge2": 37.1665,
733
+ "eval_rougeL": 53.9299,
734
+ "eval_rougeLsum": 53.9259,
735
+ "eval_runtime": 120.1221,
736
+ "eval_samples_per_second": 40.367,
737
+ "eval_steps_per_second": 5.053,
738
+ "step": 50000
739
+ },
740
+ {
741
+ "epoch": 3.52,
742
+ "learning_rate": 0.0001944545074543681,
743
+ "loss": 2.2185,
744
+ "step": 50500
745
+ },
746
+ {
747
+ "epoch": 3.55,
748
+ "learning_rate": 0.00019340950257767866,
749
+ "loss": 2.2145,
750
+ "step": 51000
751
+ },
752
+ {
753
+ "epoch": 3.59,
754
+ "learning_rate": 0.00019236449770098927,
755
+ "loss": 2.2661,
756
+ "step": 51500
757
+ },
758
+ {
759
+ "epoch": 3.62,
760
+ "learning_rate": 0.00019131949282429983,
761
+ "loss": 2.2281,
762
+ "step": 52000
763
+ },
764
+ {
765
+ "epoch": 3.66,
766
+ "learning_rate": 0.00019027448794761042,
767
+ "loss": 2.2344,
768
+ "step": 52500
769
+ },
770
+ {
771
+ "epoch": 3.69,
772
+ "learning_rate": 0.00018922948307092098,
773
+ "loss": 2.2283,
774
+ "step": 53000
775
+ },
776
+ {
777
+ "epoch": 3.73,
778
+ "learning_rate": 0.00018818447819423154,
779
+ "loss": 2.2424,
780
+ "step": 53500
781
+ },
782
+ {
783
+ "epoch": 3.76,
784
+ "learning_rate": 0.00018713947331754215,
785
+ "loss": 2.2265,
786
+ "step": 54000
787
+ },
788
+ {
789
+ "epoch": 3.8,
790
+ "learning_rate": 0.00018609446844085271,
791
+ "loss": 2.1928,
792
+ "step": 54500
793
+ },
794
+ {
795
+ "epoch": 3.83,
796
+ "learning_rate": 0.00018504946356416328,
797
+ "loss": 2.2396,
798
+ "step": 55000
799
+ },
800
+ {
801
+ "epoch": 3.83,
802
+ "eval_gen_len": 12.7989,
803
+ "eval_loss": 2.1801397800445557,
804
+ "eval_rouge1": 56.936,
805
+ "eval_rouge2": 37.5465,
806
+ "eval_rougeL": 54.1064,
807
+ "eval_rougeLsum": 54.1125,
808
+ "eval_runtime": 118.0218,
809
+ "eval_samples_per_second": 41.086,
810
+ "eval_steps_per_second": 5.143,
811
+ "step": 55000
812
+ },
813
+ {
814
+ "epoch": 3.87,
815
+ "learning_rate": 0.00018400445868747386,
816
+ "loss": 2.2357,
817
+ "step": 55500
818
+ },
819
+ {
820
+ "epoch": 3.9,
821
+ "learning_rate": 0.00018295945381078442,
822
+ "loss": 2.2118,
823
+ "step": 56000
824
+ },
825
+ {
826
+ "epoch": 3.94,
827
+ "learning_rate": 0.00018191444893409504,
828
+ "loss": 2.226,
829
+ "step": 56500
830
+ },
831
+ {
832
+ "epoch": 3.97,
833
+ "learning_rate": 0.0001808694440574056,
834
+ "loss": 2.213,
835
+ "step": 57000
836
+ },
837
+ {
838
+ "epoch": 4.01,
839
+ "learning_rate": 0.00017982443918071616,
840
+ "loss": 2.2106,
841
+ "step": 57500
842
+ },
843
+ {
844
+ "epoch": 4.04,
845
+ "learning_rate": 0.00017877943430402675,
846
+ "loss": 2.0718,
847
+ "step": 58000
848
+ },
849
+ {
850
+ "epoch": 4.08,
851
+ "learning_rate": 0.0001777344294273373,
852
+ "loss": 2.1013,
853
+ "step": 58500
854
+ },
855
+ {
856
+ "epoch": 4.11,
857
+ "learning_rate": 0.00017668942455064787,
858
+ "loss": 2.0646,
859
+ "step": 59000
860
+ },
861
+ {
862
+ "epoch": 4.15,
863
+ "learning_rate": 0.00017564441967395848,
864
+ "loss": 2.102,
865
+ "step": 59500
866
+ },
867
+ {
868
+ "epoch": 4.18,
869
+ "learning_rate": 0.00017459941479726904,
870
+ "loss": 2.0657,
871
+ "step": 60000
872
+ },
873
+ {
874
+ "epoch": 4.18,
875
+ "eval_gen_len": 12.6987,
876
+ "eval_loss": 2.1915152072906494,
877
+ "eval_rouge1": 56.6312,
878
+ "eval_rouge2": 37.1618,
879
+ "eval_rougeL": 53.8646,
880
+ "eval_rougeLsum": 53.8791,
881
+ "eval_runtime": 116.9251,
882
+ "eval_samples_per_second": 41.471,
883
+ "eval_steps_per_second": 5.191,
884
+ "step": 60000
885
+ },
886
+ {
887
+ "epoch": 4.21,
888
+ "learning_rate": 0.00017355440992057963,
889
+ "loss": 2.0758,
890
+ "step": 60500
891
+ },
892
+ {
893
+ "epoch": 4.25,
894
+ "learning_rate": 0.0001725094050438902,
895
+ "loss": 2.1113,
896
+ "step": 61000
897
+ },
898
+ {
899
+ "epoch": 4.28,
900
+ "learning_rate": 0.00017146440016720075,
901
+ "loss": 2.1134,
902
+ "step": 61500
903
+ },
904
+ {
905
+ "epoch": 4.32,
906
+ "learning_rate": 0.00017041939529051134,
907
+ "loss": 2.1019,
908
+ "step": 62000
909
+ },
910
+ {
911
+ "epoch": 4.35,
912
+ "learning_rate": 0.00016937439041382193,
913
+ "loss": 2.0924,
914
+ "step": 62500
915
+ },
916
+ {
917
+ "epoch": 4.39,
918
+ "learning_rate": 0.00016832938553713249,
919
+ "loss": 2.1106,
920
+ "step": 63000
921
+ },
922
+ {
923
+ "epoch": 4.42,
924
+ "learning_rate": 0.00016728438066044307,
925
+ "loss": 2.1112,
926
+ "step": 63500
927
+ },
928
+ {
929
+ "epoch": 4.46,
930
+ "learning_rate": 0.00016623937578375363,
931
+ "loss": 2.0951,
932
+ "step": 64000
933
+ },
934
+ {
935
+ "epoch": 4.49,
936
+ "learning_rate": 0.00016519437090706422,
937
+ "loss": 2.1011,
938
+ "step": 64500
939
+ },
940
+ {
941
+ "epoch": 4.53,
942
+ "learning_rate": 0.0001641493660303748,
943
+ "loss": 2.0806,
944
+ "step": 65000
945
+ },
946
+ {
947
+ "epoch": 4.53,
948
+ "eval_gen_len": 12.715,
949
+ "eval_loss": 2.180889844894409,
950
+ "eval_rouge1": 56.6599,
951
+ "eval_rouge2": 37.1282,
952
+ "eval_rougeL": 53.8838,
953
+ "eval_rougeLsum": 53.8781,
954
+ "eval_runtime": 116.2111,
955
+ "eval_samples_per_second": 41.726,
956
+ "eval_steps_per_second": 5.223,
957
+ "step": 65000
958
+ },
959
+ {
960
+ "epoch": 4.56,
961
+ "learning_rate": 0.00016310436115368537,
962
+ "loss": 2.1025,
963
+ "step": 65500
964
+ },
965
+ {
966
+ "epoch": 4.6,
967
+ "learning_rate": 0.00016205935627699596,
968
+ "loss": 2.1107,
969
+ "step": 66000
970
+ },
971
+ {
972
+ "epoch": 4.63,
973
+ "learning_rate": 0.00016101435140030652,
974
+ "loss": 2.1125,
975
+ "step": 66500
976
+ },
977
+ {
978
+ "epoch": 4.67,
979
+ "learning_rate": 0.00015996934652361708,
980
+ "loss": 2.0816,
981
+ "step": 67000
982
+ },
983
+ {
984
+ "epoch": 4.7,
985
+ "learning_rate": 0.00015892434164692767,
986
+ "loss": 2.1276,
987
+ "step": 67500
988
+ },
989
+ {
990
+ "epoch": 4.74,
991
+ "learning_rate": 0.00015787933677023825,
992
+ "loss": 2.1125,
993
+ "step": 68000
994
+ },
995
+ {
996
+ "epoch": 4.77,
997
+ "learning_rate": 0.00015683433189354884,
998
+ "loss": 2.1045,
999
+ "step": 68500
1000
+ },
1001
+ {
1002
+ "epoch": 4.81,
1003
+ "learning_rate": 0.0001557893270168594,
1004
+ "loss": 2.1052,
1005
+ "step": 69000
1006
+ },
1007
+ {
1008
+ "epoch": 4.84,
1009
+ "learning_rate": 0.00015474432214016996,
1010
+ "loss": 2.1224,
1011
+ "step": 69500
1012
+ },
1013
+ {
1014
+ "epoch": 4.88,
1015
+ "learning_rate": 0.00015369931726348055,
1016
+ "loss": 2.0933,
1017
+ "step": 70000
1018
+ },
1019
+ {
1020
+ "epoch": 4.88,
1021
+ "eval_gen_len": 12.6593,
1022
+ "eval_loss": 2.1771466732025146,
1023
+ "eval_rouge1": 56.5891,
1024
+ "eval_rouge2": 36.9461,
1025
+ "eval_rougeL": 53.8058,
1026
+ "eval_rougeLsum": 53.8087,
1027
+ "eval_runtime": 119.5299,
1028
+ "eval_samples_per_second": 40.567,
1029
+ "eval_steps_per_second": 5.078,
1030
+ "step": 70000
1031
+ },
1032
+ {
1033
+ "epoch": 4.91,
1034
+ "learning_rate": 0.0001526543123867911,
1035
+ "loss": 2.1076,
1036
+ "step": 70500
1037
+ },
1038
+ {
1039
+ "epoch": 4.95,
1040
+ "learning_rate": 0.0001516093075101017,
1041
+ "loss": 2.0704,
1042
+ "step": 71000
1043
+ },
1044
+ {
1045
+ "epoch": 4.98,
1046
+ "learning_rate": 0.00015056430263341228,
1047
+ "loss": 2.0975,
1048
+ "step": 71500
1049
+ },
1050
+ {
1051
+ "epoch": 5.02,
1052
+ "learning_rate": 0.00014951929775672285,
1053
+ "loss": 2.0603,
1054
+ "step": 72000
1055
+ },
1056
+ {
1057
+ "epoch": 5.05,
1058
+ "learning_rate": 0.00014847429288003343,
1059
+ "loss": 1.9328,
1060
+ "step": 72500
1061
+ },
1062
+ {
1063
+ "epoch": 5.09,
1064
+ "learning_rate": 0.000147429288003344,
1065
+ "loss": 1.9873,
1066
+ "step": 73000
1067
+ },
1068
+ {
1069
+ "epoch": 5.12,
1070
+ "learning_rate": 0.00014638428312665458,
1071
+ "loss": 1.9887,
1072
+ "step": 73500
1073
+ },
1074
+ {
1075
+ "epoch": 5.16,
1076
+ "learning_rate": 0.00014533927824996514,
1077
+ "loss": 1.9416,
1078
+ "step": 74000
1079
+ },
1080
+ {
1081
+ "epoch": 5.19,
1082
+ "learning_rate": 0.00014429427337327573,
1083
+ "loss": 2.0074,
1084
+ "step": 74500
1085
+ },
1086
+ {
1087
+ "epoch": 5.23,
1088
+ "learning_rate": 0.00014324926849658632,
1089
+ "loss": 1.9949,
1090
+ "step": 75000
1091
+ },
1092
+ {
1093
+ "epoch": 5.23,
1094
+ "eval_gen_len": 12.6723,
1095
+ "eval_loss": 2.1931562423706055,
1096
+ "eval_rouge1": 56.4956,
1097
+ "eval_rouge2": 36.9679,
1098
+ "eval_rougeL": 53.7634,
1099
+ "eval_rougeLsum": 53.7731,
1100
+ "eval_runtime": 122.4799,
1101
+ "eval_samples_per_second": 39.59,
1102
+ "eval_steps_per_second": 4.956,
1103
+ "step": 75000
1104
+ },
1105
+ {
1106
+ "epoch": 5.26,
1107
+ "learning_rate": 0.00014220426361989688,
1108
+ "loss": 2.002,
1109
+ "step": 75500
1110
+ },
1111
+ {
1112
+ "epoch": 5.29,
1113
+ "learning_rate": 0.00014115925874320744,
1114
+ "loss": 2.0161,
1115
+ "step": 76000
1116
+ },
1117
+ {
1118
+ "epoch": 5.33,
1119
+ "learning_rate": 0.00014011425386651802,
1120
+ "loss": 2.0139,
1121
+ "step": 76500
1122
+ },
1123
+ {
1124
+ "epoch": 5.36,
1125
+ "learning_rate": 0.0001390692489898286,
1126
+ "loss": 1.9874,
1127
+ "step": 77000
1128
+ },
1129
+ {
1130
+ "epoch": 5.4,
1131
+ "learning_rate": 0.0001380242441131392,
1132
+ "loss": 1.961,
1133
+ "step": 77500
1134
+ },
1135
+ {
1136
+ "epoch": 5.43,
1137
+ "learning_rate": 0.00013697923923644976,
1138
+ "loss": 2.0082,
1139
+ "step": 78000
1140
+ },
1141
+ {
1142
+ "epoch": 5.47,
1143
+ "learning_rate": 0.00013593423435976032,
1144
+ "loss": 2.0175,
1145
+ "step": 78500
1146
+ },
1147
+ {
1148
+ "epoch": 5.5,
1149
+ "learning_rate": 0.0001348892294830709,
1150
+ "loss": 1.987,
1151
+ "step": 79000
1152
+ },
1153
+ {
1154
+ "epoch": 5.54,
1155
+ "learning_rate": 0.0001338442246063815,
1156
+ "loss": 2.0167,
1157
+ "step": 79500
1158
+ },
1159
+ {
1160
+ "epoch": 5.57,
1161
+ "learning_rate": 0.00013279921972969206,
1162
+ "loss": 1.9954,
1163
+ "step": 80000
1164
+ },
1165
+ {
1166
+ "epoch": 5.57,
1167
+ "eval_gen_len": 12.6599,
1168
+ "eval_loss": 2.181297779083252,
1169
+ "eval_rouge1": 56.4827,
1170
+ "eval_rouge2": 36.8319,
1171
+ "eval_rougeL": 53.6397,
1172
+ "eval_rougeLsum": 53.6399,
1173
+ "eval_runtime": 121.225,
1174
+ "eval_samples_per_second": 40.0,
1175
+ "eval_steps_per_second": 5.007,
1176
+ "step": 80000
1177
+ },
1178
+ {
1179
+ "epoch": 5.61,
1180
+ "learning_rate": 0.00013175421485300264,
1181
+ "loss": 1.9816,
1182
+ "step": 80500
1183
+ },
1184
+ {
1185
+ "epoch": 5.64,
1186
+ "learning_rate": 0.0001307092099763132,
1187
+ "loss": 2.0116,
1188
+ "step": 81000
1189
+ },
1190
+ {
1191
+ "epoch": 5.68,
1192
+ "learning_rate": 0.0001296642050996238,
1193
+ "loss": 2.0182,
1194
+ "step": 81500
1195
+ },
1196
+ {
1197
+ "epoch": 5.71,
1198
+ "learning_rate": 0.00012861920022293435,
1199
+ "loss": 2.0032,
1200
+ "step": 82000
1201
+ },
1202
+ {
1203
+ "epoch": 5.75,
1204
+ "learning_rate": 0.00012757419534624494,
1205
+ "loss": 1.9978,
1206
+ "step": 82500
1207
+ },
1208
+ {
1209
+ "epoch": 5.78,
1210
+ "learning_rate": 0.0001265291904695555,
1211
+ "loss": 2.0083,
1212
+ "step": 83000
1213
+ },
1214
+ {
1215
+ "epoch": 5.82,
1216
+ "learning_rate": 0.0001254841855928661,
1217
+ "loss": 2.0017,
1218
+ "step": 83500
1219
+ },
1220
+ {
1221
+ "epoch": 5.85,
1222
+ "learning_rate": 0.00012443918071617665,
1223
+ "loss": 2.0163,
1224
+ "step": 84000
1225
+ },
1226
+ {
1227
+ "epoch": 5.89,
1228
+ "learning_rate": 0.00012339417583948724,
1229
+ "loss": 2.001,
1230
+ "step": 84500
1231
+ },
1232
+ {
1233
+ "epoch": 5.92,
1234
+ "learning_rate": 0.00012234917096279782,
1235
+ "loss": 1.9912,
1236
+ "step": 85000
1237
+ },
1238
+ {
1239
+ "epoch": 5.92,
1240
+ "eval_gen_len": 12.7534,
1241
+ "eval_loss": 2.1754705905914307,
1242
+ "eval_rouge1": 56.6723,
1243
+ "eval_rouge2": 37.0432,
1244
+ "eval_rougeL": 53.8339,
1245
+ "eval_rougeLsum": 53.8233,
1246
+ "eval_runtime": 119.3089,
1247
+ "eval_samples_per_second": 40.642,
1248
+ "eval_steps_per_second": 5.088,
1249
+ "step": 85000
1250
+ },
1251
+ {
1252
+ "epoch": 5.96,
1253
+ "learning_rate": 0.0001213041660861084,
1254
+ "loss": 2.0087,
1255
+ "step": 85500
1256
+ },
1257
+ {
1258
+ "epoch": 5.99,
1259
+ "learning_rate": 0.00012025916120941897,
1260
+ "loss": 1.9864,
1261
+ "step": 86000
1262
+ },
1263
+ {
1264
+ "epoch": 6.03,
1265
+ "learning_rate": 0.00011921415633272953,
1266
+ "loss": 1.9169,
1267
+ "step": 86500
1268
+ },
1269
+ {
1270
+ "epoch": 6.06,
1271
+ "learning_rate": 0.00011816915145604012,
1272
+ "loss": 1.8964,
1273
+ "step": 87000
1274
+ },
1275
+ {
1276
+ "epoch": 6.1,
1277
+ "learning_rate": 0.00011712414657935069,
1278
+ "loss": 1.8886,
1279
+ "step": 87500
1280
+ },
1281
+ {
1282
+ "epoch": 6.13,
1283
+ "learning_rate": 0.00011607914170266128,
1284
+ "loss": 1.9246,
1285
+ "step": 88000
1286
+ },
1287
+ {
1288
+ "epoch": 6.17,
1289
+ "learning_rate": 0.00011503413682597184,
1290
+ "loss": 1.9266,
1291
+ "step": 88500
1292
+ },
1293
+ {
1294
+ "epoch": 6.2,
1295
+ "learning_rate": 0.00011398913194928242,
1296
+ "loss": 1.8718,
1297
+ "step": 89000
1298
+ },
1299
+ {
1300
+ "epoch": 6.24,
1301
+ "learning_rate": 0.000112944127072593,
1302
+ "loss": 1.8617,
1303
+ "step": 89500
1304
+ },
1305
+ {
1306
+ "epoch": 6.27,
1307
+ "learning_rate": 0.00011189912219590358,
1308
+ "loss": 1.9068,
1309
+ "step": 90000
1310
+ },
1311
+ {
1312
+ "epoch": 6.27,
1313
+ "eval_gen_len": 12.7037,
1314
+ "eval_loss": 2.184929847717285,
1315
+ "eval_rouge1": 56.6574,
1316
+ "eval_rouge2": 37.0691,
1317
+ "eval_rougeL": 53.9029,
1318
+ "eval_rougeLsum": 53.892,
1319
+ "eval_runtime": 117.4531,
1320
+ "eval_samples_per_second": 41.285,
1321
+ "eval_steps_per_second": 5.168,
1322
+ "step": 90000
1323
+ },
1324
+ {
1325
+ "epoch": 6.3,
1326
+ "learning_rate": 0.00011085411731921414,
1327
+ "loss": 1.8786,
1328
+ "step": 90500
1329
+ },
1330
+ {
1331
+ "epoch": 6.34,
1332
+ "learning_rate": 0.00010980911244252472,
1333
+ "loss": 1.9071,
1334
+ "step": 91000
1335
+ },
1336
+ {
1337
+ "epoch": 6.37,
1338
+ "learning_rate": 0.0001087641075658353,
1339
+ "loss": 1.8807,
1340
+ "step": 91500
1341
+ },
1342
+ {
1343
+ "epoch": 6.41,
1344
+ "learning_rate": 0.00010771910268914589,
1345
+ "loss": 1.9267,
1346
+ "step": 92000
1347
+ },
1348
+ {
1349
+ "epoch": 6.44,
1350
+ "learning_rate": 0.00010667409781245645,
1351
+ "loss": 1.9136,
1352
+ "step": 92500
1353
+ },
1354
+ {
1355
+ "epoch": 6.48,
1356
+ "learning_rate": 0.00010562909293576702,
1357
+ "loss": 1.9075,
1358
+ "step": 93000
1359
+ },
1360
+ {
1361
+ "epoch": 6.51,
1362
+ "learning_rate": 0.00010458408805907761,
1363
+ "loss": 1.908,
1364
+ "step": 93500
1365
+ },
1366
+ {
1367
+ "epoch": 6.55,
1368
+ "learning_rate": 0.00010353908318238818,
1369
+ "loss": 1.9132,
1370
+ "step": 94000
1371
+ },
1372
+ {
1373
+ "epoch": 6.58,
1374
+ "learning_rate": 0.00010249407830569874,
1375
+ "loss": 1.9013,
1376
+ "step": 94500
1377
+ },
1378
+ {
1379
+ "epoch": 6.62,
1380
+ "learning_rate": 0.00010144907342900933,
1381
+ "loss": 1.9173,
1382
+ "step": 95000
1383
+ },
1384
+ {
1385
+ "epoch": 6.62,
1386
+ "eval_gen_len": 12.6467,
1387
+ "eval_loss": 2.1786956787109375,
1388
+ "eval_rouge1": 56.5701,
1389
+ "eval_rouge2": 36.861,
1390
+ "eval_rougeL": 53.6855,
1391
+ "eval_rougeLsum": 53.6699,
1392
+ "eval_runtime": 120.1115,
1393
+ "eval_samples_per_second": 40.371,
1394
+ "eval_steps_per_second": 5.054,
1395
+ "step": 95000
1396
+ },
1397
+ {
1398
+ "epoch": 6.65,
1399
+ "learning_rate": 0.0001004040685523199,
1400
+ "loss": 1.9182,
1401
+ "step": 95500
1402
+ },
1403
+ {
1404
+ "epoch": 6.69,
1405
+ "learning_rate": 9.935906367563048e-05,
1406
+ "loss": 1.8904,
1407
+ "step": 96000
1408
+ },
1409
+ {
1410
+ "epoch": 6.72,
1411
+ "learning_rate": 9.831405879894105e-05,
1412
+ "loss": 1.9399,
1413
+ "step": 96500
1414
+ },
1415
+ {
1416
+ "epoch": 6.76,
1417
+ "learning_rate": 9.726905392225163e-05,
1418
+ "loss": 1.9188,
1419
+ "step": 97000
1420
+ },
1421
+ {
1422
+ "epoch": 6.79,
1423
+ "learning_rate": 9.622404904556221e-05,
1424
+ "loss": 1.8742,
1425
+ "step": 97500
1426
+ },
1427
+ {
1428
+ "epoch": 6.83,
1429
+ "learning_rate": 9.517904416887279e-05,
1430
+ "loss": 1.9191,
1431
+ "step": 98000
1432
+ },
1433
+ {
1434
+ "epoch": 6.86,
1435
+ "learning_rate": 9.413403929218335e-05,
1436
+ "loss": 1.9207,
1437
+ "step": 98500
1438
+ },
1439
+ {
1440
+ "epoch": 6.9,
1441
+ "learning_rate": 9.308903441549394e-05,
1442
+ "loss": 1.9416,
1443
+ "step": 99000
1444
+ },
1445
+ {
1446
+ "epoch": 6.93,
1447
+ "learning_rate": 9.204402953880451e-05,
1448
+ "loss": 1.9364,
1449
+ "step": 99500
1450
+ },
1451
+ {
1452
+ "epoch": 6.97,
1453
+ "learning_rate": 9.099902466211508e-05,
1454
+ "loss": 1.9131,
1455
+ "step": 100000
1456
+ },
1457
+ {
1458
+ "epoch": 6.97,
1459
+ "eval_gen_len": 12.7072,
1460
+ "eval_loss": 2.186249017715454,
1461
+ "eval_rouge1": 56.7175,
1462
+ "eval_rouge2": 37.0749,
1463
+ "eval_rougeL": 53.8761,
1464
+ "eval_rougeLsum": 53.8794,
1465
+ "eval_runtime": 125.5501,
1466
+ "eval_samples_per_second": 38.622,
1467
+ "eval_steps_per_second": 4.835,
1468
+ "step": 100000
1469
+ },
1470
+ {
1471
+ "epoch": 7.0,
1472
+ "learning_rate": 8.995401978542566e-05,
1473
+ "loss": 1.9358,
1474
+ "step": 100500
1475
+ },
1476
+ {
1477
+ "epoch": 7.04,
1478
+ "learning_rate": 8.890901490873623e-05,
1479
+ "loss": 1.8457,
1480
+ "step": 101000
1481
+ },
1482
+ {
1483
+ "epoch": 7.07,
1484
+ "learning_rate": 8.78640100320468e-05,
1485
+ "loss": 1.821,
1486
+ "step": 101500
1487
+ },
1488
+ {
1489
+ "epoch": 7.11,
1490
+ "learning_rate": 8.681900515535739e-05,
1491
+ "loss": 1.8181,
1492
+ "step": 102000
1493
+ },
1494
+ {
1495
+ "epoch": 7.14,
1496
+ "learning_rate": 8.577400027866795e-05,
1497
+ "loss": 1.8372,
1498
+ "step": 102500
1499
+ },
1500
+ {
1501
+ "epoch": 7.18,
1502
+ "learning_rate": 8.472899540197853e-05,
1503
+ "loss": 1.8143,
1504
+ "step": 103000
1505
+ },
1506
+ {
1507
+ "epoch": 7.21,
1508
+ "learning_rate": 8.368399052528912e-05,
1509
+ "loss": 1.8175,
1510
+ "step": 103500
1511
+ },
1512
+ {
1513
+ "epoch": 7.25,
1514
+ "learning_rate": 8.263898564859969e-05,
1515
+ "loss": 1.8245,
1516
+ "step": 104000
1517
+ },
1518
+ {
1519
+ "epoch": 7.28,
1520
+ "learning_rate": 8.159398077191025e-05,
1521
+ "loss": 1.8187,
1522
+ "step": 104500
1523
+ },
1524
+ {
1525
+ "epoch": 7.32,
1526
+ "learning_rate": 8.054897589522084e-05,
1527
+ "loss": 1.8164,
1528
+ "step": 105000
1529
+ },
1530
+ {
1531
+ "epoch": 7.32,
1532
+ "eval_gen_len": 12.6364,
1533
+ "eval_loss": 2.1999216079711914,
1534
+ "eval_rouge1": 56.6104,
1535
+ "eval_rouge2": 37.0809,
1536
+ "eval_rougeL": 53.8098,
1537
+ "eval_rougeLsum": 53.8216,
1538
+ "eval_runtime": 117.7818,
1539
+ "eval_samples_per_second": 41.169,
1540
+ "eval_steps_per_second": 5.154,
1541
+ "step": 105000
1542
+ },
1543
+ {
1544
+ "epoch": 7.35,
1545
+ "learning_rate": 7.950397101853141e-05,
1546
+ "loss": 1.8402,
1547
+ "step": 105500
1548
+ },
1549
+ {
1550
+ "epoch": 7.38,
1551
+ "learning_rate": 7.8458966141842e-05,
1552
+ "loss": 1.8282,
1553
+ "step": 106000
1554
+ },
1555
+ {
1556
+ "epoch": 7.42,
1557
+ "learning_rate": 7.741396126515256e-05,
1558
+ "loss": 1.811,
1559
+ "step": 106500
1560
+ },
1561
+ {
1562
+ "epoch": 7.45,
1563
+ "learning_rate": 7.636895638846313e-05,
1564
+ "loss": 1.8315,
1565
+ "step": 107000
1566
+ },
1567
+ {
1568
+ "epoch": 7.49,
1569
+ "learning_rate": 7.532395151177372e-05,
1570
+ "loss": 1.8636,
1571
+ "step": 107500
1572
+ },
1573
+ {
1574
+ "epoch": 7.52,
1575
+ "learning_rate": 7.42789466350843e-05,
1576
+ "loss": 1.8146,
1577
+ "step": 108000
1578
+ },
1579
+ {
1580
+ "epoch": 7.56,
1581
+ "learning_rate": 7.323394175839487e-05,
1582
+ "loss": 1.8336,
1583
+ "step": 108500
1584
+ },
1585
+ {
1586
+ "epoch": 7.59,
1587
+ "learning_rate": 7.218893688170544e-05,
1588
+ "loss": 1.8256,
1589
+ "step": 109000
1590
+ },
1591
+ {
1592
+ "epoch": 7.63,
1593
+ "learning_rate": 7.114393200501602e-05,
1594
+ "loss": 1.8438,
1595
+ "step": 109500
1596
+ },
1597
+ {
1598
+ "epoch": 7.66,
1599
+ "learning_rate": 7.009892712832659e-05,
1600
+ "loss": 1.8489,
1601
+ "step": 110000
1602
+ },
1603
+ {
1604
+ "epoch": 7.66,
1605
+ "eval_gen_len": 12.5741,
1606
+ "eval_loss": 2.1944735050201416,
1607
+ "eval_rouge1": 56.6645,
1608
+ "eval_rouge2": 37.1267,
1609
+ "eval_rougeL": 53.9009,
1610
+ "eval_rougeLsum": 53.9008,
1611
+ "eval_runtime": 119.7301,
1612
+ "eval_samples_per_second": 40.499,
1613
+ "eval_steps_per_second": 5.07,
1614
+ "step": 110000
1615
+ },
1616
+ {
1617
+ "epoch": 7.7,
1618
+ "learning_rate": 6.905392225163716e-05,
1619
+ "loss": 1.7998,
1620
+ "step": 110500
1621
+ },
1622
+ {
1623
+ "epoch": 7.73,
1624
+ "learning_rate": 6.800891737494774e-05,
1625
+ "loss": 1.8382,
1626
+ "step": 111000
1627
+ },
1628
+ {
1629
+ "epoch": 7.77,
1630
+ "learning_rate": 6.696391249825833e-05,
1631
+ "loss": 1.8198,
1632
+ "step": 111500
1633
+ },
1634
+ {
1635
+ "epoch": 7.8,
1636
+ "learning_rate": 6.591890762156889e-05,
1637
+ "loss": 1.8558,
1638
+ "step": 112000
1639
+ },
1640
+ {
1641
+ "epoch": 7.84,
1642
+ "learning_rate": 6.487390274487947e-05,
1643
+ "loss": 1.8395,
1644
+ "step": 112500
1645
+ },
1646
+ {
1647
+ "epoch": 7.87,
1648
+ "learning_rate": 6.382889786819005e-05,
1649
+ "loss": 1.8386,
1650
+ "step": 113000
1651
+ },
1652
+ {
1653
+ "epoch": 7.91,
1654
+ "learning_rate": 6.278389299150062e-05,
1655
+ "loss": 1.8703,
1656
+ "step": 113500
1657
+ },
1658
+ {
1659
+ "epoch": 7.94,
1660
+ "learning_rate": 6.17388881148112e-05,
1661
+ "loss": 1.8576,
1662
+ "step": 114000
1663
+ },
1664
+ {
1665
+ "epoch": 7.98,
1666
+ "learning_rate": 6.069388323812178e-05,
1667
+ "loss": 1.8179,
1668
+ "step": 114500
1669
+ },
1670
+ {
1671
+ "epoch": 8.01,
1672
+ "learning_rate": 5.9648878361432344e-05,
1673
+ "loss": 1.82,
1674
+ "step": 115000
1675
+ },
1676
+ {
1677
+ "epoch": 8.01,
1678
+ "eval_gen_len": 12.6428,
1679
+ "eval_loss": 2.2074716091156006,
1680
+ "eval_rouge1": 56.6075,
1681
+ "eval_rouge2": 37.0359,
1682
+ "eval_rougeL": 53.8792,
1683
+ "eval_rougeLsum": 53.8833,
1684
+ "eval_runtime": 121.7726,
1685
+ "eval_samples_per_second": 39.82,
1686
+ "eval_steps_per_second": 4.985,
1687
+ "step": 115000
1688
+ },
1689
+ {
1690
+ "epoch": 8.05,
1691
+ "learning_rate": 5.8603873484742925e-05,
1692
+ "loss": 1.7476,
1693
+ "step": 115500
1694
+ },
1695
+ {
1696
+ "epoch": 8.08,
1697
+ "learning_rate": 5.75588686080535e-05,
1698
+ "loss": 1.798,
1699
+ "step": 116000
1700
+ },
1701
+ {
1702
+ "epoch": 8.12,
1703
+ "learning_rate": 5.651386373136407e-05,
1704
+ "loss": 1.7595,
1705
+ "step": 116500
1706
+ },
1707
+ {
1708
+ "epoch": 8.15,
1709
+ "learning_rate": 5.546885885467465e-05,
1710
+ "loss": 1.7551,
1711
+ "step": 117000
1712
+ },
1713
+ {
1714
+ "epoch": 8.19,
1715
+ "learning_rate": 5.442385397798523e-05,
1716
+ "loss": 1.7635,
1717
+ "step": 117500
1718
+ },
1719
+ {
1720
+ "epoch": 8.22,
1721
+ "learning_rate": 5.33788491012958e-05,
1722
+ "loss": 1.7637,
1723
+ "step": 118000
1724
+ },
1725
+ {
1726
+ "epoch": 8.26,
1727
+ "learning_rate": 5.2333844224606375e-05,
1728
+ "loss": 1.7355,
1729
+ "step": 118500
1730
+ },
1731
+ {
1732
+ "epoch": 8.29,
1733
+ "learning_rate": 5.128883934791695e-05,
1734
+ "loss": 1.7711,
1735
+ "step": 119000
1736
+ },
1737
+ {
1738
+ "epoch": 8.33,
1739
+ "learning_rate": 5.024383447122753e-05,
1740
+ "loss": 1.7786,
1741
+ "step": 119500
1742
+ },
1743
+ {
1744
+ "epoch": 8.36,
1745
+ "learning_rate": 4.91988295945381e-05,
1746
+ "loss": 1.772,
1747
+ "step": 120000
1748
+ },
1749
+ {
1750
+ "epoch": 8.36,
1751
+ "eval_gen_len": 12.6591,
1752
+ "eval_loss": 2.2067320346832275,
1753
+ "eval_rouge1": 56.4716,
1754
+ "eval_rouge2": 36.8675,
1755
+ "eval_rougeL": 53.6826,
1756
+ "eval_rougeLsum": 53.6742,
1757
+ "eval_runtime": 122.8181,
1758
+ "eval_samples_per_second": 39.481,
1759
+ "eval_steps_per_second": 4.942,
1760
+ "step": 120000
1761
+ },
1762
+ {
1763
+ "epoch": 8.39,
1764
+ "learning_rate": 4.815382471784868e-05,
1765
+ "loss": 1.8009,
1766
+ "step": 120500
1767
+ },
1768
+ {
1769
+ "epoch": 8.43,
1770
+ "learning_rate": 4.710881984115925e-05,
1771
+ "loss": 1.7549,
1772
+ "step": 121000
1773
+ },
1774
+ {
1775
+ "epoch": 8.46,
1776
+ "learning_rate": 4.606381496446983e-05,
1777
+ "loss": 1.7607,
1778
+ "step": 121500
1779
+ },
1780
+ {
1781
+ "epoch": 8.5,
1782
+ "learning_rate": 4.50188100877804e-05,
1783
+ "loss": 1.7686,
1784
+ "step": 122000
1785
+ },
1786
+ {
1787
+ "epoch": 8.53,
1788
+ "learning_rate": 4.397380521109098e-05,
1789
+ "loss": 1.7666,
1790
+ "step": 122500
1791
+ },
1792
+ {
1793
+ "epoch": 8.57,
1794
+ "learning_rate": 4.2928800334401555e-05,
1795
+ "loss": 1.7789,
1796
+ "step": 123000
1797
+ },
1798
+ {
1799
+ "epoch": 8.6,
1800
+ "learning_rate": 4.1883795457712136e-05,
1801
+ "loss": 1.7836,
1802
+ "step": 123500
1803
+ },
1804
+ {
1805
+ "epoch": 8.64,
1806
+ "learning_rate": 4.08387905810227e-05,
1807
+ "loss": 1.8019,
1808
+ "step": 124000
1809
+ },
1810
+ {
1811
+ "epoch": 8.67,
1812
+ "learning_rate": 3.9793785704333284e-05,
1813
+ "loss": 1.7651,
1814
+ "step": 124500
1815
+ },
1816
+ {
1817
+ "epoch": 8.71,
1818
+ "learning_rate": 3.874878082764386e-05,
1819
+ "loss": 1.7795,
1820
+ "step": 125000
1821
+ },
1822
+ {
1823
+ "epoch": 8.71,
1824
+ "eval_gen_len": 12.608,
1825
+ "eval_loss": 2.205610990524292,
1826
+ "eval_rouge1": 56.4112,
1827
+ "eval_rouge2": 36.9011,
1828
+ "eval_rougeL": 53.6554,
1829
+ "eval_rougeLsum": 53.6495,
1830
+ "eval_runtime": 119.8689,
1831
+ "eval_samples_per_second": 40.453,
1832
+ "eval_steps_per_second": 5.064,
1833
+ "step": 125000
1834
+ },
1835
+ {
1836
+ "epoch": 8.74,
1837
+ "learning_rate": 3.770377595095443e-05,
1838
+ "loss": 1.7496,
1839
+ "step": 125500
1840
+ },
1841
+ {
1842
+ "epoch": 8.78,
1843
+ "learning_rate": 3.665877107426501e-05,
1844
+ "loss": 1.7984,
1845
+ "step": 126000
1846
+ },
1847
+ {
1848
+ "epoch": 8.81,
1849
+ "learning_rate": 3.5613766197575586e-05,
1850
+ "loss": 1.781,
1851
+ "step": 126500
1852
+ },
1853
+ {
1854
+ "epoch": 8.85,
1855
+ "learning_rate": 3.456876132088616e-05,
1856
+ "loss": 1.783,
1857
+ "step": 127000
1858
+ },
1859
+ {
1860
+ "epoch": 8.88,
1861
+ "learning_rate": 3.3523756444196734e-05,
1862
+ "loss": 1.7638,
1863
+ "step": 127500
1864
+ },
1865
+ {
1866
+ "epoch": 8.92,
1867
+ "learning_rate": 3.2478751567507315e-05,
1868
+ "loss": 1.7673,
1869
+ "step": 128000
1870
+ },
1871
+ {
1872
+ "epoch": 8.95,
1873
+ "learning_rate": 3.143374669081789e-05,
1874
+ "loss": 1.7821,
1875
+ "step": 128500
1876
+ },
1877
+ {
1878
+ "epoch": 8.99,
1879
+ "learning_rate": 3.0388741814128463e-05,
1880
+ "loss": 1.7632,
1881
+ "step": 129000
1882
+ },
1883
+ {
1884
+ "epoch": 9.02,
1885
+ "learning_rate": 2.9343736937439037e-05,
1886
+ "loss": 1.7608,
1887
+ "step": 129500
1888
+ },
1889
+ {
1890
+ "epoch": 9.06,
1891
+ "learning_rate": 2.8298732060749614e-05,
1892
+ "loss": 1.72,
1893
+ "step": 130000
1894
+ },
1895
+ {
1896
+ "epoch": 9.06,
1897
+ "eval_gen_len": 12.6758,
1898
+ "eval_loss": 2.2197024822235107,
1899
+ "eval_rouge1": 56.4735,
1900
+ "eval_rouge2": 36.9255,
1901
+ "eval_rougeL": 53.6592,
1902
+ "eval_rougeLsum": 53.6463,
1903
+ "eval_runtime": 115.7881,
1904
+ "eval_samples_per_second": 41.878,
1905
+ "eval_steps_per_second": 5.242,
1906
+ "step": 130000
1907
+ },
1908
+ {
1909
+ "epoch": 9.09,
1910
+ "learning_rate": 2.725372718406019e-05,
1911
+ "loss": 1.7181,
1912
+ "step": 130500
1913
+ },
1914
+ {
1915
+ "epoch": 9.13,
1916
+ "learning_rate": 2.6208722307370766e-05,
1917
+ "loss": 1.6894,
1918
+ "step": 131000
1919
+ },
1920
+ {
1921
+ "epoch": 9.16,
1922
+ "learning_rate": 2.516371743068134e-05,
1923
+ "loss": 1.7012,
1924
+ "step": 131500
1925
+ },
1926
+ {
1927
+ "epoch": 9.2,
1928
+ "learning_rate": 2.4118712553991917e-05,
1929
+ "loss": 1.7261,
1930
+ "step": 132000
1931
+ },
1932
+ {
1933
+ "epoch": 9.23,
1934
+ "learning_rate": 2.307370767730249e-05,
1935
+ "loss": 1.752,
1936
+ "step": 132500
1937
+ },
1938
+ {
1939
+ "epoch": 9.27,
1940
+ "learning_rate": 2.202870280061307e-05,
1941
+ "loss": 1.7228,
1942
+ "step": 133000
1943
+ },
1944
+ {
1945
+ "epoch": 9.3,
1946
+ "learning_rate": 2.0983697923923643e-05,
1947
+ "loss": 1.7194,
1948
+ "step": 133500
1949
+ },
1950
+ {
1951
+ "epoch": 9.34,
1952
+ "learning_rate": 1.9938693047234217e-05,
1953
+ "loss": 1.7077,
1954
+ "step": 134000
1955
+ },
1956
+ {
1957
+ "epoch": 9.37,
1958
+ "learning_rate": 1.8893688170544794e-05,
1959
+ "loss": 1.7183,
1960
+ "step": 134500
1961
+ },
1962
+ {
1963
+ "epoch": 9.41,
1964
+ "learning_rate": 1.7848683293855368e-05,
1965
+ "loss": 1.7174,
1966
+ "step": 135000
1967
+ },
1968
+ {
1969
+ "epoch": 9.41,
1970
+ "eval_gen_len": 12.6568,
1971
+ "eval_loss": 2.216855764389038,
1972
+ "eval_rouge1": 56.4209,
1973
+ "eval_rouge2": 36.8139,
1974
+ "eval_rougeL": 53.5778,
1975
+ "eval_rougeLsum": 53.5685,
1976
+ "eval_runtime": 116.7222,
1977
+ "eval_samples_per_second": 41.543,
1978
+ "eval_steps_per_second": 5.2,
1979
+ "step": 135000
1980
+ },
1981
+ {
1982
+ "epoch": 9.44,
1983
+ "learning_rate": 1.6803678417165945e-05,
1984
+ "loss": 1.7175,
1985
+ "step": 135500
1986
+ },
1987
+ {
1988
+ "epoch": 9.47,
1989
+ "learning_rate": 1.575867354047652e-05,
1990
+ "loss": 1.7225,
1991
+ "step": 136000
1992
+ },
1993
+ {
1994
+ "epoch": 9.51,
1995
+ "learning_rate": 1.4713668663787095e-05,
1996
+ "loss": 1.7305,
1997
+ "step": 136500
1998
+ },
1999
+ {
2000
+ "epoch": 9.54,
2001
+ "learning_rate": 1.366866378709767e-05,
2002
+ "loss": 1.7352,
2003
+ "step": 137000
2004
+ },
2005
+ {
2006
+ "epoch": 9.58,
2007
+ "learning_rate": 1.2623658910408248e-05,
2008
+ "loss": 1.727,
2009
+ "step": 137500
2010
+ },
2011
+ {
2012
+ "epoch": 9.61,
2013
+ "learning_rate": 1.1578654033718824e-05,
2014
+ "loss": 1.7204,
2015
+ "step": 138000
2016
+ },
2017
+ {
2018
+ "epoch": 9.65,
2019
+ "learning_rate": 1.05336491570294e-05,
2020
+ "loss": 1.7324,
2021
+ "step": 138500
2022
+ },
2023
+ {
2024
+ "epoch": 9.68,
2025
+ "learning_rate": 9.488644280339975e-06,
2026
+ "loss": 1.7106,
2027
+ "step": 139000
2028
+ },
2029
+ {
2030
+ "epoch": 9.72,
2031
+ "learning_rate": 8.443639403650549e-06,
2032
+ "loss": 1.7305,
2033
+ "step": 139500
2034
+ },
2035
+ {
2036
+ "epoch": 9.75,
2037
+ "learning_rate": 7.398634526961125e-06,
2038
+ "loss": 1.7466,
2039
+ "step": 140000
2040
+ },
2041
+ {
2042
+ "epoch": 9.75,
2043
+ "eval_gen_len": 12.6416,
2044
+ "eval_loss": 2.2165005207061768,
2045
+ "eval_rouge1": 56.3715,
2046
+ "eval_rouge2": 36.767,
2047
+ "eval_rougeL": 53.555,
2048
+ "eval_rougeLsum": 53.5468,
2049
+ "eval_runtime": 116.5858,
2050
+ "eval_samples_per_second": 41.592,
2051
+ "eval_steps_per_second": 5.206,
2052
+ "step": 140000
2053
+ },
2054
+ {
2055
+ "epoch": 9.79,
2056
+ "learning_rate": 6.3536296502717004e-06,
2057
+ "loss": 1.7393,
2058
+ "step": 140500
2059
+ },
2060
+ {
2061
+ "epoch": 9.82,
2062
+ "learning_rate": 5.308624773582276e-06,
2063
+ "loss": 1.7315,
2064
+ "step": 141000
2065
+ },
2066
+ {
2067
+ "epoch": 9.86,
2068
+ "learning_rate": 4.263619896892852e-06,
2069
+ "loss": 1.7313,
2070
+ "step": 141500
2071
+ },
2072
+ {
2073
+ "epoch": 9.89,
2074
+ "learning_rate": 3.2186150202034275e-06,
2075
+ "loss": 1.741,
2076
+ "step": 142000
2077
+ },
2078
+ {
2079
+ "epoch": 9.93,
2080
+ "learning_rate": 2.1736101435140028e-06,
2081
+ "loss": 1.7116,
2082
+ "step": 142500
2083
+ },
2084
+ {
2085
+ "epoch": 9.96,
2086
+ "learning_rate": 1.1286052668245784e-06,
2087
+ "loss": 1.7329,
2088
+ "step": 143000
2089
+ },
2090
+ {
2091
+ "epoch": 10.0,
2092
+ "learning_rate": 8.360039013515396e-08,
2093
+ "loss": 1.736,
2094
+ "step": 143500
2095
+ },
2096
+ {
2097
+ "epoch": 10.0,
2098
+ "step": 143540,
2099
+ "total_flos": 2.0621473641824256e+16,
2100
+ "train_loss": 2.137477010615576,
2101
+ "train_runtime": 24602.576,
2102
+ "train_samples_per_second": 46.674,
2103
+ "train_steps_per_second": 5.834
2104
+ }
2105
+ ],
2106
+ "max_steps": 143540,
2107
+ "num_train_epochs": 10,
2108
+ "total_flos": 2.0621473641824256e+16,
2109
+ "trial_name": null,
2110
+ "trial_params": null
2111
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4be21e718e5b1976834285c17209f2804a07d0c0dda278e6fe7423adf12ed2f1
3
+ size 3183