artelabsuper commited on
Commit
db7427b
1 Parent(s): 2963f0d

trained model

Browse files
README.md ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - generated_from_trainer
4
+ metrics:
5
+ - rouge
6
+ model-index:
7
+ - name: summarization_fanpage128
8
+ results: []
9
+ ---
10
+
11
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
12
+ should probably proofread and complete it, then remove this comment. -->
13
+
14
+ # summarization_fanpage128
15
+
16
+ This model is a fine-tuned version of [gsarti/it5-base](https://huggingface.co/gsarti/it5-base) on an unknown dataset.
17
+ It achieves the following results on the evaluation set:
18
+ - Loss: 1.5492
19
+ - Rouge1: 33.8286
20
+ - Rouge2: 15.4551
21
+ - Rougel: 24.9001
22
+ - Rougelsum: 28.3133
23
+ - Gen Len: 69.7954
24
+
25
+ ## Model description
26
+
27
+ More information needed
28
+
29
+ ## Intended uses & limitations
30
+
31
+ More information needed
32
+
33
+ ## Training and evaluation data
34
+
35
+ More information needed
36
+
37
+ ## Training procedure
38
+
39
+ ### Training hyperparameters
40
+
41
+ The following hyperparameters were used during training:
42
+ - learning_rate: 5e-05
43
+ - train_batch_size: 3
44
+ - eval_batch_size: 3
45
+ - seed: 42
46
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
+ - lr_scheduler_type: linear
48
+ - num_epochs: 4.0
49
+
50
+ ### Training results
51
+
52
+
53
+
54
+ ### Framework versions
55
+
56
+ - Transformers 4.12.0.dev0
57
+ - Pytorch 1.9.1+cu102
58
+ - Datasets 1.12.1
59
+ - Tokenizers 0.10.3
all_results.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 4.0,
3
+ "eval_gen_len": 69.7954,
4
+ "eval_loss": 1.549155831336975,
5
+ "eval_rouge1": 33.8286,
6
+ "eval_rouge2": 15.4551,
7
+ "eval_rougeL": 24.9001,
8
+ "eval_rougeLsum": 28.3133,
9
+ "eval_runtime": 3492.8584,
10
+ "eval_samples": 8436,
11
+ "eval_samples_per_second": 2.415,
12
+ "eval_steps_per_second": 0.805,
13
+ "predict_gen_len": 69.3041,
14
+ "predict_loss": 1.5348224639892578,
15
+ "predict_rouge1": 34.1882,
16
+ "predict_rouge2": 15.7866,
17
+ "predict_rougeL": 25.141,
18
+ "predict_rougeLsum": 28.4882,
19
+ "predict_runtime": 3479.9848,
20
+ "predict_samples": 8437,
21
+ "predict_samples_per_second": 2.424,
22
+ "predict_steps_per_second": 0.808,
23
+ "train_loss": 1.6458884161285257,
24
+ "train_runtime": 76560.3935,
25
+ "train_samples": 67492,
26
+ "train_samples_per_second": 3.526,
27
+ "train_steps_per_second": 1.175
28
+ }
config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "gsarti/it5-base",
3
+ "architectures": [
4
+ "T5ForConditionalGeneration"
5
+ ],
6
+ "d_ff": 2048,
7
+ "d_kv": 64,
8
+ "d_model": 768,
9
+ "decoder_start_token_id": 0,
10
+ "dropout_rate": 0.1,
11
+ "eos_token_id": 1,
12
+ "feed_forward_proj": "gated-gelu",
13
+ "gradient_checkpointing": false,
14
+ "initializer_factor": 1.0,
15
+ "is_encoder_decoder": true,
16
+ "layer_norm_epsilon": 1e-06,
17
+ "model_type": "t5",
18
+ "num_decoder_layers": 12,
19
+ "num_heads": 12,
20
+ "num_layers": 12,
21
+ "output_past": true,
22
+ "pad_token_id": 0,
23
+ "relative_attention_num_buckets": 32,
24
+ "tie_word_embeddings": false,
25
+ "torch_dtype": "float32",
26
+ "transformers_version": "4.12.0.dev0",
27
+ "use_cache": true,
28
+ "vocab_size": 32103
29
+ }
eval_results.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 4.0,
3
+ "eval_gen_len": 69.7954,
4
+ "eval_loss": 1.549155831336975,
5
+ "eval_rouge1": 33.8286,
6
+ "eval_rouge2": 15.4551,
7
+ "eval_rougeL": 24.9001,
8
+ "eval_rougeLsum": 28.3133,
9
+ "eval_runtime": 3492.8584,
10
+ "eval_samples": 8436,
11
+ "eval_samples_per_second": 2.415,
12
+ "eval_steps_per_second": 0.805
13
+ }
generated_predictions.txt ADDED
The diff for this file is too large to render. See raw diff
 
predict_results.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "predict_gen_len": 69.3041,
3
+ "predict_loss": 1.5348224639892578,
4
+ "predict_rouge1": 34.1882,
5
+ "predict_rouge2": 15.7866,
6
+ "predict_rougeL": 25.141,
7
+ "predict_rougeLsum": 28.4882,
8
+ "predict_runtime": 3479.9848,
9
+ "predict_samples": 8437,
10
+ "predict_samples_per_second": 2.424,
11
+ "predict_steps_per_second": 0.808
12
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c0524edc93a24fa7f771f42e288519e09498fb9379d71013cd91400f557efe0
3
+ size 990284749
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>"]}
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": "gsarti/it5-base", "tokenizer_class": "T5Tokenizer"}
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 4.0,
3
+ "train_loss": 1.6458884161285257,
4
+ "train_runtime": 76560.3935,
5
+ "train_samples": 67492,
6
+ "train_samples_per_second": 3.526,
7
+ "train_steps_per_second": 1.175
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,1099 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 4.0,
5
+ "global_step": 89992,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.02,
12
+ "learning_rate": 4.972219752866922e-05,
13
+ "loss": 2.1683,
14
+ "step": 500
15
+ },
16
+ {
17
+ "epoch": 0.04,
18
+ "learning_rate": 4.9444395057338435e-05,
19
+ "loss": 1.892,
20
+ "step": 1000
21
+ },
22
+ {
23
+ "epoch": 0.07,
24
+ "learning_rate": 4.9166592586007645e-05,
25
+ "loss": 1.8415,
26
+ "step": 1500
27
+ },
28
+ {
29
+ "epoch": 0.09,
30
+ "learning_rate": 4.888879011467686e-05,
31
+ "loss": 1.7915,
32
+ "step": 2000
33
+ },
34
+ {
35
+ "epoch": 0.11,
36
+ "learning_rate": 4.861098764334608e-05,
37
+ "loss": 1.7884,
38
+ "step": 2500
39
+ },
40
+ {
41
+ "epoch": 0.13,
42
+ "learning_rate": 4.8333185172015294e-05,
43
+ "loss": 1.7897,
44
+ "step": 3000
45
+ },
46
+ {
47
+ "epoch": 0.16,
48
+ "learning_rate": 4.805538270068451e-05,
49
+ "loss": 1.7978,
50
+ "step": 3500
51
+ },
52
+ {
53
+ "epoch": 0.18,
54
+ "learning_rate": 4.777758022935373e-05,
55
+ "loss": 1.7701,
56
+ "step": 4000
57
+ },
58
+ {
59
+ "epoch": 0.2,
60
+ "learning_rate": 4.7499777758022936e-05,
61
+ "loss": 1.7776,
62
+ "step": 4500
63
+ },
64
+ {
65
+ "epoch": 0.22,
66
+ "learning_rate": 4.722197528669215e-05,
67
+ "loss": 1.7768,
68
+ "step": 5000
69
+ },
70
+ {
71
+ "epoch": 0.24,
72
+ "learning_rate": 4.694417281536137e-05,
73
+ "loss": 1.784,
74
+ "step": 5500
75
+ },
76
+ {
77
+ "epoch": 0.27,
78
+ "learning_rate": 4.6666370344030586e-05,
79
+ "loss": 1.7417,
80
+ "step": 6000
81
+ },
82
+ {
83
+ "epoch": 0.29,
84
+ "learning_rate": 4.6388567872699795e-05,
85
+ "loss": 1.7433,
86
+ "step": 6500
87
+ },
88
+ {
89
+ "epoch": 0.31,
90
+ "learning_rate": 4.611076540136901e-05,
91
+ "loss": 1.7252,
92
+ "step": 7000
93
+ },
94
+ {
95
+ "epoch": 0.33,
96
+ "learning_rate": 4.583296293003823e-05,
97
+ "loss": 1.7322,
98
+ "step": 7500
99
+ },
100
+ {
101
+ "epoch": 0.36,
102
+ "learning_rate": 4.555516045870744e-05,
103
+ "loss": 1.7337,
104
+ "step": 8000
105
+ },
106
+ {
107
+ "epoch": 0.38,
108
+ "learning_rate": 4.5277357987376654e-05,
109
+ "loss": 1.7481,
110
+ "step": 8500
111
+ },
112
+ {
113
+ "epoch": 0.4,
114
+ "learning_rate": 4.499955551604587e-05,
115
+ "loss": 1.7261,
116
+ "step": 9000
117
+ },
118
+ {
119
+ "epoch": 0.42,
120
+ "learning_rate": 4.472175304471509e-05,
121
+ "loss": 1.7654,
122
+ "step": 9500
123
+ },
124
+ {
125
+ "epoch": 0.44,
126
+ "learning_rate": 4.44439505733843e-05,
127
+ "loss": 1.7241,
128
+ "step": 10000
129
+ },
130
+ {
131
+ "epoch": 0.47,
132
+ "learning_rate": 4.416614810205352e-05,
133
+ "loss": 1.7256,
134
+ "step": 10500
135
+ },
136
+ {
137
+ "epoch": 0.49,
138
+ "learning_rate": 4.388834563072273e-05,
139
+ "loss": 1.7115,
140
+ "step": 11000
141
+ },
142
+ {
143
+ "epoch": 0.51,
144
+ "learning_rate": 4.3610543159391946e-05,
145
+ "loss": 1.7019,
146
+ "step": 11500
147
+ },
148
+ {
149
+ "epoch": 0.53,
150
+ "learning_rate": 4.333274068806116e-05,
151
+ "loss": 1.7066,
152
+ "step": 12000
153
+ },
154
+ {
155
+ "epoch": 0.56,
156
+ "learning_rate": 4.305493821673038e-05,
157
+ "loss": 1.7005,
158
+ "step": 12500
159
+ },
160
+ {
161
+ "epoch": 0.58,
162
+ "learning_rate": 4.2777135745399595e-05,
163
+ "loss": 1.7056,
164
+ "step": 13000
165
+ },
166
+ {
167
+ "epoch": 0.6,
168
+ "learning_rate": 4.249933327406881e-05,
169
+ "loss": 1.7052,
170
+ "step": 13500
171
+ },
172
+ {
173
+ "epoch": 0.62,
174
+ "learning_rate": 4.222153080273802e-05,
175
+ "loss": 1.7141,
176
+ "step": 14000
177
+ },
178
+ {
179
+ "epoch": 0.64,
180
+ "learning_rate": 4.194372833140724e-05,
181
+ "loss": 1.7128,
182
+ "step": 14500
183
+ },
184
+ {
185
+ "epoch": 0.67,
186
+ "learning_rate": 4.1665925860076454e-05,
187
+ "loss": 1.6943,
188
+ "step": 15000
189
+ },
190
+ {
191
+ "epoch": 0.69,
192
+ "learning_rate": 4.138812338874567e-05,
193
+ "loss": 1.7187,
194
+ "step": 15500
195
+ },
196
+ {
197
+ "epoch": 0.71,
198
+ "learning_rate": 4.1110320917414887e-05,
199
+ "loss": 1.7134,
200
+ "step": 16000
201
+ },
202
+ {
203
+ "epoch": 0.73,
204
+ "learning_rate": 4.08325184460841e-05,
205
+ "loss": 1.7088,
206
+ "step": 16500
207
+ },
208
+ {
209
+ "epoch": 0.76,
210
+ "learning_rate": 4.055471597475331e-05,
211
+ "loss": 1.6984,
212
+ "step": 17000
213
+ },
214
+ {
215
+ "epoch": 0.78,
216
+ "learning_rate": 4.027691350342253e-05,
217
+ "loss": 1.7107,
218
+ "step": 17500
219
+ },
220
+ {
221
+ "epoch": 0.8,
222
+ "learning_rate": 3.9999111032091745e-05,
223
+ "loss": 1.7043,
224
+ "step": 18000
225
+ },
226
+ {
227
+ "epoch": 0.82,
228
+ "learning_rate": 3.9721308560760955e-05,
229
+ "loss": 1.7023,
230
+ "step": 18500
231
+ },
232
+ {
233
+ "epoch": 0.84,
234
+ "learning_rate": 3.944350608943017e-05,
235
+ "loss": 1.6946,
236
+ "step": 19000
237
+ },
238
+ {
239
+ "epoch": 0.87,
240
+ "learning_rate": 3.916570361809939e-05,
241
+ "loss": 1.6791,
242
+ "step": 19500
243
+ },
244
+ {
245
+ "epoch": 0.89,
246
+ "learning_rate": 3.8887901146768604e-05,
247
+ "loss": 1.7051,
248
+ "step": 20000
249
+ },
250
+ {
251
+ "epoch": 0.91,
252
+ "learning_rate": 3.8610098675437814e-05,
253
+ "loss": 1.6723,
254
+ "step": 20500
255
+ },
256
+ {
257
+ "epoch": 0.93,
258
+ "learning_rate": 3.833229620410703e-05,
259
+ "loss": 1.7001,
260
+ "step": 21000
261
+ },
262
+ {
263
+ "epoch": 0.96,
264
+ "learning_rate": 3.8054493732776247e-05,
265
+ "loss": 1.6728,
266
+ "step": 21500
267
+ },
268
+ {
269
+ "epoch": 0.98,
270
+ "learning_rate": 3.777669126144546e-05,
271
+ "loss": 1.6689,
272
+ "step": 22000
273
+ },
274
+ {
275
+ "epoch": 1.0,
276
+ "learning_rate": 3.749888879011468e-05,
277
+ "loss": 1.6921,
278
+ "step": 22500
279
+ },
280
+ {
281
+ "epoch": 1.02,
282
+ "learning_rate": 3.7221086318783896e-05,
283
+ "loss": 1.653,
284
+ "step": 23000
285
+ },
286
+ {
287
+ "epoch": 1.04,
288
+ "learning_rate": 3.6943283847453105e-05,
289
+ "loss": 1.6692,
290
+ "step": 23500
291
+ },
292
+ {
293
+ "epoch": 1.07,
294
+ "learning_rate": 3.666548137612232e-05,
295
+ "loss": 1.6404,
296
+ "step": 24000
297
+ },
298
+ {
299
+ "epoch": 1.09,
300
+ "learning_rate": 3.638767890479154e-05,
301
+ "loss": 1.6781,
302
+ "step": 24500
303
+ },
304
+ {
305
+ "epoch": 1.11,
306
+ "learning_rate": 3.6109876433460755e-05,
307
+ "loss": 1.6622,
308
+ "step": 25000
309
+ },
310
+ {
311
+ "epoch": 1.13,
312
+ "learning_rate": 3.583207396212997e-05,
313
+ "loss": 1.645,
314
+ "step": 25500
315
+ },
316
+ {
317
+ "epoch": 1.16,
318
+ "learning_rate": 3.555427149079919e-05,
319
+ "loss": 1.6476,
320
+ "step": 26000
321
+ },
322
+ {
323
+ "epoch": 1.18,
324
+ "learning_rate": 3.52764690194684e-05,
325
+ "loss": 1.6429,
326
+ "step": 26500
327
+ },
328
+ {
329
+ "epoch": 1.2,
330
+ "learning_rate": 3.4998666548137613e-05,
331
+ "loss": 1.6649,
332
+ "step": 27000
333
+ },
334
+ {
335
+ "epoch": 1.22,
336
+ "learning_rate": 3.472086407680683e-05,
337
+ "loss": 1.6437,
338
+ "step": 27500
339
+ },
340
+ {
341
+ "epoch": 1.24,
342
+ "learning_rate": 3.4443061605476046e-05,
343
+ "loss": 1.6383,
344
+ "step": 28000
345
+ },
346
+ {
347
+ "epoch": 1.27,
348
+ "learning_rate": 3.416525913414526e-05,
349
+ "loss": 1.6574,
350
+ "step": 28500
351
+ },
352
+ {
353
+ "epoch": 1.29,
354
+ "learning_rate": 3.388745666281448e-05,
355
+ "loss": 1.6443,
356
+ "step": 29000
357
+ },
358
+ {
359
+ "epoch": 1.31,
360
+ "learning_rate": 3.360965419148369e-05,
361
+ "loss": 1.6584,
362
+ "step": 29500
363
+ },
364
+ {
365
+ "epoch": 1.33,
366
+ "learning_rate": 3.3331851720152905e-05,
367
+ "loss": 1.6487,
368
+ "step": 30000
369
+ },
370
+ {
371
+ "epoch": 1.36,
372
+ "learning_rate": 3.3054049248822115e-05,
373
+ "loss": 1.6691,
374
+ "step": 30500
375
+ },
376
+ {
377
+ "epoch": 1.38,
378
+ "learning_rate": 3.277624677749133e-05,
379
+ "loss": 1.663,
380
+ "step": 31000
381
+ },
382
+ {
383
+ "epoch": 1.4,
384
+ "learning_rate": 3.249844430616055e-05,
385
+ "loss": 1.6332,
386
+ "step": 31500
387
+ },
388
+ {
389
+ "epoch": 1.42,
390
+ "learning_rate": 3.2220641834829764e-05,
391
+ "loss": 1.6474,
392
+ "step": 32000
393
+ },
394
+ {
395
+ "epoch": 1.44,
396
+ "learning_rate": 3.194283936349898e-05,
397
+ "loss": 1.6257,
398
+ "step": 32500
399
+ },
400
+ {
401
+ "epoch": 1.47,
402
+ "learning_rate": 3.166503689216819e-05,
403
+ "loss": 1.6491,
404
+ "step": 33000
405
+ },
406
+ {
407
+ "epoch": 1.49,
408
+ "learning_rate": 3.1387234420837406e-05,
409
+ "loss": 1.6215,
410
+ "step": 33500
411
+ },
412
+ {
413
+ "epoch": 1.51,
414
+ "learning_rate": 3.110943194950662e-05,
415
+ "loss": 1.6691,
416
+ "step": 34000
417
+ },
418
+ {
419
+ "epoch": 1.53,
420
+ "learning_rate": 3.083162947817584e-05,
421
+ "loss": 1.6339,
422
+ "step": 34500
423
+ },
424
+ {
425
+ "epoch": 1.56,
426
+ "learning_rate": 3.0553827006845055e-05,
427
+ "loss": 1.6701,
428
+ "step": 35000
429
+ },
430
+ {
431
+ "epoch": 1.58,
432
+ "learning_rate": 3.027602453551427e-05,
433
+ "loss": 1.6105,
434
+ "step": 35500
435
+ },
436
+ {
437
+ "epoch": 1.6,
438
+ "learning_rate": 2.9998222064183485e-05,
439
+ "loss": 1.6545,
440
+ "step": 36000
441
+ },
442
+ {
443
+ "epoch": 1.62,
444
+ "learning_rate": 2.97204195928527e-05,
445
+ "loss": 1.6452,
446
+ "step": 36500
447
+ },
448
+ {
449
+ "epoch": 1.64,
450
+ "learning_rate": 2.9442617121521914e-05,
451
+ "loss": 1.6699,
452
+ "step": 37000
453
+ },
454
+ {
455
+ "epoch": 1.67,
456
+ "learning_rate": 2.916481465019113e-05,
457
+ "loss": 1.6366,
458
+ "step": 37500
459
+ },
460
+ {
461
+ "epoch": 1.69,
462
+ "learning_rate": 2.8887012178860344e-05,
463
+ "loss": 1.624,
464
+ "step": 38000
465
+ },
466
+ {
467
+ "epoch": 1.71,
468
+ "learning_rate": 2.860920970752956e-05,
469
+ "loss": 1.6441,
470
+ "step": 38500
471
+ },
472
+ {
473
+ "epoch": 1.73,
474
+ "learning_rate": 2.8331407236198777e-05,
475
+ "loss": 1.6528,
476
+ "step": 39000
477
+ },
478
+ {
479
+ "epoch": 1.76,
480
+ "learning_rate": 2.805360476486799e-05,
481
+ "loss": 1.6217,
482
+ "step": 39500
483
+ },
484
+ {
485
+ "epoch": 1.78,
486
+ "learning_rate": 2.7775802293537206e-05,
487
+ "loss": 1.6429,
488
+ "step": 40000
489
+ },
490
+ {
491
+ "epoch": 1.8,
492
+ "learning_rate": 2.7497999822206422e-05,
493
+ "loss": 1.6334,
494
+ "step": 40500
495
+ },
496
+ {
497
+ "epoch": 1.82,
498
+ "learning_rate": 2.7220197350875635e-05,
499
+ "loss": 1.6595,
500
+ "step": 41000
501
+ },
502
+ {
503
+ "epoch": 1.84,
504
+ "learning_rate": 2.6942394879544852e-05,
505
+ "loss": 1.636,
506
+ "step": 41500
507
+ },
508
+ {
509
+ "epoch": 1.87,
510
+ "learning_rate": 2.6664592408214068e-05,
511
+ "loss": 1.6176,
512
+ "step": 42000
513
+ },
514
+ {
515
+ "epoch": 1.89,
516
+ "learning_rate": 2.6386789936883278e-05,
517
+ "loss": 1.6374,
518
+ "step": 42500
519
+ },
520
+ {
521
+ "epoch": 1.91,
522
+ "learning_rate": 2.610898746555249e-05,
523
+ "loss": 1.6541,
524
+ "step": 43000
525
+ },
526
+ {
527
+ "epoch": 1.93,
528
+ "learning_rate": 2.5831184994221707e-05,
529
+ "loss": 1.6518,
530
+ "step": 43500
531
+ },
532
+ {
533
+ "epoch": 1.96,
534
+ "learning_rate": 2.5553382522890924e-05,
535
+ "loss": 1.645,
536
+ "step": 44000
537
+ },
538
+ {
539
+ "epoch": 1.98,
540
+ "learning_rate": 2.5275580051560137e-05,
541
+ "loss": 1.637,
542
+ "step": 44500
543
+ },
544
+ {
545
+ "epoch": 2.0,
546
+ "learning_rate": 2.4997777580229356e-05,
547
+ "loss": 1.6229,
548
+ "step": 45000
549
+ },
550
+ {
551
+ "epoch": 2.02,
552
+ "learning_rate": 2.471997510889857e-05,
553
+ "loss": 1.601,
554
+ "step": 45500
555
+ },
556
+ {
557
+ "epoch": 2.04,
558
+ "learning_rate": 2.4442172637567782e-05,
559
+ "loss": 1.6071,
560
+ "step": 46000
561
+ },
562
+ {
563
+ "epoch": 2.07,
564
+ "learning_rate": 2.4164370166237e-05,
565
+ "loss": 1.6028,
566
+ "step": 46500
567
+ },
568
+ {
569
+ "epoch": 2.09,
570
+ "learning_rate": 2.3886567694906215e-05,
571
+ "loss": 1.6091,
572
+ "step": 47000
573
+ },
574
+ {
575
+ "epoch": 2.11,
576
+ "learning_rate": 2.3608765223575428e-05,
577
+ "loss": 1.5878,
578
+ "step": 47500
579
+ },
580
+ {
581
+ "epoch": 2.13,
582
+ "learning_rate": 2.3330962752244645e-05,
583
+ "loss": 1.6169,
584
+ "step": 48000
585
+ },
586
+ {
587
+ "epoch": 2.16,
588
+ "learning_rate": 2.305316028091386e-05,
589
+ "loss": 1.6102,
590
+ "step": 48500
591
+ },
592
+ {
593
+ "epoch": 2.18,
594
+ "learning_rate": 2.2775357809583074e-05,
595
+ "loss": 1.6253,
596
+ "step": 49000
597
+ },
598
+ {
599
+ "epoch": 2.2,
600
+ "learning_rate": 2.249755533825229e-05,
601
+ "loss": 1.636,
602
+ "step": 49500
603
+ },
604
+ {
605
+ "epoch": 2.22,
606
+ "learning_rate": 2.2219752866921507e-05,
607
+ "loss": 1.6303,
608
+ "step": 50000
609
+ },
610
+ {
611
+ "epoch": 2.24,
612
+ "learning_rate": 2.194195039559072e-05,
613
+ "loss": 1.6342,
614
+ "step": 50500
615
+ },
616
+ {
617
+ "epoch": 2.27,
618
+ "learning_rate": 2.1664147924259936e-05,
619
+ "loss": 1.6082,
620
+ "step": 51000
621
+ },
622
+ {
623
+ "epoch": 2.29,
624
+ "learning_rate": 2.138634545292915e-05,
625
+ "loss": 1.6241,
626
+ "step": 51500
627
+ },
628
+ {
629
+ "epoch": 2.31,
630
+ "learning_rate": 2.1108542981598366e-05,
631
+ "loss": 1.6364,
632
+ "step": 52000
633
+ },
634
+ {
635
+ "epoch": 2.33,
636
+ "learning_rate": 2.083074051026758e-05,
637
+ "loss": 1.5943,
638
+ "step": 52500
639
+ },
640
+ {
641
+ "epoch": 2.36,
642
+ "learning_rate": 2.0552938038936795e-05,
643
+ "loss": 1.5904,
644
+ "step": 53000
645
+ },
646
+ {
647
+ "epoch": 2.38,
648
+ "learning_rate": 2.027513556760601e-05,
649
+ "loss": 1.6107,
650
+ "step": 53500
651
+ },
652
+ {
653
+ "epoch": 2.4,
654
+ "learning_rate": 1.9997333096275224e-05,
655
+ "loss": 1.623,
656
+ "step": 54000
657
+ },
658
+ {
659
+ "epoch": 2.42,
660
+ "learning_rate": 1.971953062494444e-05,
661
+ "loss": 1.5865,
662
+ "step": 54500
663
+ },
664
+ {
665
+ "epoch": 2.44,
666
+ "learning_rate": 1.9441728153613657e-05,
667
+ "loss": 1.6293,
668
+ "step": 55000
669
+ },
670
+ {
671
+ "epoch": 2.47,
672
+ "learning_rate": 1.916392568228287e-05,
673
+ "loss": 1.6075,
674
+ "step": 55500
675
+ },
676
+ {
677
+ "epoch": 2.49,
678
+ "learning_rate": 1.8886123210952087e-05,
679
+ "loss": 1.6136,
680
+ "step": 56000
681
+ },
682
+ {
683
+ "epoch": 2.51,
684
+ "learning_rate": 1.8608320739621303e-05,
685
+ "loss": 1.6275,
686
+ "step": 56500
687
+ },
688
+ {
689
+ "epoch": 2.53,
690
+ "learning_rate": 1.8330518268290516e-05,
691
+ "loss": 1.604,
692
+ "step": 57000
693
+ },
694
+ {
695
+ "epoch": 2.56,
696
+ "learning_rate": 1.805271579695973e-05,
697
+ "loss": 1.6248,
698
+ "step": 57500
699
+ },
700
+ {
701
+ "epoch": 2.58,
702
+ "learning_rate": 1.7774913325628945e-05,
703
+ "loss": 1.6077,
704
+ "step": 58000
705
+ },
706
+ {
707
+ "epoch": 2.6,
708
+ "learning_rate": 1.749711085429816e-05,
709
+ "loss": 1.6032,
710
+ "step": 58500
711
+ },
712
+ {
713
+ "epoch": 2.62,
714
+ "learning_rate": 1.7219308382967375e-05,
715
+ "loss": 1.6181,
716
+ "step": 59000
717
+ },
718
+ {
719
+ "epoch": 2.64,
720
+ "learning_rate": 1.694150591163659e-05,
721
+ "loss": 1.6061,
722
+ "step": 59500
723
+ },
724
+ {
725
+ "epoch": 2.67,
726
+ "learning_rate": 1.6663703440305804e-05,
727
+ "loss": 1.5769,
728
+ "step": 60000
729
+ },
730
+ {
731
+ "epoch": 2.69,
732
+ "learning_rate": 1.638590096897502e-05,
733
+ "loss": 1.6039,
734
+ "step": 60500
735
+ },
736
+ {
737
+ "epoch": 2.71,
738
+ "learning_rate": 1.6108098497644237e-05,
739
+ "loss": 1.6071,
740
+ "step": 61000
741
+ },
742
+ {
743
+ "epoch": 2.73,
744
+ "learning_rate": 1.583029602631345e-05,
745
+ "loss": 1.5944,
746
+ "step": 61500
747
+ },
748
+ {
749
+ "epoch": 2.76,
750
+ "learning_rate": 1.5552493554982667e-05,
751
+ "loss": 1.5803,
752
+ "step": 62000
753
+ },
754
+ {
755
+ "epoch": 2.78,
756
+ "learning_rate": 1.5274691083651883e-05,
757
+ "loss": 1.6037,
758
+ "step": 62500
759
+ },
760
+ {
761
+ "epoch": 2.8,
762
+ "learning_rate": 1.4996888612321098e-05,
763
+ "loss": 1.5921,
764
+ "step": 63000
765
+ },
766
+ {
767
+ "epoch": 2.82,
768
+ "learning_rate": 1.4719086140990309e-05,
769
+ "loss": 1.6005,
770
+ "step": 63500
771
+ },
772
+ {
773
+ "epoch": 2.84,
774
+ "learning_rate": 1.4441283669659525e-05,
775
+ "loss": 1.5907,
776
+ "step": 64000
777
+ },
778
+ {
779
+ "epoch": 2.87,
780
+ "learning_rate": 1.416348119832874e-05,
781
+ "loss": 1.6009,
782
+ "step": 64500
783
+ },
784
+ {
785
+ "epoch": 2.89,
786
+ "learning_rate": 1.3885678726997955e-05,
787
+ "loss": 1.5981,
788
+ "step": 65000
789
+ },
790
+ {
791
+ "epoch": 2.91,
792
+ "learning_rate": 1.3607876255667171e-05,
793
+ "loss": 1.6182,
794
+ "step": 65500
795
+ },
796
+ {
797
+ "epoch": 2.93,
798
+ "learning_rate": 1.3330073784336386e-05,
799
+ "loss": 1.6073,
800
+ "step": 66000
801
+ },
802
+ {
803
+ "epoch": 2.96,
804
+ "learning_rate": 1.30522713130056e-05,
805
+ "loss": 1.6208,
806
+ "step": 66500
807
+ },
808
+ {
809
+ "epoch": 2.98,
810
+ "learning_rate": 1.2774468841674817e-05,
811
+ "loss": 1.5967,
812
+ "step": 67000
813
+ },
814
+ {
815
+ "epoch": 3.0,
816
+ "learning_rate": 1.2496666370344032e-05,
817
+ "loss": 1.6261,
818
+ "step": 67500
819
+ },
820
+ {
821
+ "epoch": 3.02,
822
+ "learning_rate": 1.2218863899013246e-05,
823
+ "loss": 1.5709,
824
+ "step": 68000
825
+ },
826
+ {
827
+ "epoch": 3.04,
828
+ "learning_rate": 1.1941061427682461e-05,
829
+ "loss": 1.604,
830
+ "step": 68500
831
+ },
832
+ {
833
+ "epoch": 3.07,
834
+ "learning_rate": 1.1663258956351676e-05,
835
+ "loss": 1.5782,
836
+ "step": 69000
837
+ },
838
+ {
839
+ "epoch": 3.09,
840
+ "learning_rate": 1.1385456485020892e-05,
841
+ "loss": 1.5971,
842
+ "step": 69500
843
+ },
844
+ {
845
+ "epoch": 3.11,
846
+ "learning_rate": 1.1107654013690107e-05,
847
+ "loss": 1.6089,
848
+ "step": 70000
849
+ },
850
+ {
851
+ "epoch": 3.13,
852
+ "learning_rate": 1.0829851542359322e-05,
853
+ "loss": 1.5871,
854
+ "step": 70500
855
+ },
856
+ {
857
+ "epoch": 3.16,
858
+ "learning_rate": 1.0552049071028536e-05,
859
+ "loss": 1.5854,
860
+ "step": 71000
861
+ },
862
+ {
863
+ "epoch": 3.18,
864
+ "learning_rate": 1.0274246599697751e-05,
865
+ "loss": 1.6105,
866
+ "step": 71500
867
+ },
868
+ {
869
+ "epoch": 3.2,
870
+ "learning_rate": 9.996444128366966e-06,
871
+ "loss": 1.5779,
872
+ "step": 72000
873
+ },
874
+ {
875
+ "epoch": 3.22,
876
+ "learning_rate": 9.718641657036182e-06,
877
+ "loss": 1.5993,
878
+ "step": 72500
879
+ },
880
+ {
881
+ "epoch": 3.24,
882
+ "learning_rate": 9.440839185705397e-06,
883
+ "loss": 1.5811,
884
+ "step": 73000
885
+ },
886
+ {
887
+ "epoch": 3.27,
888
+ "learning_rate": 9.163036714374612e-06,
889
+ "loss": 1.5707,
890
+ "step": 73500
891
+ },
892
+ {
893
+ "epoch": 3.29,
894
+ "learning_rate": 8.885234243043826e-06,
895
+ "loss": 1.5867,
896
+ "step": 74000
897
+ },
898
+ {
899
+ "epoch": 3.31,
900
+ "learning_rate": 8.607431771713041e-06,
901
+ "loss": 1.6162,
902
+ "step": 74500
903
+ },
904
+ {
905
+ "epoch": 3.33,
906
+ "learning_rate": 8.329629300382257e-06,
907
+ "loss": 1.6259,
908
+ "step": 75000
909
+ },
910
+ {
911
+ "epoch": 3.36,
912
+ "learning_rate": 8.051826829051472e-06,
913
+ "loss": 1.5916,
914
+ "step": 75500
915
+ },
916
+ {
917
+ "epoch": 3.38,
918
+ "learning_rate": 7.774024357720687e-06,
919
+ "loss": 1.5834,
920
+ "step": 76000
921
+ },
922
+ {
923
+ "epoch": 3.4,
924
+ "learning_rate": 7.496221886389902e-06,
925
+ "loss": 1.593,
926
+ "step": 76500
927
+ },
928
+ {
929
+ "epoch": 3.42,
930
+ "learning_rate": 7.218419415059116e-06,
931
+ "loss": 1.5937,
932
+ "step": 77000
933
+ },
934
+ {
935
+ "epoch": 3.44,
936
+ "learning_rate": 6.940616943728332e-06,
937
+ "loss": 1.5642,
938
+ "step": 77500
939
+ },
940
+ {
941
+ "epoch": 3.47,
942
+ "learning_rate": 6.662814472397546e-06,
943
+ "loss": 1.575,
944
+ "step": 78000
945
+ },
946
+ {
947
+ "epoch": 3.49,
948
+ "learning_rate": 6.385012001066762e-06,
949
+ "loss": 1.5726,
950
+ "step": 78500
951
+ },
952
+ {
953
+ "epoch": 3.51,
954
+ "learning_rate": 6.1072095297359775e-06,
955
+ "loss": 1.5616,
956
+ "step": 79000
957
+ },
958
+ {
959
+ "epoch": 3.53,
960
+ "learning_rate": 5.829407058405191e-06,
961
+ "loss": 1.5951,
962
+ "step": 79500
963
+ },
964
+ {
965
+ "epoch": 3.56,
966
+ "learning_rate": 5.551604587074407e-06,
967
+ "loss": 1.6033,
968
+ "step": 80000
969
+ },
970
+ {
971
+ "epoch": 3.58,
972
+ "learning_rate": 5.2738021157436225e-06,
973
+ "loss": 1.593,
974
+ "step": 80500
975
+ },
976
+ {
977
+ "epoch": 3.6,
978
+ "learning_rate": 4.995999644412837e-06,
979
+ "loss": 1.5798,
980
+ "step": 81000
981
+ },
982
+ {
983
+ "epoch": 3.62,
984
+ "learning_rate": 4.718197173082052e-06,
985
+ "loss": 1.5774,
986
+ "step": 81500
987
+ },
988
+ {
989
+ "epoch": 3.64,
990
+ "learning_rate": 4.4403947017512674e-06,
991
+ "loss": 1.5894,
992
+ "step": 82000
993
+ },
994
+ {
995
+ "epoch": 3.67,
996
+ "learning_rate": 4.162592230420482e-06,
997
+ "loss": 1.5609,
998
+ "step": 82500
999
+ },
1000
+ {
1001
+ "epoch": 3.69,
1002
+ "learning_rate": 3.884789759089697e-06,
1003
+ "loss": 1.5854,
1004
+ "step": 83000
1005
+ },
1006
+ {
1007
+ "epoch": 3.71,
1008
+ "learning_rate": 3.6069872877589124e-06,
1009
+ "loss": 1.5871,
1010
+ "step": 83500
1011
+ },
1012
+ {
1013
+ "epoch": 3.73,
1014
+ "learning_rate": 3.329184816428127e-06,
1015
+ "loss": 1.5745,
1016
+ "step": 84000
1017
+ },
1018
+ {
1019
+ "epoch": 3.76,
1020
+ "learning_rate": 3.0513823450973422e-06,
1021
+ "loss": 1.5986,
1022
+ "step": 84500
1023
+ },
1024
+ {
1025
+ "epoch": 3.78,
1026
+ "learning_rate": 2.773579873766557e-06,
1027
+ "loss": 1.5986,
1028
+ "step": 85000
1029
+ },
1030
+ {
1031
+ "epoch": 3.8,
1032
+ "learning_rate": 2.495777402435772e-06,
1033
+ "loss": 1.5965,
1034
+ "step": 85500
1035
+ },
1036
+ {
1037
+ "epoch": 3.82,
1038
+ "learning_rate": 2.217974931104987e-06,
1039
+ "loss": 1.583,
1040
+ "step": 86000
1041
+ },
1042
+ {
1043
+ "epoch": 3.84,
1044
+ "learning_rate": 1.9401724597742023e-06,
1045
+ "loss": 1.5983,
1046
+ "step": 86500
1047
+ },
1048
+ {
1049
+ "epoch": 3.87,
1050
+ "learning_rate": 1.662369988443417e-06,
1051
+ "loss": 1.5991,
1052
+ "step": 87000
1053
+ },
1054
+ {
1055
+ "epoch": 3.89,
1056
+ "learning_rate": 1.3845675171126324e-06,
1057
+ "loss": 1.5761,
1058
+ "step": 87500
1059
+ },
1060
+ {
1061
+ "epoch": 3.91,
1062
+ "learning_rate": 1.1067650457818473e-06,
1063
+ "loss": 1.583,
1064
+ "step": 88000
1065
+ },
1066
+ {
1067
+ "epoch": 3.93,
1068
+ "learning_rate": 8.289625744510624e-07,
1069
+ "loss": 1.6017,
1070
+ "step": 88500
1071
+ },
1072
+ {
1073
+ "epoch": 3.96,
1074
+ "learning_rate": 5.511601031202774e-07,
1075
+ "loss": 1.574,
1076
+ "step": 89000
1077
+ },
1078
+ {
1079
+ "epoch": 3.98,
1080
+ "learning_rate": 2.733576317894924e-07,
1081
+ "loss": 1.5734,
1082
+ "step": 89500
1083
+ },
1084
+ {
1085
+ "epoch": 4.0,
1086
+ "step": 89992,
1087
+ "total_flos": 2.1371909200869427e+17,
1088
+ "train_loss": 1.6458884161285257,
1089
+ "train_runtime": 76560.3935,
1090
+ "train_samples_per_second": 3.526,
1091
+ "train_steps_per_second": 1.175
1092
+ }
1093
+ ],
1094
+ "max_steps": 89992,
1095
+ "num_train_epochs": 4,
1096
+ "total_flos": 2.1371909200869427e+17,
1097
+ "trial_name": null,
1098
+ "trial_params": null
1099
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:595fc384baf4c09a888884cb7c24ab83cc7f68d40852de25b7f62a7e051752d1
3
+ size 2927