Hugging Face's logo

ChrisZeng
/
bart-base-detox

Text2Text Generation
Transformers
PyTorch
bart
Generated from Trainer
Inference Endpoints
Model card Files Community
ChrisZeng commited on
Commit
f50308f
•
1 Parent(s): 6bf577b

Training in progress, epoch 14

Browse files
Files changed (29) hide show
  1. checkpoint-1890/added_tokens.json +1 -0
  2. checkpoint-1890/config.json +75 -0
  3. checkpoint-1890/merges.txt +0 -0
  4. checkpoint-1890/optimizer.pt +3 -0
  5. checkpoint-1890/pytorch_model.bin +3 -0
  6. checkpoint-1890/rng_state.pth +3 -0
  7. checkpoint-1890/scaler.pt +3 -0
  8. checkpoint-1890/scheduler.pt +3 -0
  9. checkpoint-1890/special_tokens_map.json +1 -0
  10. checkpoint-1890/tokenizer.json +0 -0
  11. checkpoint-1890/tokenizer_config.json +1 -0
  12. checkpoint-1890/trainer_state.json +212 -0
  13. checkpoint-1890/training_args.bin +3 -0
  14. checkpoint-1890/vocab.json +0 -0
  15. checkpoint-2025/added_tokens.json +1 -0
  16. checkpoint-2025/config.json +75 -0
  17. checkpoint-2025/merges.txt +0 -0
  18. checkpoint-2025/optimizer.pt +3 -0
  19. checkpoint-2025/pytorch_model.bin +3 -0
  20. checkpoint-2025/rng_state.pth +3 -0
  21. checkpoint-2025/scaler.pt +3 -0
  22. checkpoint-2025/scheduler.pt +3 -0
  23. checkpoint-2025/special_tokens_map.json +1 -0
  24. checkpoint-2025/tokenizer.json +0 -0
  25. checkpoint-2025/tokenizer_config.json +1 -0
  26. checkpoint-2025/trainer_state.json +226 -0
  27. checkpoint-2025/training_args.bin +3 -0
  28. checkpoint-2025/vocab.json +0 -0
  29. pytorch_model.bin +1 -1
checkpoint-1890/added_tokens.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"<CSD>": 50265}
checkpoint-1890/config.json ADDED
@@ -0,0 +1,75 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/bart-base",
3
+ "activation_dropout": 0.1,
4
+ "activation_function": "gelu",
5
+ "add_bias_logits": false,
6
+ "add_final_layer_norm": false,
7
+ "architectures": [
8
+ "BartForConditionalGeneration"
9
+ ],
10
+ "attention_dropout": 0.1,
11
+ "bos_token_id": 0,
12
+ "classif_dropout": 0.1,
13
+ "classifier_dropout": 0.0,
14
+ "d_model": 768,
15
+ "decoder_attention_heads": 12,
16
+ "decoder_ffn_dim": 3072,
17
+ "decoder_layerdrop": 0.0,
18
+ "decoder_layers": 6,
19
+ "decoder_start_token_id": 2,
20
+ "dropout": 0.1,
21
+ "early_stopping": true,
22
+ "encoder_attention_heads": 12,
23
+ "encoder_ffn_dim": 3072,
24
+ "encoder_layerdrop": 0.0,
25
+ "encoder_layers": 6,
26
+ "eos_token_id": 2,
27
+ "forced_bos_token_id": 0,
28
+ "forced_eos_token_id": 2,
29
+ "gradient_checkpointing": false,
30
+ "id2label": {
31
+ "0": "LABEL_0",
32
+ "1": "LABEL_1",
33
+ "2": "LABEL_2"
34
+ },
35
+ "init_std": 0.02,
36
+ "is_encoder_decoder": true,
37
+ "label2id": {
38
+ "LABEL_0": 0,
39
+ "LABEL_1": 1,
40
+ "LABEL_2": 2
41
+ },
42
+ "max_position_embeddings": 1024,
43
+ "model_type": "bart",
44
+ "no_repeat_ngram_size": 3,
45
+ "normalize_before": false,
46
+ "normalize_embedding": true,
47
+ "num_beams": 4,
48
+ "num_hidden_layers": 6,
49
+ "pad_token_id": 1,
50
+ "scale_embedding": false,
51
+ "task_specific_params": {
52
+ "summarization": {
53
+ "length_penalty": 1.0,
54
+ "max_length": 128,
55
+ "min_length": 12,
56
+ "num_beams": 4
57
+ },
58
+ "summarization_cnn": {
59
+ "length_penalty": 2.0,
60
+ "max_length": 142,
61
+ "min_length": 56,
62
+ "num_beams": 4
63
+ },
64
+ "summarization_xsum": {
65
+ "length_penalty": 1.0,
66
+ "max_length": 62,
67
+ "min_length": 11,
68
+ "num_beams": 6
69
+ }
70
+ },
71
+ "torch_dtype": "float32",
72
+ "transformers_version": "4.16.2",
73
+ "use_cache": false,
74
+ "vocab_size": 50266
75
+ }
checkpoint-1890/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-1890/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9bf86d4fffe19c3acdbfc8ae24faaa4443a71e91cb7a40e14808ad3c602fd8b6
3
+ size 1115518581
checkpoint-1890/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e0ebb4efe1dd97abeeedfb085bbfb1f8c1e2366889d006a732ada21b1bfa5e6d
3
+ size 557982265
checkpoint-1890/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:74ac93a5990ba355a30409caff58865c74ea4121f187248aad534c2016c69463
3
+ size 14503
checkpoint-1890/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d8b557902c70dd900c18634e2e38ce5ed11a803cb71ada011bcb53cb0a166fe
3
+ size 559
checkpoint-1890/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:461ac14fbc4b5cc8d8690234e19d57e00df5b91375a7476b64f578337c81a64b
3
+ size 623
checkpoint-1890/special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}}
checkpoint-1890/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-1890/tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>", "add_prefix_space": false, "errors": "replace", "sep_token": "</s>", "cls_token": "<s>", "pad_token": "<pad>", "mask_token": "<mask>", "trim_offsets": true, "model_max_length": 1024, "special_tokens_map_file": null, "name_or_path": "facebook/bart-base", "tokenizer_class": "BartTokenizer"}
checkpoint-1890/trainer_state.json ADDED
@@ -0,0 +1,212 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.18199852108955383,
3
+ "best_model_checkpoint": "outputs/bart-base-detox/checkpoint-1620",
4
+ "epoch": 13.995391705069125,
5
+ "global_step": 1890,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 1.0,
12
+ "learning_rate": 9e-06,
13
+ "loss": 0.5633,
14
+ "step": 135
15
+ },
16
+ {
17
+ "epoch": 1.0,
18
+ "eval_loss": 0.25235414505004883,
19
+ "eval_runtime": 12.2006,
20
+ "eval_samples_per_second": 254.085,
21
+ "eval_steps_per_second": 31.802,
22
+ "step": 135
23
+ },
24
+ {
25
+ "epoch": 2.0,
26
+ "learning_rate": 8.000000000000001e-06,
27
+ "loss": 0.2589,
28
+ "step": 270
29
+ },
30
+ {
31
+ "epoch": 2.0,
32
+ "eval_loss": 0.21927106380462646,
33
+ "eval_runtime": 11.2792,
34
+ "eval_samples_per_second": 274.842,
35
+ "eval_steps_per_second": 34.4,
36
+ "step": 270
37
+ },
38
+ {
39
+ "epoch": 3.0,
40
+ "learning_rate": 7e-06,
41
+ "loss": 0.2307,
42
+ "step": 405
43
+ },
44
+ {
45
+ "epoch": 3.0,
46
+ "eval_loss": 0.19929151237010956,
47
+ "eval_runtime": 11.2313,
48
+ "eval_samples_per_second": 276.016,
49
+ "eval_steps_per_second": 34.546,
50
+ "step": 405
51
+ },
52
+ {
53
+ "epoch": 4.0,
54
+ "learning_rate": 6e-06,
55
+ "loss": 0.2171,
56
+ "step": 540
57
+ },
58
+ {
59
+ "epoch": 4.0,
60
+ "eval_loss": 0.20016591250896454,
61
+ "eval_runtime": 11.0923,
62
+ "eval_samples_per_second": 279.473,
63
+ "eval_steps_per_second": 34.979,
64
+ "step": 540
65
+ },
66
+ {
67
+ "epoch": 5.0,
68
+ "learning_rate": 5e-06,
69
+ "loss": 0.2027,
70
+ "step": 675
71
+ },
72
+ {
73
+ "epoch": 5.0,
74
+ "eval_loss": 0.19366399943828583,
75
+ "eval_runtime": 11.2232,
76
+ "eval_samples_per_second": 276.213,
77
+ "eval_steps_per_second": 34.571,
78
+ "step": 675
79
+ },
80
+ {
81
+ "epoch": 6.0,
82
+ "learning_rate": 4.000000000000001e-06,
83
+ "loss": 0.1946,
84
+ "step": 810
85
+ },
86
+ {
87
+ "epoch": 6.0,
88
+ "eval_loss": 0.19715721905231476,
89
+ "eval_runtime": 11.2739,
90
+ "eval_samples_per_second": 274.973,
91
+ "eval_steps_per_second": 34.416,
92
+ "step": 810
93
+ },
94
+ {
95
+ "epoch": 7.0,
96
+ "learning_rate": 3e-06,
97
+ "loss": 0.1874,
98
+ "step": 945
99
+ },
100
+ {
101
+ "epoch": 7.0,
102
+ "eval_loss": 0.19172348082065582,
103
+ "eval_runtime": 11.1804,
104
+ "eval_samples_per_second": 277.27,
105
+ "eval_steps_per_second": 34.704,
106
+ "step": 945
107
+ },
108
+ {
109
+ "epoch": 8.0,
110
+ "learning_rate": 2.0000000000000003e-06,
111
+ "loss": 0.1853,
112
+ "step": 1080
113
+ },
114
+ {
115
+ "epoch": 8.0,
116
+ "eval_loss": 0.1867838054895401,
117
+ "eval_runtime": 11.2543,
118
+ "eval_samples_per_second": 275.451,
119
+ "eval_steps_per_second": 34.476,
120
+ "step": 1080
121
+ },
122
+ {
123
+ "epoch": 9.0,
124
+ "learning_rate": 1.0000000000000002e-06,
125
+ "loss": 0.1811,
126
+ "step": 1215
127
+ },
128
+ {
129
+ "epoch": 9.0,
130
+ "eval_loss": 0.18896569311618805,
131
+ "eval_runtime": 11.6639,
132
+ "eval_samples_per_second": 265.777,
133
+ "eval_steps_per_second": 33.265,
134
+ "step": 1215
135
+ },
136
+ {
137
+ "epoch": 10.0,
138
+ "learning_rate": 0.0,
139
+ "loss": 0.1776,
140
+ "step": 1350
141
+ },
142
+ {
143
+ "epoch": 10.0,
144
+ "eval_loss": 0.18712429702281952,
145
+ "eval_runtime": 11.9321,
146
+ "eval_samples_per_second": 259.803,
147
+ "eval_steps_per_second": 32.517,
148
+ "step": 1350
149
+ },
150
+ {
151
+ "epoch": 11.0,
152
+ "learning_rate": 4.5e-06,
153
+ "loss": 0.1798,
154
+ "step": 1485
155
+ },
156
+ {
157
+ "epoch": 11.0,
158
+ "eval_loss": 0.18577729165554047,
159
+ "eval_runtime": 11.5191,
160
+ "eval_samples_per_second": 269.117,
161
+ "eval_steps_per_second": 33.683,
162
+ "step": 1485
163
+ },
164
+ {
165
+ "epoch": 12.0,
166
+ "learning_rate": 4.000000000000001e-06,
167
+ "loss": 0.1745,
168
+ "step": 1620
169
+ },
170
+ {
171
+ "epoch": 12.0,
172
+ "eval_loss": 0.18199852108955383,
173
+ "eval_runtime": 11.54,
174
+ "eval_samples_per_second": 268.63,
175
+ "eval_steps_per_second": 33.622,
176
+ "step": 1620
177
+ },
178
+ {
179
+ "epoch": 13.0,
180
+ "learning_rate": 3.5e-06,
181
+ "loss": 0.1689,
182
+ "step": 1755
183
+ },
184
+ {
185
+ "epoch": 13.0,
186
+ "eval_loss": 0.18266141414642334,
187
+ "eval_runtime": 11.4865,
188
+ "eval_samples_per_second": 269.881,
189
+ "eval_steps_per_second": 33.779,
190
+ "step": 1755
191
+ },
192
+ {
193
+ "epoch": 14.0,
194
+ "learning_rate": 3e-06,
195
+ "loss": 0.1707,
196
+ "step": 1890
197
+ },
198
+ {
199
+ "epoch": 14.0,
200
+ "eval_loss": 0.18427973985671997,
201
+ "eval_runtime": 11.7088,
202
+ "eval_samples_per_second": 264.757,
203
+ "eval_steps_per_second": 33.137,
204
+ "step": 1890
205
+ }
206
+ ],
207
+ "max_steps": 2700,
208
+ "num_train_epochs": 20,
209
+ "total_flos": 7535299402874880.0,
210
+ "trial_name": null,
211
+ "trial_params": null
212
+ }
checkpoint-1890/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:abd235b48e5708905b15febf940f8c469a46192ae834301997bdf033c3918692
3
+ size 3183
checkpoint-1890/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-2025/added_tokens.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"<CSD>": 50265}
checkpoint-2025/config.json ADDED
@@ -0,0 +1,75 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "facebook/bart-base",
3
+ "activation_dropout": 0.1,
4
+ "activation_function": "gelu",
5
+ "add_bias_logits": false,
6
+ "add_final_layer_norm": false,
7
+ "architectures": [
8
+ "BartForConditionalGeneration"
9
+ ],
10
+ "attention_dropout": 0.1,
11
+ "bos_token_id": 0,
12
+ "classif_dropout": 0.1,
13
+ "classifier_dropout": 0.0,
14
+ "d_model": 768,
15
+ "decoder_attention_heads": 12,
16
+ "decoder_ffn_dim": 3072,
17
+ "decoder_layerdrop": 0.0,
18
+ "decoder_layers": 6,
19
+ "decoder_start_token_id": 2,
20
+ "dropout": 0.1,
21
+ "early_stopping": true,
22
+ "encoder_attention_heads": 12,
23
+ "encoder_ffn_dim": 3072,
24
+ "encoder_layerdrop": 0.0,
25
+ "encoder_layers": 6,
26
+ "eos_token_id": 2,
27
+ "forced_bos_token_id": 0,
28
+ "forced_eos_token_id": 2,
29
+ "gradient_checkpointing": false,
30
+ "id2label": {
31
+ "0": "LABEL_0",
32
+ "1": "LABEL_1",
33
+ "2": "LABEL_2"
34
+ },
35
+ "init_std": 0.02,
36
+ "is_encoder_decoder": true,
37
+ "label2id": {
38
+ "LABEL_0": 0,
39
+ "LABEL_1": 1,
40
+ "LABEL_2": 2
41
+ },
42
+ "max_position_embeddings": 1024,
43
+ "model_type": "bart",
44
+ "no_repeat_ngram_size": 3,
45
+ "normalize_before": false,
46
+ "normalize_embedding": true,
47
+ "num_beams": 4,
48
+ "num_hidden_layers": 6,
49
+ "pad_token_id": 1,
50
+ "scale_embedding": false,
51
+ "task_specific_params": {
52
+ "summarization": {
53
+ "length_penalty": 1.0,
54
+ "max_length": 128,
55
+ "min_length": 12,
56
+ "num_beams": 4
57
+ },
58
+ "summarization_cnn": {
59
+ "length_penalty": 2.0,
60
+ "max_length": 142,
61
+ "min_length": 56,
62
+ "num_beams": 4
63
+ },
64
+ "summarization_xsum": {
65
+ "length_penalty": 1.0,
66
+ "max_length": 62,
67
+ "min_length": 11,
68
+ "num_beams": 6
69
+ }
70
+ },
71
+ "torch_dtype": "float32",
72
+ "transformers_version": "4.16.2",
73
+ "use_cache": false,
74
+ "vocab_size": 50266
75
+ }
checkpoint-2025/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-2025/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d175da92b8ebe427565fbff8857967828b46bae2f3f4939ec3689e6aebcba30
3
+ size 1115518581
checkpoint-2025/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2587f3e4c192900aeac4f98d331a36359460c40ecf6b2285963af12fd0466a15
3
+ size 557982265
checkpoint-2025/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5b7b94e2e5e9e5f8433bcd9a18eecc241bcdfd97d1792f33d984ea49450386b8
3
+ size 14503
checkpoint-2025/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ce3c9145f761afa6aa2f997a1915883807b35a6937675ab3074cea5a3943af18
3
+ size 559
checkpoint-2025/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:60014359662c7e7b442f8ad74f9b309fa188d800f0b25ff7935a57f955c547f3
3
+ size 623
checkpoint-2025/special_tokens_map.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}}
checkpoint-2025/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-2025/tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>", "add_prefix_space": false, "errors": "replace", "sep_token": "</s>", "cls_token": "<s>", "pad_token": "<pad>", "mask_token": "<mask>", "trim_offsets": true, "model_max_length": 1024, "special_tokens_map_file": null, "name_or_path": "facebook/bart-base", "tokenizer_class": "BartTokenizer"}
checkpoint-2025/trainer_state.json ADDED
@@ -0,0 +1,226 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.18199852108955383,
3
+ "best_model_checkpoint": "outputs/bart-base-detox/checkpoint-1620",
4
+ "epoch": 14.995391705069125,
5
+ "global_step": 2025,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 1.0,
12
+ "learning_rate": 9e-06,
13
+ "loss": 0.5633,
14
+ "step": 135
15
+ },
16
+ {
17
+ "epoch": 1.0,
18
+ "eval_loss": 0.25235414505004883,
19
+ "eval_runtime": 12.2006,
20
+ "eval_samples_per_second": 254.085,
21
+ "eval_steps_per_second": 31.802,
22
+ "step": 135
23
+ },
24
+ {
25
+ "epoch": 2.0,
26
+ "learning_rate": 8.000000000000001e-06,
27
+ "loss": 0.2589,
28
+ "step": 270
29
+ },
30
+ {
31
+ "epoch": 2.0,
32
+ "eval_loss": 0.21927106380462646,
33
+ "eval_runtime": 11.2792,
34
+ "eval_samples_per_second": 274.842,
35
+ "eval_steps_per_second": 34.4,
36
+ "step": 270
37
+ },
38
+ {
39
+ "epoch": 3.0,
40
+ "learning_rate": 7e-06,
41
+ "loss": 0.2307,
42
+ "step": 405
43
+ },
44
+ {
45
+ "epoch": 3.0,
46
+ "eval_loss": 0.19929151237010956,
47
+ "eval_runtime": 11.2313,
48
+ "eval_samples_per_second": 276.016,
49
+ "eval_steps_per_second": 34.546,
50
+ "step": 405
51
+ },
52
+ {
53
+ "epoch": 4.0,
54
+ "learning_rate": 6e-06,
55
+ "loss": 0.2171,
56
+ "step": 540
57
+ },
58
+ {
59
+ "epoch": 4.0,
60
+ "eval_loss": 0.20016591250896454,
61
+ "eval_runtime": 11.0923,
62
+ "eval_samples_per_second": 279.473,
63
+ "eval_steps_per_second": 34.979,
64
+ "step": 540
65
+ },
66
+ {
67
+ "epoch": 5.0,
68
+ "learning_rate": 5e-06,
69
+ "loss": 0.2027,
70
+ "step": 675
71
+ },
72
+ {
73
+ "epoch": 5.0,
74
+ "eval_loss": 0.19366399943828583,
75
+ "eval_runtime": 11.2232,
76
+ "eval_samples_per_second": 276.213,
77
+ "eval_steps_per_second": 34.571,
78
+ "step": 675
79
+ },
80
+ {
81
+ "epoch": 6.0,
82
+ "learning_rate": 4.000000000000001e-06,
83
+ "loss": 0.1946,
84
+ "step": 810
85
+ },
86
+ {
87
+ "epoch": 6.0,
88
+ "eval_loss": 0.19715721905231476,
89
+ "eval_runtime": 11.2739,
90
+ "eval_samples_per_second": 274.973,
91
+ "eval_steps_per_second": 34.416,
92
+ "step": 810
93
+ },
94
+ {
95
+ "epoch": 7.0,
96
+ "learning_rate": 3e-06,
97
+ "loss": 0.1874,
98
+ "step": 945
99
+ },
100
+ {
101
+ "epoch": 7.0,
102
+ "eval_loss": 0.19172348082065582,
103
+ "eval_runtime": 11.1804,
104
+ "eval_samples_per_second": 277.27,
105
+ "eval_steps_per_second": 34.704,
106
+ "step": 945
107
+ },
108
+ {
109
+ "epoch": 8.0,
110
+ "learning_rate": 2.0000000000000003e-06,
111
+ "loss": 0.1853,
112
+ "step": 1080
113
+ },
114
+ {
115
+ "epoch": 8.0,
116
+ "eval_loss": 0.1867838054895401,
117
+ "eval_runtime": 11.2543,
118
+ "eval_samples_per_second": 275.451,
119
+ "eval_steps_per_second": 34.476,
120
+ "step": 1080
121
+ },
122
+ {
123
+ "epoch": 9.0,
124
+ "learning_rate": 1.0000000000000002e-06,
125
+ "loss": 0.1811,
126
+ "step": 1215
127
+ },
128
+ {
129
+ "epoch": 9.0,
130
+ "eval_loss": 0.18896569311618805,
131
+ "eval_runtime": 11.6639,
132
+ "eval_samples_per_second": 265.777,
133
+ "eval_steps_per_second": 33.265,
134
+ "step": 1215
135
+ },
136
+ {
137
+ "epoch": 10.0,
138
+ "learning_rate": 0.0,
139
+ "loss": 0.1776,
140
+ "step": 1350
141
+ },
142
+ {
143
+ "epoch": 10.0,
144
+ "eval_loss": 0.18712429702281952,
145
+ "eval_runtime": 11.9321,
146
+ "eval_samples_per_second": 259.803,
147
+ "eval_steps_per_second": 32.517,
148
+ "step": 1350
149
+ },
150
+ {
151
+ "epoch": 11.0,
152
+ "learning_rate": 4.5e-06,
153
+ "loss": 0.1798,
154
+ "step": 1485
155
+ },
156
+ {
157
+ "epoch": 11.0,
158
+ "eval_loss": 0.18577729165554047,
159
+ "eval_runtime": 11.5191,
160
+ "eval_samples_per_second": 269.117,
161
+ "eval_steps_per_second": 33.683,
162
+ "step": 1485
163
+ },
164
+ {
165
+ "epoch": 12.0,
166
+ "learning_rate": 4.000000000000001e-06,
167
+ "loss": 0.1745,
168
+ "step": 1620
169
+ },
170
+ {
171
+ "epoch": 12.0,
172
+ "eval_loss": 0.18199852108955383,
173
+ "eval_runtime": 11.54,
174
+ "eval_samples_per_second": 268.63,
175
+ "eval_steps_per_second": 33.622,
176
+ "step": 1620
177
+ },
178
+ {
179
+ "epoch": 13.0,
180
+ "learning_rate": 3.5e-06,
181
+ "loss": 0.1689,
182
+ "step": 1755
183
+ },
184
+ {
185
+ "epoch": 13.0,
186
+ "eval_loss": 0.18266141414642334,
187
+ "eval_runtime": 11.4865,
188
+ "eval_samples_per_second": 269.881,
189
+ "eval_steps_per_second": 33.779,
190
+ "step": 1755
191
+ },
192
+ {
193
+ "epoch": 14.0,
194
+ "learning_rate": 3e-06,
195
+ "loss": 0.1707,
196
+ "step": 1890
197
+ },
198
+ {
199
+ "epoch": 14.0,
200
+ "eval_loss": 0.18427973985671997,
201
+ "eval_runtime": 11.7088,
202
+ "eval_samples_per_second": 264.757,
203
+ "eval_steps_per_second": 33.137,
204
+ "step": 1890
205
+ },
206
+ {
207
+ "epoch": 15.0,
208
+ "learning_rate": 2.5e-06,
209
+ "loss": 0.1658,
210
+ "step": 2025
211
+ },
212
+ {
213
+ "epoch": 15.0,
214
+ "eval_loss": 0.18342117965221405,
215
+ "eval_runtime": 11.3728,
216
+ "eval_samples_per_second": 272.58,
217
+ "eval_steps_per_second": 34.116,
218
+ "step": 2025
219
+ }
220
+ ],
221
+ "max_steps": 2700,
222
+ "num_train_epochs": 20,
223
+ "total_flos": 8074835187793920.0,
224
+ "trial_name": null,
225
+ "trial_params": null
226
+ }
checkpoint-2025/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:abd235b48e5708905b15febf940f8c469a46192ae834301997bdf033c3918692
3
+ size 3183
checkpoint-2025/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8e37fdf8067334e03eceeb8b6f8eca1a1a74d2e9efa0d20b01bdddda9b778fb4
3
  size 557982265
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2587f3e4c192900aeac4f98d331a36359460c40ecf6b2285963af12fd0466a15
3
  size 557982265