Hugging Face's logo

Riyagarg01
/
practice

Model card Files
xet
Community
Riyagarg01 commited on
Commit
a84b8fb
·
1 Parent(s): 6279ebe

new model new

Browse files
Files changed (25) hide show
  1. checkpoint-1501/config.json +74 -0
  2. checkpoint-1501/merges.txt +0 -0
  3. checkpoint-1501/optimizer.pt +3 -0
  4. checkpoint-1501/pytorch_model.bin +3 -0
  5. checkpoint-1501/rng_state.pth +3 -0
  6. checkpoint-1501/scheduler.pt +3 -0
  7. checkpoint-1501/special_tokens_map.json +1 -0
  8. checkpoint-1501/tokenizer.json +0 -0
  9. checkpoint-1501/tokenizer_config.json +1 -0
  10. checkpoint-1501/trainer_state.json +196 -0
  11. checkpoint-1501/training_args.bin +3 -0
  12. checkpoint-1501/vocab.json +0 -0
  13. checkpoint-2001/config.json +74 -0
  14. checkpoint-2001/merges.txt +0 -0
  15. checkpoint-2001/optimizer.pt +3 -0
  16. checkpoint-2001/practice +1 -0
  17. checkpoint-2001/pytorch_model.bin +3 -0
  18. checkpoint-2001/rng_state.pth +3 -0
  19. checkpoint-2001/scheduler.pt +3 -0
  20. checkpoint-2001/special_tokens_map.json +1 -0
  21. checkpoint-2001/tokenizer.json +0 -0
  22. checkpoint-2001/tokenizer_config.json +1 -0
  23. checkpoint-2001/trainer_state.json +256 -0
  24. checkpoint-2001/training_args.bin +3 -0
  25. checkpoint-2001/vocab.json +0 -0
checkpoint-1501/config.json ADDED
@@ -0,0 +1,74 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "mse30/bart-base-finetuned-pubmed",
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_eos_token_id": 2,
28
+ "gradient_checkpointing": false,
29
+ "id2label": {
30
+ "0": "LABEL_0",
31
+ "1": "LABEL_1",
32
+ "2": "LABEL_2"
33
+ },
34
+ "init_std": 0.02,
35
+ "is_encoder_decoder": true,
36
+ "label2id": {
37
+ "LABEL_0": 0,
38
+ "LABEL_1": 1,
39
+ "LABEL_2": 2
40
+ },
41
+ "max_position_embeddings": 1024,
42
+ "model_type": "bart",
43
+ "no_repeat_ngram_size": 3,
44
+ "normalize_before": false,
45
+ "normalize_embedding": true,
46
+ "num_beams": 4,
47
+ "num_hidden_layers": 6,
48
+ "pad_token_id": 1,
49
+ "scale_embedding": false,
50
+ "task_specific_params": {
51
+ "summarization": {
52
+ "length_penalty": 1.0,
53
+ "max_length": 128,
54
+ "min_length": 12,
55
+ "num_beams": 4
56
+ },
57
+ "summarization_cnn": {
58
+ "length_penalty": 2.0,
59
+ "max_length": 142,
60
+ "min_length": 56,
61
+ "num_beams": 4
62
+ },
63
+ "summarization_xsum": {
64
+ "length_penalty": 1.0,
65
+ "max_length": 62,
66
+ "min_length": 11,
67
+ "num_beams": 6
68
+ }
69
+ },
70
+ "torch_dtype": "float32",
71
+ "transformers_version": "4.17.0",
72
+ "use_cache": true,
73
+ "vocab_size": 50265
74
+ }
checkpoint-1501/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-1501/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f463290e1af5e7fd7dc5a02e4145e51f2b0b54fb2d97e49ba6290cbbe4a52a16
3
+ size 1115513717
checkpoint-1501/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b522d428b2bc94feb4609f8af22e8710786ac95cf52547a14865b43f3906bba8
3
+ size 557979897
checkpoint-1501/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:711f03dcc59b9f8dc08326df8cd11830f0cd9b6df1d2099fa4d515f414009d6f
3
+ size 14503
checkpoint-1501/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:948709ab58459baf217b15d02ea1a3614eb8668501108aef40a6eb529f12b000
3
+ size 623
checkpoint-1501/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-1501/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-1501/tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"errors": "replace", "bos_token": "<s>", "eos_token": "</s>", "sep_token": "</s>", "cls_token": "<s>", "unk_token": "<unk>", "pad_token": "<pad>", "mask_token": "<mask>", "add_prefix_space": false, "trim_offsets": true, "model_max_length": 1024, "special_tokens_map_file": null, "name_or_path": "mse30/bart-base-finetuned-pubmed", "tokenizer_class": "BartTokenizer"}
checkpoint-1501/trainer_state.json ADDED
@@ -0,0 +1,196 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 68.18181818181819,
5
+ "global_step": 1500,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 2.27,
12
+ "learning_rate": 3e-06,
13
+ "loss": 6.9841,
14
+ "step": 50
15
+ },
16
+ {
17
+ "epoch": 4.55,
18
+ "learning_rate": 6e-06,
19
+ "loss": 3.6549,
20
+ "step": 100
21
+ },
22
+ {
23
+ "epoch": 6.82,
24
+ "learning_rate": 9e-06,
25
+ "loss": 2.3101,
26
+ "step": 150
27
+ },
28
+ {
29
+ "epoch": 9.09,
30
+ "learning_rate": 1.2e-05,
31
+ "loss": 1.9692,
32
+ "step": 200
33
+ },
34
+ {
35
+ "epoch": 11.36,
36
+ "learning_rate": 1.5e-05,
37
+ "loss": 1.7899,
38
+ "step": 250
39
+ },
40
+ {
41
+ "epoch": 13.64,
42
+ "learning_rate": 1.8e-05,
43
+ "loss": 1.6814,
44
+ "step": 300
45
+ },
46
+ {
47
+ "epoch": 15.91,
48
+ "learning_rate": 2.1e-05,
49
+ "loss": 1.6234,
50
+ "step": 350
51
+ },
52
+ {
53
+ "epoch": 18.18,
54
+ "learning_rate": 2.4e-05,
55
+ "loss": 1.5821,
56
+ "step": 400
57
+ },
58
+ {
59
+ "epoch": 20.45,
60
+ "learning_rate": 2.7000000000000002e-05,
61
+ "loss": 1.5501,
62
+ "step": 450
63
+ },
64
+ {
65
+ "epoch": 22.73,
66
+ "learning_rate": 3e-05,
67
+ "loss": 1.5385,
68
+ "step": 500
69
+ },
70
+ {
71
+ "epoch": 25.0,
72
+ "learning_rate": 2.911764705882353e-05,
73
+ "loss": 1.5289,
74
+ "step": 550
75
+ },
76
+ {
77
+ "epoch": 27.27,
78
+ "learning_rate": 2.823529411764706e-05,
79
+ "loss": 1.5101,
80
+ "step": 600
81
+ },
82
+ {
83
+ "epoch": 29.55,
84
+ "learning_rate": 2.735294117647059e-05,
85
+ "loss": 1.4921,
86
+ "step": 650
87
+ },
88
+ {
89
+ "epoch": 31.82,
90
+ "learning_rate": 2.647058823529412e-05,
91
+ "loss": 1.4881,
92
+ "step": 700
93
+ },
94
+ {
95
+ "epoch": 34.09,
96
+ "learning_rate": 2.5588235294117648e-05,
97
+ "loss": 1.4834,
98
+ "step": 750
99
+ },
100
+ {
101
+ "epoch": 36.36,
102
+ "learning_rate": 2.4705882352941174e-05,
103
+ "loss": 1.4783,
104
+ "step": 800
105
+ },
106
+ {
107
+ "epoch": 38.64,
108
+ "learning_rate": 2.3823529411764704e-05,
109
+ "loss": 1.4742,
110
+ "step": 850
111
+ },
112
+ {
113
+ "epoch": 40.91,
114
+ "learning_rate": 2.2941176470588233e-05,
115
+ "loss": 1.4671,
116
+ "step": 900
117
+ },
118
+ {
119
+ "epoch": 43.18,
120
+ "learning_rate": 2.2058823529411766e-05,
121
+ "loss": 1.4711,
122
+ "step": 950
123
+ },
124
+ {
125
+ "epoch": 45.45,
126
+ "learning_rate": 2.1176470588235296e-05,
127
+ "loss": 1.465,
128
+ "step": 1000
129
+ },
130
+ {
131
+ "epoch": 47.73,
132
+ "learning_rate": 2.0294117647058825e-05,
133
+ "loss": 1.4592,
134
+ "step": 1050
135
+ },
136
+ {
137
+ "epoch": 50.0,
138
+ "learning_rate": 1.9411764705882355e-05,
139
+ "loss": 1.4607,
140
+ "step": 1100
141
+ },
142
+ {
143
+ "epoch": 52.27,
144
+ "learning_rate": 1.8529411764705884e-05,
145
+ "loss": 1.4629,
146
+ "step": 1150
147
+ },
148
+ {
149
+ "epoch": 54.55,
150
+ "learning_rate": 1.7647058823529414e-05,
151
+ "loss": 1.4577,
152
+ "step": 1200
153
+ },
154
+ {
155
+ "epoch": 56.82,
156
+ "learning_rate": 1.6764705882352943e-05,
157
+ "loss": 1.4557,
158
+ "step": 1250
159
+ },
160
+ {
161
+ "epoch": 59.09,
162
+ "learning_rate": 1.5882352941176473e-05,
163
+ "loss": 1.4525,
164
+ "step": 1300
165
+ },
166
+ {
167
+ "epoch": 61.36,
168
+ "learning_rate": 1.5e-05,
169
+ "loss": 1.4519,
170
+ "step": 1350
171
+ },
172
+ {
173
+ "epoch": 63.64,
174
+ "learning_rate": 1.411764705882353e-05,
175
+ "loss": 1.4513,
176
+ "step": 1400
177
+ },
178
+ {
179
+ "epoch": 65.91,
180
+ "learning_rate": 1.323529411764706e-05,
181
+ "loss": 1.4517,
182
+ "step": 1450
183
+ },
184
+ {
185
+ "epoch": 68.18,
186
+ "learning_rate": 1.2352941176470587e-05,
187
+ "loss": 1.4493,
188
+ "step": 1500
189
+ }
190
+ ],
191
+ "max_steps": 2200,
192
+ "num_train_epochs": 100,
193
+ "total_flos": 3534032511959040.0,
194
+ "trial_name": null,
195
+ "trial_params": null
196
+ }
checkpoint-1501/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f4e16c82fc920541fb0be31b27b9faa1943666c9162486d550f23aae767e9831
3
+ size 3119
checkpoint-1501/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-2001/config.json ADDED
@@ -0,0 +1,74 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "mse30/bart-base-finetuned-pubmed",
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_eos_token_id": 2,
28
+ "gradient_checkpointing": false,
29
+ "id2label": {
30
+ "0": "LABEL_0",
31
+ "1": "LABEL_1",
32
+ "2": "LABEL_2"
33
+ },
34
+ "init_std": 0.02,
35
+ "is_encoder_decoder": true,
36
+ "label2id": {
37
+ "LABEL_0": 0,
38
+ "LABEL_1": 1,
39
+ "LABEL_2": 2
40
+ },
41
+ "max_position_embeddings": 1024,
42
+ "model_type": "bart",
43
+ "no_repeat_ngram_size": 3,
44
+ "normalize_before": false,
45
+ "normalize_embedding": true,
46
+ "num_beams": 4,
47
+ "num_hidden_layers": 6,
48
+ "pad_token_id": 1,
49
+ "scale_embedding": false,
50
+ "task_specific_params": {
51
+ "summarization": {
52
+ "length_penalty": 1.0,
53
+ "max_length": 128,
54
+ "min_length": 12,
55
+ "num_beams": 4
56
+ },
57
+ "summarization_cnn": {
58
+ "length_penalty": 2.0,
59
+ "max_length": 142,
60
+ "min_length": 56,
61
+ "num_beams": 4
62
+ },
63
+ "summarization_xsum": {
64
+ "length_penalty": 1.0,
65
+ "max_length": 62,
66
+ "min_length": 11,
67
+ "num_beams": 6
68
+ }
69
+ },
70
+ "torch_dtype": "float32",
71
+ "transformers_version": "4.17.0",
72
+ "use_cache": true,
73
+ "vocab_size": 50265
74
+ }
checkpoint-2001/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-2001/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df603f6c2c4dbddfb98c56c2a95908d535a6d7d4296647d3dac3c84a3385680b
3
+ size 1115513717
checkpoint-2001/practice ADDED
@@ -0,0 +1 @@
 
 
1
+ Subproject commit 6279ebe45524781c41d13adde4a44b93ac16f94b
checkpoint-2001/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b9d4a4d9817d60c0fb2a539bee6fc2ac261ca4eceddd37b0490317f3338922d
3
+ size 557979897
checkpoint-2001/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2cd06c17946498bd195533f43686eea0b8f81a1cfcdeb9438b6f754f80e3dcb6
3
+ size 14503
checkpoint-2001/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d1b3c04811897c85d0bb1701f0f07ac9b7b37a57bd95a011e5a6e2f70a196485
3
+ size 623
checkpoint-2001/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-2001/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-2001/tokenizer_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"errors": "replace", "bos_token": "<s>", "eos_token": "</s>", "sep_token": "</s>", "cls_token": "<s>", "unk_token": "<unk>", "pad_token": "<pad>", "mask_token": "<mask>", "add_prefix_space": false, "trim_offsets": true, "model_max_length": 1024, "special_tokens_map_file": null, "name_or_path": "mse30/bart-base-finetuned-pubmed", "tokenizer_class": "BartTokenizer"}
checkpoint-2001/trainer_state.json ADDED
@@ -0,0 +1,256 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 90.9090909090909,
5
+ "global_step": 2000,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 2.27,
12
+ "learning_rate": 3e-06,
13
+ "loss": 6.9841,
14
+ "step": 50
15
+ },
16
+ {
17
+ "epoch": 4.55,
18
+ "learning_rate": 6e-06,
19
+ "loss": 3.6549,
20
+ "step": 100
21
+ },
22
+ {
23
+ "epoch": 6.82,
24
+ "learning_rate": 9e-06,
25
+ "loss": 2.3101,
26
+ "step": 150
27
+ },
28
+ {
29
+ "epoch": 9.09,
30
+ "learning_rate": 1.2e-05,
31
+ "loss": 1.9692,
32
+ "step": 200
33
+ },
34
+ {
35
+ "epoch": 11.36,
36
+ "learning_rate": 1.5e-05,
37
+ "loss": 1.7899,
38
+ "step": 250
39
+ },
40
+ {
41
+ "epoch": 13.64,
42
+ "learning_rate": 1.8e-05,
43
+ "loss": 1.6814,
44
+ "step": 300
45
+ },
46
+ {
47
+ "epoch": 15.91,
48
+ "learning_rate": 2.1e-05,
49
+ "loss": 1.6234,
50
+ "step": 350
51
+ },
52
+ {
53
+ "epoch": 18.18,
54
+ "learning_rate": 2.4e-05,
55
+ "loss": 1.5821,
56
+ "step": 400
57
+ },
58
+ {
59
+ "epoch": 20.45,
60
+ "learning_rate": 2.7000000000000002e-05,
61
+ "loss": 1.5501,
62
+ "step": 450
63
+ },
64
+ {
65
+ "epoch": 22.73,
66
+ "learning_rate": 3e-05,
67
+ "loss": 1.5385,
68
+ "step": 500
69
+ },
70
+ {
71
+ "epoch": 25.0,
72
+ "learning_rate": 2.911764705882353e-05,
73
+ "loss": 1.5289,
74
+ "step": 550
75
+ },
76
+ {
77
+ "epoch": 27.27,
78
+ "learning_rate": 2.823529411764706e-05,
79
+ "loss": 1.5101,
80
+ "step": 600
81
+ },
82
+ {
83
+ "epoch": 29.55,
84
+ "learning_rate": 2.735294117647059e-05,
85
+ "loss": 1.4921,
86
+ "step": 650
87
+ },
88
+ {
89
+ "epoch": 31.82,
90
+ "learning_rate": 2.647058823529412e-05,
91
+ "loss": 1.4881,
92
+ "step": 700
93
+ },
94
+ {
95
+ "epoch": 34.09,
96
+ "learning_rate": 2.5588235294117648e-05,
97
+ "loss": 1.4834,
98
+ "step": 750
99
+ },
100
+ {
101
+ "epoch": 36.36,
102
+ "learning_rate": 2.4705882352941174e-05,
103
+ "loss": 1.4783,
104
+ "step": 800
105
+ },
106
+ {
107
+ "epoch": 38.64,
108
+ "learning_rate": 2.3823529411764704e-05,
109
+ "loss": 1.4742,
110
+ "step": 850
111
+ },
112
+ {
113
+ "epoch": 40.91,
114
+ "learning_rate": 2.2941176470588233e-05,
115
+ "loss": 1.4671,
116
+ "step": 900
117
+ },
118
+ {
119
+ "epoch": 43.18,
120
+ "learning_rate": 2.2058823529411766e-05,
121
+ "loss": 1.4711,
122
+ "step": 950
123
+ },
124
+ {
125
+ "epoch": 45.45,
126
+ "learning_rate": 2.1176470588235296e-05,
127
+ "loss": 1.465,
128
+ "step": 1000
129
+ },
130
+ {
131
+ "epoch": 47.73,
132
+ "learning_rate": 2.0294117647058825e-05,
133
+ "loss": 1.4592,
134
+ "step": 1050
135
+ },
136
+ {
137
+ "epoch": 50.0,
138
+ "learning_rate": 1.9411764705882355e-05,
139
+ "loss": 1.4607,
140
+ "step": 1100
141
+ },
142
+ {
143
+ "epoch": 52.27,
144
+ "learning_rate": 1.8529411764705884e-05,
145
+ "loss": 1.4629,
146
+ "step": 1150
147
+ },
148
+ {
149
+ "epoch": 54.55,
150
+ "learning_rate": 1.7647058823529414e-05,
151
+ "loss": 1.4577,
152
+ "step": 1200
153
+ },
154
+ {
155
+ "epoch": 56.82,
156
+ "learning_rate": 1.6764705882352943e-05,
157
+ "loss": 1.4557,
158
+ "step": 1250
159
+ },
160
+ {
161
+ "epoch": 59.09,
162
+ "learning_rate": 1.5882352941176473e-05,
163
+ "loss": 1.4525,
164
+ "step": 1300
165
+ },
166
+ {
167
+ "epoch": 61.36,
168
+ "learning_rate": 1.5e-05,
169
+ "loss": 1.4519,
170
+ "step": 1350
171
+ },
172
+ {
173
+ "epoch": 63.64,
174
+ "learning_rate": 1.411764705882353e-05,
175
+ "loss": 1.4513,
176
+ "step": 1400
177
+ },
178
+ {
179
+ "epoch": 65.91,
180
+ "learning_rate": 1.323529411764706e-05,
181
+ "loss": 1.4517,
182
+ "step": 1450
183
+ },
184
+ {
185
+ "epoch": 68.18,
186
+ "learning_rate": 1.2352941176470587e-05,
187
+ "loss": 1.4493,
188
+ "step": 1500
189
+ },
190
+ {
191
+ "epoch": 70.45,
192
+ "learning_rate": 1.1470588235294117e-05,
193
+ "loss": 1.4502,
194
+ "step": 1550
195
+ },
196
+ {
197
+ "epoch": 72.73,
198
+ "learning_rate": 1.0588235294117648e-05,
199
+ "loss": 1.4598,
200
+ "step": 1600
201
+ },
202
+ {
203
+ "epoch": 75.0,
204
+ "learning_rate": 9.705882352941177e-06,
205
+ "loss": 1.4471,
206
+ "step": 1650
207
+ },
208
+ {
209
+ "epoch": 77.27,
210
+ "learning_rate": 8.823529411764707e-06,
211
+ "loss": 1.446,
212
+ "step": 1700
213
+ },
214
+ {
215
+ "epoch": 79.55,
216
+ "learning_rate": 7.941176470588236e-06,
217
+ "loss": 1.4473,
218
+ "step": 1750
219
+ },
220
+ {
221
+ "epoch": 81.82,
222
+ "learning_rate": 7.058823529411765e-06,
223
+ "loss": 1.4453,
224
+ "step": 1800
225
+ },
226
+ {
227
+ "epoch": 84.09,
228
+ "learning_rate": 6.176470588235294e-06,
229
+ "loss": 1.4462,
230
+ "step": 1850
231
+ },
232
+ {
233
+ "epoch": 86.36,
234
+ "learning_rate": 5.294117647058824e-06,
235
+ "loss": 1.4449,
236
+ "step": 1900
237
+ },
238
+ {
239
+ "epoch": 88.64,
240
+ "learning_rate": 4.411764705882353e-06,
241
+ "loss": 1.4489,
242
+ "step": 1950
243
+ },
244
+ {
245
+ "epoch": 90.91,
246
+ "learning_rate": 3.5294117647058825e-06,
247
+ "loss": 1.4447,
248
+ "step": 2000
249
+ }
250
+ ],
251
+ "max_steps": 2200,
252
+ "num_train_epochs": 100,
253
+ "total_flos": 4713262822195200.0,
254
+ "trial_name": null,
255
+ "trial_params": null
256
+ }
checkpoint-2001/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f4e16c82fc920541fb0be31b27b9faa1943666c9162486d550f23aae767e9831
3
+ size 3119
checkpoint-2001/vocab.json ADDED
The diff for this file is too large to render. See raw diff