prompterminal commited on
Commit
6eec01a
·
verified ·
1 Parent(s): e3b5bd8

Upload folder using huggingface_hub

Browse files
checkpoint-760/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:939926b6b84304f6d0f0e4afd95c8857bfed45811841cf9fe711d4b0d9a26ebd
3
+ size 437987212
checkpoint-760/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c1a7a4121b36acd13fd76e6634388cde594800fee760cd4ec4d12463efd67939
3
+ size 871377227
checkpoint-760/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d13f9f4e680f55d9b4db63b3398bcabeb2100fe458786ee6cc9c5236ade96111
3
+ size 14645
checkpoint-760/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ff9ef4f7a5114b1ab6dfb479a822c7b3612c1e469cd35786b43cba512a3e16e
3
+ size 1465
checkpoint-760/trainer_state.json ADDED
@@ -0,0 +1,171 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 4.0,
6
+ "eval_steps": 500,
7
+ "global_step": 760,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.2631578947368421,
14
+ "grad_norm": 4.845608711242676,
15
+ "learning_rate": 4.9000000000000005e-06,
16
+ "loss": 2.3306,
17
+ "step": 50
18
+ },
19
+ {
20
+ "epoch": 0.5263157894736842,
21
+ "grad_norm": 4.860968112945557,
22
+ "learning_rate": 9.900000000000002e-06,
23
+ "loss": 1.928,
24
+ "step": 100
25
+ },
26
+ {
27
+ "epoch": 0.7894736842105263,
28
+ "grad_norm": 5.453705787658691,
29
+ "learning_rate": 1.49e-05,
30
+ "loss": 1.6681,
31
+ "step": 150
32
+ },
33
+ {
34
+ "epoch": 1.0,
35
+ "eval_loss": 1.570725440979004,
36
+ "eval_runtime": 1.5119,
37
+ "eval_samples_per_second": 1005.327,
38
+ "eval_steps_per_second": 15.874,
39
+ "step": 190
40
+ },
41
+ {
42
+ "epoch": 1.0526315789473684,
43
+ "grad_norm": 4.810089111328125,
44
+ "learning_rate": 1.9900000000000003e-05,
45
+ "loss": 1.5943,
46
+ "step": 200
47
+ },
48
+ {
49
+ "epoch": 1.3157894736842106,
50
+ "grad_norm": 13.012678146362305,
51
+ "learning_rate": 2.4900000000000002e-05,
52
+ "loss": 1.4694,
53
+ "step": 250
54
+ },
55
+ {
56
+ "epoch": 1.5789473684210527,
57
+ "grad_norm": 11.198631286621094,
58
+ "learning_rate": 2.9900000000000002e-05,
59
+ "loss": 1.3752,
60
+ "step": 300
61
+ },
62
+ {
63
+ "epoch": 1.8421052631578947,
64
+ "grad_norm": 9.748913764953613,
65
+ "learning_rate": 3.49e-05,
66
+ "loss": 1.2861,
67
+ "step": 350
68
+ },
69
+ {
70
+ "epoch": 2.0,
71
+ "eval_loss": 1.3308887481689453,
72
+ "eval_runtime": 1.544,
73
+ "eval_samples_per_second": 984.488,
74
+ "eval_steps_per_second": 15.545,
75
+ "step": 380
76
+ },
77
+ {
78
+ "epoch": 2.1052631578947367,
79
+ "grad_norm": 12.868274688720703,
80
+ "learning_rate": 3.99e-05,
81
+ "loss": 1.2325,
82
+ "step": 400
83
+ },
84
+ {
85
+ "epoch": 2.3684210526315788,
86
+ "grad_norm": 10.431174278259277,
87
+ "learning_rate": 4.49e-05,
88
+ "loss": 1.0542,
89
+ "step": 450
90
+ },
91
+ {
92
+ "epoch": 2.6315789473684212,
93
+ "grad_norm": 8.311651229858398,
94
+ "learning_rate": 4.99e-05,
95
+ "loss": 1.0175,
96
+ "step": 500
97
+ },
98
+ {
99
+ "epoch": 2.8947368421052633,
100
+ "grad_norm": 22.464628219604492,
101
+ "learning_rate": 4.4555555555555555e-05,
102
+ "loss": 1.0534,
103
+ "step": 550
104
+ },
105
+ {
106
+ "epoch": 3.0,
107
+ "eval_loss": 1.2336760759353638,
108
+ "eval_runtime": 1.5299,
109
+ "eval_samples_per_second": 993.557,
110
+ "eval_steps_per_second": 15.688,
111
+ "step": 570
112
+ },
113
+ {
114
+ "epoch": 3.1578947368421053,
115
+ "grad_norm": 12.188404083251953,
116
+ "learning_rate": 3.9000000000000006e-05,
117
+ "loss": 0.8699,
118
+ "step": 600
119
+ },
120
+ {
121
+ "epoch": 3.4210526315789473,
122
+ "grad_norm": 11.911046981811523,
123
+ "learning_rate": 3.3444444444444443e-05,
124
+ "loss": 0.6847,
125
+ "step": 650
126
+ },
127
+ {
128
+ "epoch": 3.6842105263157894,
129
+ "grad_norm": 11.840217590332031,
130
+ "learning_rate": 2.788888888888889e-05,
131
+ "loss": 0.7332,
132
+ "step": 700
133
+ },
134
+ {
135
+ "epoch": 3.9473684210526314,
136
+ "grad_norm": 19.36884117126465,
137
+ "learning_rate": 2.2333333333333335e-05,
138
+ "loss": 0.6441,
139
+ "step": 750
140
+ },
141
+ {
142
+ "epoch": 4.0,
143
+ "eval_loss": 1.3029890060424805,
144
+ "eval_runtime": 1.5383,
145
+ "eval_samples_per_second": 988.106,
146
+ "eval_steps_per_second": 15.602,
147
+ "step": 760
148
+ }
149
+ ],
150
+ "logging_steps": 50,
151
+ "max_steps": 950,
152
+ "num_input_tokens_seen": 0,
153
+ "num_train_epochs": 5,
154
+ "save_steps": 500,
155
+ "stateful_callbacks": {
156
+ "TrainerControl": {
157
+ "args": {
158
+ "should_epoch_stop": false,
159
+ "should_evaluate": false,
160
+ "should_log": false,
161
+ "should_save": true,
162
+ "should_training_stop": false
163
+ },
164
+ "attributes": {}
165
+ }
166
+ },
167
+ "total_flos": 0.0,
168
+ "train_batch_size": 32,
169
+ "trial_name": null,
170
+ "trial_params": null
171
+ }
checkpoint-760/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:edb39620e665d8678bed7e9532bd80b68760b6353c69212767e3bd300dad6d01
3
+ size 5841
checkpoint-950/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:217b88b7dcfa47a8512478f3cd24c3be19119948a1f0fe72695b6078bcee6141
3
+ size 437987212
checkpoint-950/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4f3ba61acdc0974d1d2cf9730af53fd59544992bb20f2197b64b8939c20e35ac
3
+ size 871377227
checkpoint-950/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eaef42598cde90799dea3ccdacc0bf522b8d57e89693a8cdc2dd174a7d71b4ab
3
+ size 14645
checkpoint-950/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f3d2378bc5b746c762327d4822ca1447f1f50eb97a95a925d360512fec0cf2bc
3
+ size 1465
checkpoint-950/trainer_state.json ADDED
@@ -0,0 +1,207 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 5.0,
6
+ "eval_steps": 500,
7
+ "global_step": 950,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.2631578947368421,
14
+ "grad_norm": 4.845608711242676,
15
+ "learning_rate": 4.9000000000000005e-06,
16
+ "loss": 2.3306,
17
+ "step": 50
18
+ },
19
+ {
20
+ "epoch": 0.5263157894736842,
21
+ "grad_norm": 4.860968112945557,
22
+ "learning_rate": 9.900000000000002e-06,
23
+ "loss": 1.928,
24
+ "step": 100
25
+ },
26
+ {
27
+ "epoch": 0.7894736842105263,
28
+ "grad_norm": 5.453705787658691,
29
+ "learning_rate": 1.49e-05,
30
+ "loss": 1.6681,
31
+ "step": 150
32
+ },
33
+ {
34
+ "epoch": 1.0,
35
+ "eval_loss": 1.570725440979004,
36
+ "eval_runtime": 1.5119,
37
+ "eval_samples_per_second": 1005.327,
38
+ "eval_steps_per_second": 15.874,
39
+ "step": 190
40
+ },
41
+ {
42
+ "epoch": 1.0526315789473684,
43
+ "grad_norm": 4.810089111328125,
44
+ "learning_rate": 1.9900000000000003e-05,
45
+ "loss": 1.5943,
46
+ "step": 200
47
+ },
48
+ {
49
+ "epoch": 1.3157894736842106,
50
+ "grad_norm": 13.012678146362305,
51
+ "learning_rate": 2.4900000000000002e-05,
52
+ "loss": 1.4694,
53
+ "step": 250
54
+ },
55
+ {
56
+ "epoch": 1.5789473684210527,
57
+ "grad_norm": 11.198631286621094,
58
+ "learning_rate": 2.9900000000000002e-05,
59
+ "loss": 1.3752,
60
+ "step": 300
61
+ },
62
+ {
63
+ "epoch": 1.8421052631578947,
64
+ "grad_norm": 9.748913764953613,
65
+ "learning_rate": 3.49e-05,
66
+ "loss": 1.2861,
67
+ "step": 350
68
+ },
69
+ {
70
+ "epoch": 2.0,
71
+ "eval_loss": 1.3308887481689453,
72
+ "eval_runtime": 1.544,
73
+ "eval_samples_per_second": 984.488,
74
+ "eval_steps_per_second": 15.545,
75
+ "step": 380
76
+ },
77
+ {
78
+ "epoch": 2.1052631578947367,
79
+ "grad_norm": 12.868274688720703,
80
+ "learning_rate": 3.99e-05,
81
+ "loss": 1.2325,
82
+ "step": 400
83
+ },
84
+ {
85
+ "epoch": 2.3684210526315788,
86
+ "grad_norm": 10.431174278259277,
87
+ "learning_rate": 4.49e-05,
88
+ "loss": 1.0542,
89
+ "step": 450
90
+ },
91
+ {
92
+ "epoch": 2.6315789473684212,
93
+ "grad_norm": 8.311651229858398,
94
+ "learning_rate": 4.99e-05,
95
+ "loss": 1.0175,
96
+ "step": 500
97
+ },
98
+ {
99
+ "epoch": 2.8947368421052633,
100
+ "grad_norm": 22.464628219604492,
101
+ "learning_rate": 4.4555555555555555e-05,
102
+ "loss": 1.0534,
103
+ "step": 550
104
+ },
105
+ {
106
+ "epoch": 3.0,
107
+ "eval_loss": 1.2336760759353638,
108
+ "eval_runtime": 1.5299,
109
+ "eval_samples_per_second": 993.557,
110
+ "eval_steps_per_second": 15.688,
111
+ "step": 570
112
+ },
113
+ {
114
+ "epoch": 3.1578947368421053,
115
+ "grad_norm": 12.188404083251953,
116
+ "learning_rate": 3.9000000000000006e-05,
117
+ "loss": 0.8699,
118
+ "step": 600
119
+ },
120
+ {
121
+ "epoch": 3.4210526315789473,
122
+ "grad_norm": 11.911046981811523,
123
+ "learning_rate": 3.3444444444444443e-05,
124
+ "loss": 0.6847,
125
+ "step": 650
126
+ },
127
+ {
128
+ "epoch": 3.6842105263157894,
129
+ "grad_norm": 11.840217590332031,
130
+ "learning_rate": 2.788888888888889e-05,
131
+ "loss": 0.7332,
132
+ "step": 700
133
+ },
134
+ {
135
+ "epoch": 3.9473684210526314,
136
+ "grad_norm": 19.36884117126465,
137
+ "learning_rate": 2.2333333333333335e-05,
138
+ "loss": 0.6441,
139
+ "step": 750
140
+ },
141
+ {
142
+ "epoch": 4.0,
143
+ "eval_loss": 1.3029890060424805,
144
+ "eval_runtime": 1.5383,
145
+ "eval_samples_per_second": 988.106,
146
+ "eval_steps_per_second": 15.602,
147
+ "step": 760
148
+ },
149
+ {
150
+ "epoch": 4.2105263157894735,
151
+ "grad_norm": 13.214131355285645,
152
+ "learning_rate": 1.677777777777778e-05,
153
+ "loss": 0.5272,
154
+ "step": 800
155
+ },
156
+ {
157
+ "epoch": 4.473684210526316,
158
+ "grad_norm": 15.042282104492188,
159
+ "learning_rate": 1.1222222222222224e-05,
160
+ "loss": 0.4258,
161
+ "step": 850
162
+ },
163
+ {
164
+ "epoch": 4.7368421052631575,
165
+ "grad_norm": 15.808998107910156,
166
+ "learning_rate": 5.666666666666667e-06,
167
+ "loss": 0.4341,
168
+ "step": 900
169
+ },
170
+ {
171
+ "epoch": 5.0,
172
+ "grad_norm": 42.850643157958984,
173
+ "learning_rate": 1.1111111111111112e-07,
174
+ "loss": 0.4298,
175
+ "step": 950
176
+ },
177
+ {
178
+ "epoch": 5.0,
179
+ "eval_loss": 1.5854742527008057,
180
+ "eval_runtime": 1.5439,
181
+ "eval_samples_per_second": 984.541,
182
+ "eval_steps_per_second": 15.545,
183
+ "step": 950
184
+ }
185
+ ],
186
+ "logging_steps": 50,
187
+ "max_steps": 950,
188
+ "num_input_tokens_seen": 0,
189
+ "num_train_epochs": 5,
190
+ "save_steps": 500,
191
+ "stateful_callbacks": {
192
+ "TrainerControl": {
193
+ "args": {
194
+ "should_epoch_stop": false,
195
+ "should_evaluate": false,
196
+ "should_log": false,
197
+ "should_save": true,
198
+ "should_training_stop": true
199
+ },
200
+ "attributes": {}
201
+ }
202
+ },
203
+ "total_flos": 0.0,
204
+ "train_batch_size": 32,
205
+ "trial_name": null,
206
+ "trial_params": null
207
+ }
checkpoint-950/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:edb39620e665d8678bed7e9532bd80b68760b6353c69212767e3bd300dad6d01
3
+ size 5841
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:217b88b7dcfa47a8512478f3cd24c3be19119948a1f0fe72695b6078bcee6141
3
+ size 437987212
special_tokens_map.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "cls_token": "[CLS]",
3
+ "mask_token": "[MASK]",
4
+ "pad_token": "[PAD]",
5
+ "sep_token": "[SEP]",
6
+ "unk_token": "[UNK]"
7
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "[PAD]",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "100": {
12
+ "content": "[UNK]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "101": {
20
+ "content": "[CLS]",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "102": {
28
+ "content": "[SEP]",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "103": {
36
+ "content": "[MASK]",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "clean_up_tokenization_spaces": true,
45
+ "cls_token": "[CLS]",
46
+ "do_basic_tokenize": true,
47
+ "do_lower_case": true,
48
+ "extra_special_tokens": {},
49
+ "mask_token": "[MASK]",
50
+ "model_max_length": 512,
51
+ "never_split": null,
52
+ "pad_token": "[PAD]",
53
+ "sep_token": "[SEP]",
54
+ "strip_accents": null,
55
+ "tokenize_chinese_chars": true,
56
+ "tokenizer_class": "BertTokenizer",
57
+ "unk_token": "[UNK]"
58
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:edb39620e665d8678bed7e9532bd80b68760b6353c69212767e3bd300dad6d01
3
+ size 5841
vocab.txt ADDED
The diff for this file is too large to render. See raw diff