Hugging Face's logo

CodeIsAbstract
/
Hybrid_anasolve_kaggle

Safetensors
Model card Files
xet
 Community
CodeIsAbstract commited on
Commit
dd33bc5
·
verified ·
1 Parent(s): 58707c7

Training in progress, step 100, checkpoint

Browse files
Files changed (9) hide show
  1. last-checkpoint/model.safetensors +3 -0
  2. last-checkpoint/optimizer.pt +3 -0
  3. last-checkpoint/rng_state_0.pth +3 -0
  4. last-checkpoint/rng_state_1.pth +3 -0
  5. last-checkpoint/scheduler.pt +3 -0
  6. last-checkpoint/tokenizer.json +0 -0
  7. last-checkpoint/tokenizer_config.json +13 -0
  8. last-checkpoint/trainer_state.json +221 -0
  9. last-checkpoint/training_args.bin +3 -0
last-checkpoint/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cf8acb1736feb9f9c5744dff791935d4ee71340ef84e99e799cecec44ef1fba4
3
+ size 847599616
last-checkpoint/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e05d6bc58e1920866c2f6e583cd7a9d3c80b7f5e6a77d49cc0d9c8a26a08af8
3
+ size 1386414411
last-checkpoint/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:47750b38402e142f696be83e692f0dcaeaec3650f3a539a8172bb90643534bb3
3
+ size 14917
last-checkpoint/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a571280ee41c7271d53b8310f62e388e2b05dcdc4ed27f67ba6b3018cacc34ae
3
+ size 14917
last-checkpoint/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:28ce995976843ea29dcf27303959f0b6a782b62ac5ec5d7682e78bdf61d82c85
3
+ size 1465
last-checkpoint/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
last-checkpoint/tokenizer_config.json ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "backend": "tokenizers",
4
+ "bos_token": "<|endoftext|>",
5
+ "eos_token": "<|endoftext|>",
6
+ "errors": "replace",
7
+ "is_local": false,
8
+ "model_max_length": 1000000000,
9
+ "pad_token": "<|padding|>",
10
+ "tokenizer_class": "GPTNeoXTokenizer",
11
+ "trim_offsets": true,
12
+ "unk_token": "<|endoftext|>"
13
+ }
last-checkpoint/trainer_state.json ADDED
@@ -0,0 +1,221 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 0.1,
6
+ "eval_steps": 5,
7
+ "global_step": 100,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.005,
14
+ "eval_accuracy": 3.92156862745098e-06,
15
+ "eval_loss": 21.843835830688477,
16
+ "eval_runtime": 45.1096,
17
+ "eval_samples_per_second": 11.084,
18
+ "eval_steps_per_second": 5.542,
19
+ "step": 5
20
+ },
21
+ {
22
+ "epoch": 0.01,
23
+ "eval_accuracy": 0.005796078431372549,
24
+ "eval_loss": 21.70684814453125,
25
+ "eval_runtime": 44.6216,
26
+ "eval_samples_per_second": 11.205,
27
+ "eval_steps_per_second": 5.603,
28
+ "step": 10
29
+ },
30
+ {
31
+ "epoch": 0.015,
32
+ "eval_accuracy": 0.019337254901960785,
33
+ "eval_loss": 21.580129623413086,
34
+ "eval_runtime": 45.0557,
35
+ "eval_samples_per_second": 11.097,
36
+ "eval_steps_per_second": 5.549,
37
+ "step": 15
38
+ },
39
+ {
40
+ "epoch": 0.02,
41
+ "eval_accuracy": 0.022207843137254903,
42
+ "eval_loss": 21.46198081970215,
43
+ "eval_runtime": 45.1875,
44
+ "eval_samples_per_second": 11.065,
45
+ "eval_steps_per_second": 5.533,
46
+ "step": 20
47
+ },
48
+ {
49
+ "epoch": 0.025,
50
+ "eval_accuracy": 0.029156862745098037,
51
+ "eval_loss": 21.34127426147461,
52
+ "eval_runtime": 45.3567,
53
+ "eval_samples_per_second": 11.024,
54
+ "eval_steps_per_second": 5.512,
55
+ "step": 25
56
+ },
57
+ {
58
+ "epoch": 0.03,
59
+ "eval_accuracy": 0.03545098039215686,
60
+ "eval_loss": 21.242088317871094,
61
+ "eval_runtime": 45.3984,
62
+ "eval_samples_per_second": 11.014,
63
+ "eval_steps_per_second": 5.507,
64
+ "step": 30
65
+ },
66
+ {
67
+ "epoch": 0.035,
68
+ "eval_accuracy": 0.042094117647058824,
69
+ "eval_loss": 21.127534866333008,
70
+ "eval_runtime": 46.4511,
71
+ "eval_samples_per_second": 10.764,
72
+ "eval_steps_per_second": 5.382,
73
+ "step": 35
74
+ },
75
+ {
76
+ "epoch": 0.04,
77
+ "eval_accuracy": 0.05104313725490196,
78
+ "eval_loss": 21.007797241210938,
79
+ "eval_runtime": 45.2887,
80
+ "eval_samples_per_second": 11.04,
81
+ "eval_steps_per_second": 5.52,
82
+ "step": 40
83
+ },
84
+ {
85
+ "epoch": 0.045,
86
+ "eval_accuracy": 0.05892549019607843,
87
+ "eval_loss": 20.8879451751709,
88
+ "eval_runtime": 45.4919,
89
+ "eval_samples_per_second": 10.991,
90
+ "eval_steps_per_second": 5.495,
91
+ "step": 45
92
+ },
93
+ {
94
+ "epoch": 0.05,
95
+ "eval_accuracy": 0.06429411764705882,
96
+ "eval_loss": 20.779932022094727,
97
+ "eval_runtime": 45.3237,
98
+ "eval_samples_per_second": 11.032,
99
+ "eval_steps_per_second": 5.516,
100
+ "step": 50
101
+ },
102
+ {
103
+ "epoch": 0.055,
104
+ "eval_accuracy": 0.06933333333333333,
105
+ "eval_loss": 20.666351318359375,
106
+ "eval_runtime": 45.5272,
107
+ "eval_samples_per_second": 10.982,
108
+ "eval_steps_per_second": 5.491,
109
+ "step": 55
110
+ },
111
+ {
112
+ "epoch": 0.06,
113
+ "eval_accuracy": 0.0722156862745098,
114
+ "eval_loss": 20.56865692138672,
115
+ "eval_runtime": 45.4567,
116
+ "eval_samples_per_second": 10.999,
117
+ "eval_steps_per_second": 5.5,
118
+ "step": 60
119
+ },
120
+ {
121
+ "epoch": 0.065,
122
+ "eval_accuracy": 0.07492549019607843,
123
+ "eval_loss": 20.474367141723633,
124
+ "eval_runtime": 45.2841,
125
+ "eval_samples_per_second": 11.041,
126
+ "eval_steps_per_second": 5.521,
127
+ "step": 65
128
+ },
129
+ {
130
+ "epoch": 0.07,
131
+ "eval_accuracy": 0.07572941176470588,
132
+ "eval_loss": 20.385995864868164,
133
+ "eval_runtime": 45.3374,
134
+ "eval_samples_per_second": 11.028,
135
+ "eval_steps_per_second": 5.514,
136
+ "step": 70
137
+ },
138
+ {
139
+ "epoch": 0.075,
140
+ "eval_accuracy": 0.07717254901960785,
141
+ "eval_loss": 20.2958984375,
142
+ "eval_runtime": 45.3438,
143
+ "eval_samples_per_second": 11.027,
144
+ "eval_steps_per_second": 5.513,
145
+ "step": 75
146
+ },
147
+ {
148
+ "epoch": 0.08,
149
+ "eval_accuracy": 0.07829411764705882,
150
+ "eval_loss": 20.204992294311523,
151
+ "eval_runtime": 45.427,
152
+ "eval_samples_per_second": 11.007,
153
+ "eval_steps_per_second": 5.503,
154
+ "step": 80
155
+ },
156
+ {
157
+ "epoch": 0.085,
158
+ "eval_accuracy": 0.07968235294117647,
159
+ "eval_loss": 20.112102508544922,
160
+ "eval_runtime": 45.0567,
161
+ "eval_samples_per_second": 11.097,
162
+ "eval_steps_per_second": 5.549,
163
+ "step": 85
164
+ },
165
+ {
166
+ "epoch": 0.09,
167
+ "eval_accuracy": 0.07994509803921569,
168
+ "eval_loss": 20.023468017578125,
169
+ "eval_runtime": 45.1806,
170
+ "eval_samples_per_second": 11.067,
171
+ "eval_steps_per_second": 5.533,
172
+ "step": 90
173
+ },
174
+ {
175
+ "epoch": 0.095,
176
+ "eval_accuracy": 0.07969411764705882,
177
+ "eval_loss": 19.922317504882812,
178
+ "eval_runtime": 45.3425,
179
+ "eval_samples_per_second": 11.027,
180
+ "eval_steps_per_second": 5.514,
181
+ "step": 95
182
+ },
183
+ {
184
+ "epoch": 0.1,
185
+ "grad_norm": 3.734435558319092,
186
+ "learning_rate": 3.973800426880847e-06,
187
+ "loss": 167.01556640625,
188
+ "step": 100
189
+ },
190
+ {
191
+ "epoch": 0.1,
192
+ "eval_accuracy": 0.07997254901960785,
193
+ "eval_loss": 19.829484939575195,
194
+ "eval_runtime": 45.4368,
195
+ "eval_samples_per_second": 11.004,
196
+ "eval_steps_per_second": 5.502,
197
+ "step": 100
198
+ }
199
+ ],
200
+ "logging_steps": 100,
201
+ "max_steps": 1000,
202
+ "num_input_tokens_seen": 0,
203
+ "num_train_epochs": 9223372036854775807,
204
+ "save_steps": 100,
205
+ "stateful_callbacks": {
206
+ "TrainerControl": {
207
+ "args": {
208
+ "should_epoch_stop": false,
209
+ "should_evaluate": false,
210
+ "should_log": false,
211
+ "should_save": true,
212
+ "should_training_stop": false
213
+ },
214
+ "attributes": {}
215
+ }
216
+ },
217
+ "total_flos": 0.0,
218
+ "train_batch_size": 1,
219
+ "trial_name": null,
220
+ "trial_params": null
221
+ }
last-checkpoint/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:61901a80b548b22f93a9c3be114cffc81cb96a048a415d030c20431d54e95e01
3
+ size 5265