Hugging Face's logo

mllm-dev
/
gpt2_f_experiment_2_drug_data

Text Classification
Transformers
Safetensors
gpt2
Model card Files
xet
Community
mllm-dev commited on
Commit
48db575
·
verified ·
1 Parent(s): d0d04f3

Upload folder using huggingface_hub

Browse files
Files changed (6) hide show
  1. model.safetensors +1 -1
  2. optimizer.pt +1 -1
  3. rng_state.pth +1 -1
  4. scheduler.pt +1 -1
  5. trainer_state.json +169 -14
  6. training_args.bin +1 -1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:32b849e2c9e0f1841adf44361e3908ae7371734c2c0e074b1f92bdb06b88769a
3
  size 497805008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e4da67f62237b3bb0c425f93bedf5464e7ae9507a6affb62c37112d795be69f5
3
  size 497805008
optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:68246cc9169ce766b856705da31adaba45e4032fd00ac87653ea3ccf8ed46397
3
  size 995704133
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:63e54c8c4efb35059a75ba77fb769670f234d1cd5f600d814a097f2d33613da0
3
  size 995704133
rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bc22a7f4646136ee686f8ffffc4c17960827b8d0690d08f1faedc80a3e6f6ef4
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb4dd9d1e2a50bc3d07cac2022a784819448dd290d65076fdfe62b5aa6c41def
3
  size 14575
scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bc92e8c6ac35d569c4ab17f395a4ac90783d80d786f272b0e4e95e53d403a71e
3
  size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac7407a0c8d2fe4371dadfa59d9dddefa668d77469707548ef1435b98fa09050
3
  size 627
trainer_state.json CHANGED
@@ -1,30 +1,185 @@
1
  {
2
- "best_metric": 1.4763978719711304,
3
- "best_model_checkpoint": "tam_test_out_drug_data/checkpoint-449",
4
- "epoch": 1.0,
5
  "eval_steps": 500,
6
- "global_step": 449,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
10
  "log_history": [
11
  {
12
  "epoch": 1.0,
13
- "eval_accuracy": 0.44926997117083606,
14
- "eval_loss": 1.4763978719711304,
15
- "eval_runtime": 17.5163,
16
- "eval_samples_per_second": 613.884,
17
- "eval_steps_per_second": 8.563,
18
- "step": 449
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
19
  }
20
  ],
21
  "logging_steps": 500,
22
- "max_steps": 2245,
23
  "num_input_tokens_seen": 0,
24
- "num_train_epochs": 5,
25
  "save_steps": 500,
26
- "total_flos": 4158825922068480.0,
27
- "train_batch_size": 72,
28
  "trial_name": null,
29
  "trial_params": null
30
  }
 
1
  {
2
+ "best_metric": 1.4213874340057373,
3
+ "best_model_checkpoint": "tam_test_out_drug_data/checkpoint-1011",
4
+ "epoch": 12.0,
5
  "eval_steps": 500,
6
+ "global_step": 4044,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
10
  "log_history": [
11
  {
12
  "epoch": 1.0,
13
+ "eval_accuracy": 0.46219659629870735,
14
+ "eval_loss": 1.4630001783370972,
15
+ "eval_runtime": 15.2997,
16
+ "eval_samples_per_second": 702.823,
17
+ "eval_steps_per_second": 7.386,
18
+ "step": 337
19
+ },
20
+ {
21
+ "epoch": 1.48,
22
+ "grad_norm": 283691.34375,
23
+ "learning_rate": 5.554896142433234e-05,
24
+ "loss": 1.599,
25
+ "step": 500
26
+ },
27
+ {
28
+ "epoch": 2.0,
29
+ "eval_accuracy": 0.4721473077280759,
30
+ "eval_loss": 1.443649411201477,
31
+ "eval_runtime": 15.1007,
32
+ "eval_samples_per_second": 712.086,
33
+ "eval_steps_per_second": 7.483,
34
+ "step": 674
35
+ },
36
+ {
37
+ "epoch": 2.97,
38
+ "grad_norm": 246200.171875,
39
+ "learning_rate": 5.109792284866469e-05,
40
+ "loss": 1.3511,
41
+ "step": 1000
42
+ },
43
+ {
44
+ "epoch": 3.0,
45
+ "eval_accuracy": 0.471310332000372,
46
+ "eval_loss": 1.4213874340057373,
47
+ "eval_runtime": 14.9491,
48
+ "eval_samples_per_second": 719.309,
49
+ "eval_steps_per_second": 7.559,
50
+ "step": 1011
51
+ },
52
+ {
53
+ "epoch": 4.0,
54
+ "eval_accuracy": 0.45615177159862363,
55
+ "eval_loss": 1.5083941221237183,
56
+ "eval_runtime": 15.0793,
57
+ "eval_samples_per_second": 713.097,
58
+ "eval_steps_per_second": 7.494,
59
+ "step": 1348
60
+ },
61
+ {
62
+ "epoch": 4.45,
63
+ "grad_norm": 280970.59375,
64
+ "learning_rate": 4.664688427299703e-05,
65
+ "loss": 1.1818,
66
+ "step": 1500
67
+ },
68
+ {
69
+ "epoch": 5.0,
70
+ "eval_accuracy": 0.461173625964847,
71
+ "eval_loss": 1.5575577020645142,
72
+ "eval_runtime": 15.1913,
73
+ "eval_samples_per_second": 707.84,
74
+ "eval_steps_per_second": 7.438,
75
+ "step": 1685
76
+ },
77
+ {
78
+ "epoch": 5.93,
79
+ "grad_norm": 403212.34375,
80
+ "learning_rate": 4.219584569732938e-05,
81
+ "loss": 1.0233,
82
+ "step": 2000
83
+ },
84
+ {
85
+ "epoch": 6.0,
86
+ "eval_accuracy": 0.46907839672649493,
87
+ "eval_loss": 1.6354960203170776,
88
+ "eval_runtime": 15.1613,
89
+ "eval_samples_per_second": 709.238,
90
+ "eval_steps_per_second": 7.453,
91
+ "step": 2022
92
+ },
93
+ {
94
+ "epoch": 7.0,
95
+ "eval_accuracy": 0.4567097554170929,
96
+ "eval_loss": 1.7575633525848389,
97
+ "eval_runtime": 15.399,
98
+ "eval_samples_per_second": 698.293,
99
+ "eval_steps_per_second": 7.338,
100
+ "step": 2359
101
+ },
102
+ {
103
+ "epoch": 7.42,
104
+ "grad_norm": 479722.78125,
105
+ "learning_rate": 3.774480712166172e-05,
106
+ "loss": 0.8189,
107
+ "step": 2500
108
+ },
109
+ {
110
+ "epoch": 8.0,
111
+ "eval_accuracy": 0.4754022133358133,
112
+ "eval_loss": 1.8389304876327515,
113
+ "eval_runtime": 15.2863,
114
+ "eval_samples_per_second": 703.44,
115
+ "eval_steps_per_second": 7.392,
116
+ "step": 2696
117
+ },
118
+ {
119
+ "epoch": 8.9,
120
+ "grad_norm": 851824.9375,
121
+ "learning_rate": 3.3293768545994065e-05,
122
+ "loss": 0.6647,
123
+ "step": 3000
124
+ },
125
+ {
126
+ "epoch": 9.0,
127
+ "eval_accuracy": 0.48228401376360086,
128
+ "eval_loss": 1.9549497365951538,
129
+ "eval_runtime": 14.9633,
130
+ "eval_samples_per_second": 718.624,
131
+ "eval_steps_per_second": 7.552,
132
+ "step": 3033
133
+ },
134
+ {
135
+ "epoch": 10.0,
136
+ "eval_accuracy": 0.4780991351250814,
137
+ "eval_loss": 2.1215293407440186,
138
+ "eval_runtime": 15.2366,
139
+ "eval_samples_per_second": 705.736,
140
+ "eval_steps_per_second": 7.416,
141
+ "step": 3370
142
+ },
143
+ {
144
+ "epoch": 10.39,
145
+ "grad_norm": 430901.96875,
146
+ "learning_rate": 2.884272997032641e-05,
147
+ "loss": 0.5063,
148
+ "step": 3500
149
+ },
150
+ {
151
+ "epoch": 11.0,
152
+ "eval_accuracy": 0.4572677392355622,
153
+ "eval_loss": 2.341653823852539,
154
+ "eval_runtime": 15.1545,
155
+ "eval_samples_per_second": 709.56,
156
+ "eval_steps_per_second": 7.457,
157
+ "step": 3707
158
+ },
159
+ {
160
+ "epoch": 11.87,
161
+ "grad_norm": 649377.0625,
162
+ "learning_rate": 2.4391691394658753e-05,
163
+ "loss": 0.3982,
164
+ "step": 4000
165
+ },
166
+ {
167
+ "epoch": 12.0,
168
+ "eval_accuracy": 0.47633218636659536,
169
+ "eval_loss": 2.4381961822509766,
170
+ "eval_runtime": 15.2391,
171
+ "eval_samples_per_second": 705.618,
172
+ "eval_steps_per_second": 7.415,
173
+ "step": 4044
174
  }
175
  ],
176
  "logging_steps": 500,
177
+ "max_steps": 6740,
178
  "num_input_tokens_seen": 0,
179
+ "num_train_epochs": 20,
180
  "save_steps": 500,
181
+ "total_flos": 5.300994106017792e+16,
182
+ "train_batch_size": 96,
183
  "trial_name": null,
184
  "trial_params": null
185
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:db003e0b8701e6480fec83890e167f87831cc64f9bd6f4f25b408c4d452e291b
3
  size 4603
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:031e77c7775f2760360cdc9ed1a2d9e618d47728f22b58e85ee32d4d55d0ce3d
3
  size 4603