avijit commited on
Commit
da78c38
·
verified ·
1 Parent(s): ef5943f

Upload folder using huggingface_hub

Browse files
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b7a1b3d8d6bfa2e6a8306c1aa3cbc7e8cfd9e5e1270555282f6254b14c86040d
3
+ size 1033285754
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f32c3368ae6f4a7b4e6b6c01ddc41dfddcb142bfb5c682d6ea7918c7bf4e01e
3
+ size 516633490
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f57bbd6a2a84ca302ee982f6dbaca1caec3fee886f5a19a63e4c5c3b8223989
3
+ size 14244
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e92c94c1bda18f79332c162ea14d2c8d83153d864d49d6c68a3017b5d57e43e
3
+ size 1064
special_tokens_map.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|endoftext|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": "<|endoftext|>",
10
+ "mask_token": {
11
+ "content": "<mask>",
12
+ "lstrip": true,
13
+ "normalized": false,
14
+ "rstrip": false,
15
+ "single_word": false
16
+ },
17
+ "pad_token": "<|endoftext|>",
18
+ "unk_token": {
19
+ "content": "<|endoftext|>",
20
+ "lstrip": false,
21
+ "normalized": false,
22
+ "rstrip": false,
23
+ "single_word": false
24
+ }
25
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,220 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<|padding|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "50254": {
21
+ "content": "<mask>",
22
+ "lstrip": true,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "50255": {
29
+ "content": " ",
30
+ "lstrip": false,
31
+ "normalized": true,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": false
35
+ },
36
+ "50256": {
37
+ "content": " ",
38
+ "lstrip": false,
39
+ "normalized": true,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": false
43
+ },
44
+ "50257": {
45
+ "content": " ",
46
+ "lstrip": false,
47
+ "normalized": true,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": false
51
+ },
52
+ "50258": {
53
+ "content": " ",
54
+ "lstrip": false,
55
+ "normalized": true,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": false
59
+ },
60
+ "50259": {
61
+ "content": " ",
62
+ "lstrip": false,
63
+ "normalized": true,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": false
67
+ },
68
+ "50260": {
69
+ "content": " ",
70
+ "lstrip": false,
71
+ "normalized": true,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": false
75
+ },
76
+ "50261": {
77
+ "content": " ",
78
+ "lstrip": false,
79
+ "normalized": true,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": false
83
+ },
84
+ "50262": {
85
+ "content": " ",
86
+ "lstrip": false,
87
+ "normalized": true,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": false
91
+ },
92
+ "50263": {
93
+ "content": " ",
94
+ "lstrip": false,
95
+ "normalized": true,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": false
99
+ },
100
+ "50264": {
101
+ "content": " ",
102
+ "lstrip": false,
103
+ "normalized": true,
104
+ "rstrip": false,
105
+ "single_word": false,
106
+ "special": false
107
+ },
108
+ "50265": {
109
+ "content": " ",
110
+ "lstrip": false,
111
+ "normalized": true,
112
+ "rstrip": false,
113
+ "single_word": false,
114
+ "special": false
115
+ },
116
+ "50266": {
117
+ "content": " ",
118
+ "lstrip": false,
119
+ "normalized": true,
120
+ "rstrip": false,
121
+ "single_word": false,
122
+ "special": false
123
+ },
124
+ "50267": {
125
+ "content": " ",
126
+ "lstrip": false,
127
+ "normalized": true,
128
+ "rstrip": false,
129
+ "single_word": false,
130
+ "special": false
131
+ },
132
+ "50268": {
133
+ "content": " ",
134
+ "lstrip": false,
135
+ "normalized": true,
136
+ "rstrip": false,
137
+ "single_word": false,
138
+ "special": false
139
+ },
140
+ "50269": {
141
+ "content": " ",
142
+ "lstrip": false,
143
+ "normalized": true,
144
+ "rstrip": false,
145
+ "single_word": false,
146
+ "special": false
147
+ },
148
+ "50270": {
149
+ "content": " ",
150
+ "lstrip": false,
151
+ "normalized": true,
152
+ "rstrip": false,
153
+ "single_word": false,
154
+ "special": false
155
+ },
156
+ "50271": {
157
+ "content": " ",
158
+ "lstrip": false,
159
+ "normalized": true,
160
+ "rstrip": false,
161
+ "single_word": false,
162
+ "special": false
163
+ },
164
+ "50272": {
165
+ "content": " ",
166
+ "lstrip": false,
167
+ "normalized": true,
168
+ "rstrip": false,
169
+ "single_word": false,
170
+ "special": false
171
+ },
172
+ "50273": {
173
+ "content": " ",
174
+ "lstrip": false,
175
+ "normalized": true,
176
+ "rstrip": false,
177
+ "single_word": false,
178
+ "special": false
179
+ },
180
+ "50274": {
181
+ "content": " ",
182
+ "lstrip": false,
183
+ "normalized": true,
184
+ "rstrip": false,
185
+ "single_word": false,
186
+ "special": false
187
+ },
188
+ "50275": {
189
+ "content": " ",
190
+ "lstrip": false,
191
+ "normalized": true,
192
+ "rstrip": false,
193
+ "single_word": false,
194
+ "special": false
195
+ },
196
+ "50276": {
197
+ "content": " ",
198
+ "lstrip": false,
199
+ "normalized": true,
200
+ "rstrip": false,
201
+ "single_word": false,
202
+ "special": false
203
+ }
204
+ },
205
+ "bos_token": "<|endoftext|>",
206
+ "clean_up_tokenization_spaces": true,
207
+ "eos_token": "<|endoftext|>",
208
+ "mask_token": "<mask>",
209
+ "max_length": 14002,
210
+ "model_max_length": 1000000000000000019884624838656,
211
+ "pad_to_multiple_of": null,
212
+ "pad_token": "<|endoftext|>",
213
+ "pad_token_type_id": 0,
214
+ "padding_side": "right",
215
+ "stride": 0,
216
+ "tokenizer_class": "GPTNeoXTokenizer",
217
+ "truncation_side": "left",
218
+ "truncation_strategy": "longest_first",
219
+ "unk_token": "<|endoftext|>"
220
+ }
trainer_state.json ADDED
@@ -0,0 +1,269 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.9063403443920213,
3
+ "best_model_checkpoint": "./saved_models/climamba_prompt_sbdh_gpt4_v2_0/checkpoint-192",
4
+ "epoch": 8.0,
5
+ "eval_steps": 500,
6
+ "global_step": 192,
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
+ "grad_norm": 2.0851898193359375,
14
+ "learning_rate": 0.0003,
15
+ "loss": 1.4049,
16
+ "step": 24
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_acc_macro": 0.05554596988321858,
21
+ "eval_acc_micro": 0.17600550017187433,
22
+ "eval_auc_macro": 0.6058912515968368,
23
+ "eval_auc_micro": 0.6488212280527301,
24
+ "eval_f1_at_5": 0.25079507780987353,
25
+ "eval_f1_at_8": 0.24432286984749932,
26
+ "eval_f1_macro": 0.09066299141125865,
27
+ "eval_f1_micro": 0.2993276819643204,
28
+ "eval_loss": 0.394575834274292,
29
+ "eval_prec_at_5": 0.16187214611872147,
30
+ "eval_prec_at_8": 0.1436929223744292,
31
+ "eval_prec_macro": 0.05666691972017087,
32
+ "eval_prec_micro": 0.23115124153497826,
33
+ "eval_rec_at_5": 0.5565068493150684,
34
+ "eval_rec_at_8": 0.8152587519025876,
35
+ "eval_rec_macro": 0.22834645669278442,
36
+ "eval_rec_micro": 0.4245439469319714,
37
+ "eval_runtime": 6.3514,
38
+ "eval_samples_per_second": 137.922,
39
+ "eval_steps_per_second": 17.319,
40
+ "step": 24
41
+ },
42
+ {
43
+ "epoch": 2.0,
44
+ "grad_norm": 0.4896126985549927,
45
+ "learning_rate": 0.0003,
46
+ "loss": 0.3397,
47
+ "step": 48
48
+ },
49
+ {
50
+ "epoch": 2.0,
51
+ "eval_acc_macro": 0.5307003853873716,
52
+ "eval_acc_micro": 0.5814606741572625,
53
+ "eval_auc_macro": 0.9303990338907523,
54
+ "eval_auc_micro": 0.9371828621061181,
55
+ "eval_f1_at_5": 0.4088221844905389,
56
+ "eval_f1_at_8": 0.28901449364842885,
57
+ "eval_f1_macro": 0.6465579930529745,
58
+ "eval_f1_micro": 0.7353463587921194,
59
+ "eval_loss": 0.18900679051876068,
60
+ "eval_prec_at_5": 0.2614155251141553,
61
+ "eval_prec_at_8": 0.16980593607305935,
62
+ "eval_prec_macro": 0.7313857838097021,
63
+ "eval_prec_micro": 0.7915869980878784,
64
+ "eval_rec_at_5": 0.9374048706240486,
65
+ "eval_rec_at_8": 0.9699391171993911,
66
+ "eval_rec_macro": 0.6410238611610916,
67
+ "eval_rec_micro": 0.6865671641790475,
68
+ "eval_runtime": 6.4111,
69
+ "eval_samples_per_second": 136.637,
70
+ "eval_steps_per_second": 17.158,
71
+ "step": 48
72
+ },
73
+ {
74
+ "epoch": 3.0,
75
+ "grad_norm": 0.1705099642276764,
76
+ "learning_rate": 0.0003,
77
+ "loss": 0.0916,
78
+ "step": 72
79
+ },
80
+ {
81
+ "epoch": 3.0,
82
+ "eval_acc_macro": 0.8244239681810236,
83
+ "eval_acc_micro": 0.8311011904761286,
84
+ "eval_auc_macro": 0.9919756925761466,
85
+ "eval_auc_micro": 0.9920428839397825,
86
+ "eval_f1_at_5": 0.42784762619628447,
87
+ "eval_f1_at_8": 0.29274329072668936,
88
+ "eval_f1_macro": 0.9019972941167671,
89
+ "eval_f1_micro": 0.907761072734587,
90
+ "eval_loss": 0.0666864886879921,
91
+ "eval_prec_at_5": 0.273972602739726,
92
+ "eval_prec_at_8": 0.1720890410958904,
93
+ "eval_prec_macro": 0.8888004919536745,
94
+ "eval_prec_micro": 0.8900398406373793,
95
+ "eval_rec_at_5": 0.976027397260274,
96
+ "eval_rec_at_8": 0.9794520547945206,
97
+ "eval_rec_macro": 0.9176060797993615,
98
+ "eval_rec_micro": 0.9262023217246329,
99
+ "eval_runtime": 6.4724,
100
+ "eval_samples_per_second": 135.345,
101
+ "eval_steps_per_second": 16.995,
102
+ "step": 72
103
+ },
104
+ {
105
+ "epoch": 4.0,
106
+ "grad_norm": 0.16448086500167847,
107
+ "learning_rate": 0.0003,
108
+ "loss": 0.0471,
109
+ "step": 96
110
+ },
111
+ {
112
+ "epoch": 4.0,
113
+ "eval_acc_macro": 0.8271437680276396,
114
+ "eval_acc_micro": 0.8323529411764093,
115
+ "eval_auc_macro": 0.993671108576282,
116
+ "eval_auc_micro": 0.9937186337101654,
117
+ "eval_f1_at_5": 0.4285323653750887,
118
+ "eval_f1_at_8": 0.29274329072668936,
119
+ "eval_f1_macro": 0.9038769548624298,
120
+ "eval_f1_micro": 0.9085072231138916,
121
+ "eval_loss": 0.06305181980133057,
122
+ "eval_prec_at_5": 0.27442922374429224,
123
+ "eval_prec_at_8": 0.1720890410958904,
124
+ "eval_prec_macro": 0.8786407478949387,
125
+ "eval_prec_micro": 0.8802488335924665,
126
+ "eval_rec_at_5": 0.977359208523592,
127
+ "eval_rec_at_8": 0.9794520547945206,
128
+ "eval_rec_macro": 0.9344636739690416,
129
+ "eval_rec_micro": 0.9386401326699055,
130
+ "eval_runtime": 6.3196,
131
+ "eval_samples_per_second": 138.617,
132
+ "eval_steps_per_second": 17.406,
133
+ "step": 96
134
+ },
135
+ {
136
+ "epoch": 5.0,
137
+ "grad_norm": 0.22940804064273834,
138
+ "learning_rate": 0.0003,
139
+ "loss": 0.0292,
140
+ "step": 120
141
+ },
142
+ {
143
+ "epoch": 5.0,
144
+ "eval_acc_macro": 0.8308612963912455,
145
+ "eval_acc_micro": 0.8424710424709774,
146
+ "eval_auc_macro": 0.9930217118288992,
147
+ "eval_auc_micro": 0.9944139892271574,
148
+ "eval_f1_at_5": 0.4295136788854873,
149
+ "eval_f1_at_8": 0.29274329072668936,
150
+ "eval_f1_macro": 0.90558341223627,
151
+ "eval_f1_micro": 0.9145012573343744,
152
+ "eval_loss": 0.06955315172672272,
153
+ "eval_prec_at_5": 0.2751141552511416,
154
+ "eval_prec_at_8": 0.1720890410958904,
155
+ "eval_prec_macro": 0.9134147654048902,
156
+ "eval_prec_micro": 0.9245762711863623,
157
+ "eval_rec_at_5": 0.9788812785388128,
158
+ "eval_rec_at_8": 0.9794520547945206,
159
+ "eval_rec_macro": 0.9000407679288313,
160
+ "eval_rec_micro": 0.9046434494194938,
161
+ "eval_runtime": 6.3259,
162
+ "eval_samples_per_second": 138.479,
163
+ "eval_steps_per_second": 17.389,
164
+ "step": 120
165
+ },
166
+ {
167
+ "epoch": 6.0,
168
+ "grad_norm": 0.14079643785953522,
169
+ "learning_rate": 0.0003,
170
+ "loss": 0.0169,
171
+ "step": 144
172
+ },
173
+ {
174
+ "epoch": 6.0,
175
+ "eval_acc_macro": 0.8220596818065521,
176
+ "eval_acc_micro": 0.8319327731091801,
177
+ "eval_auc_macro": 0.9927035556143388,
178
+ "eval_auc_micro": 0.9939625962172801,
179
+ "eval_f1_at_5": 0.4277378477874334,
180
+ "eval_f1_at_8": 0.29274329072668936,
181
+ "eval_f1_macro": 0.8993295914850711,
182
+ "eval_f1_micro": 0.9082568807338691,
183
+ "eval_loss": 0.07188171148300171,
184
+ "eval_prec_at_5": 0.27397260273972607,
185
+ "eval_prec_at_8": 0.1720890410958904,
186
+ "eval_prec_macro": 0.9063614647378323,
187
+ "eval_prec_micro": 0.913590604026769,
188
+ "eval_rec_at_5": 0.9748858447488584,
189
+ "eval_rec_at_8": 0.9794520547945206,
190
+ "eval_rec_macro": 0.8937033781116202,
191
+ "eval_rec_micro": 0.9029850746267908,
192
+ "eval_runtime": 6.3449,
193
+ "eval_samples_per_second": 138.064,
194
+ "eval_steps_per_second": 17.337,
195
+ "step": 144
196
+ },
197
+ {
198
+ "epoch": 7.0,
199
+ "grad_norm": 0.12200725823640823,
200
+ "learning_rate": 0.0003,
201
+ "loss": 0.0095,
202
+ "step": 168
203
+ },
204
+ {
205
+ "epoch": 7.0,
206
+ "eval_acc_macro": 0.8261283592776246,
207
+ "eval_acc_micro": 0.8320433436531863,
208
+ "eval_auc_macro": 0.9914073448442141,
209
+ "eval_auc_micro": 0.9922562843066707,
210
+ "eval_f1_at_5": 0.42747783226694747,
211
+ "eval_f1_at_8": 0.2925113305987028,
212
+ "eval_f1_macro": 0.9026710595366999,
213
+ "eval_f1_micro": 0.9083227714405654,
214
+ "eval_loss": 0.09724259376525879,
215
+ "eval_prec_at_5": 0.27374429223744295,
216
+ "eval_prec_at_8": 0.17194634703196346,
217
+ "eval_prec_macro": 0.9186608707729786,
218
+ "eval_prec_micro": 0.9259259259258461,
219
+ "eval_rec_at_5": 0.975076103500761,
220
+ "eval_rec_at_8": 0.9788812785388128,
221
+ "eval_rec_macro": 0.8890001231603133,
222
+ "eval_rec_micro": 0.8913764510778697,
223
+ "eval_runtime": 6.3561,
224
+ "eval_samples_per_second": 137.82,
225
+ "eval_steps_per_second": 17.306,
226
+ "step": 168
227
+ },
228
+ {
229
+ "epoch": 8.0,
230
+ "grad_norm": 0.1273776739835739,
231
+ "learning_rate": 0.0003,
232
+ "loss": 0.0061,
233
+ "step": 192
234
+ },
235
+ {
236
+ "epoch": 8.0,
237
+ "eval_acc_macro": 0.8331638553801589,
238
+ "eval_acc_micro": 0.8417047184169831,
239
+ "eval_auc_macro": 0.9887523718801591,
240
+ "eval_auc_micro": 0.9910290762677764,
241
+ "eval_f1_at_5": 0.42681135828205624,
242
+ "eval_f1_at_8": 0.29225388037164507,
243
+ "eval_f1_macro": 0.9063403443920213,
244
+ "eval_f1_micro": 0.9140495867767839,
245
+ "eval_loss": 0.09798464179039001,
246
+ "eval_prec_at_5": 0.2732876712328767,
247
+ "eval_prec_at_8": 0.17180365296803654,
248
+ "eval_prec_macro": 0.9010794509609382,
249
+ "eval_prec_micro": 0.9110378912684587,
250
+ "eval_rec_at_5": 0.9739345509893454,
251
+ "eval_rec_at_8": 0.9777397260273972,
252
+ "eval_rec_macro": 0.9130526960570995,
253
+ "eval_rec_micro": 0.9170812603647663,
254
+ "eval_runtime": 6.4145,
255
+ "eval_samples_per_second": 136.565,
256
+ "eval_steps_per_second": 17.149,
257
+ "step": 192
258
+ }
259
+ ],
260
+ "logging_steps": 500,
261
+ "max_steps": 960,
262
+ "num_input_tokens_seen": 0,
263
+ "num_train_epochs": 40,
264
+ "save_steps": 500,
265
+ "total_flos": 0.0,
266
+ "train_batch_size": 32,
267
+ "trial_name": null,
268
+ "trial_params": null
269
+ }