TinyPixel commited on
Commit
17461e9
1 Parent(s): b0d0aa7

Upload folder using huggingface_hub

Browse files
adapter_config.json CHANGED
@@ -20,8 +20,8 @@
20
  "revision": null,
21
  "target_modules": [
22
  "query_key_value",
23
- "dense",
24
  "dense_h_to_4h",
 
25
  "dense_4h_to_h"
26
  ],
27
  "task_type": "CAUSAL_LM",
 
20
  "revision": null,
21
  "target_modules": [
22
  "query_key_value",
 
23
  "dense_h_to_4h",
24
+ "dense",
25
  "dense_4h_to_h"
26
  ],
27
  "task_type": "CAUSAL_LM",
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fddb2469e6ffe1163534c9cea4ae13c8a9672bf68d3d2abe558cce949943902e
3
  size 134235712
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e1498a003705f5dc06807d024876b15d8df8a44c2e04b42e597c51d06c3780b0
3
  size 134235712
optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:314d2ba87e948610c2ad9be021f9d9906adc2aed9ce526e3d2329042f35ff5c2
3
  size 268514874
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5b38ca7b86273250274e0d6a3a5676932493365d4eb943ac6e711970cb97cd73
3
  size 268514874
rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c1a8122975853f947e69e03187a29428024ead29190ec994e53ee279eeb7c9ad
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:98fe5f2173f9e5ac71064e84ba62ff7741e3d2ed1014d512a7a0fcde357a9886
3
  size 14244
scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:81007ec48272bbdc4f9622c046f9c026bf8120ed11d1398fd97bb5168a6f3dda
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b371ae767212827ffe8a91587d7467c4f40f93812413ed6571b08320a4c26332
3
  size 1064
special_tokens_map.json CHANGED
@@ -1,41 +1,19 @@
1
  {
2
- "additional_special_tokens": [
3
- {
4
- "content": "<|im_end|>",
5
- "lstrip": false,
6
- "normalized": false,
7
- "rstrip": false,
8
- "single_word": false
9
- },
10
- {
11
- "content": "<|im_start|>",
12
- "lstrip": false,
13
- "normalized": false,
14
- "rstrip": false,
15
- "single_word": false
16
- }
17
- ],
18
  "bos_token": {
19
- "content": "<|im_start|>",
20
  "lstrip": false,
21
  "normalized": false,
22
  "rstrip": false,
23
  "single_word": false
24
  },
25
  "eos_token": {
26
- "content": "<|im_end|>",
27
- "lstrip": false,
28
- "normalized": false,
29
- "rstrip": false,
30
- "single_word": false
31
- },
32
- "pad_token": {
33
- "content": "[PAD]",
34
  "lstrip": false,
35
  "normalized": false,
36
  "rstrip": false,
37
  "single_word": false
38
  },
 
39
  "unk_token": {
40
  "content": "<|endoftext|>",
41
  "lstrip": false,
 
1
  {
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2
  "bos_token": {
3
+ "content": "<|endoftext|>",
4
  "lstrip": false,
5
  "normalized": false,
6
  "rstrip": false,
7
  "single_word": false
8
  },
9
  "eos_token": {
10
+ "content": "<|endoftext|>",
 
 
 
 
 
 
 
11
  "lstrip": false,
12
  "normalized": false,
13
  "rstrip": false,
14
  "single_word": false
15
  },
16
+ "pad_token": "<|endoftext|>",
17
  "unk_token": {
18
  "content": "<|endoftext|>",
19
  "lstrip": false,
tokenizer.json CHANGED
@@ -232,33 +232,6 @@
232
  "rstrip": false,
233
  "normalized": true,
234
  "special": false
235
- },
236
- {
237
- "id": 50277,
238
- "content": "[PAD]",
239
- "single_word": false,
240
- "lstrip": false,
241
- "rstrip": false,
242
- "normalized": false,
243
- "special": true
244
- },
245
- {
246
- "id": 50278,
247
- "content": "<|im_end|>",
248
- "single_word": false,
249
- "lstrip": false,
250
- "rstrip": false,
251
- "normalized": false,
252
- "special": true
253
- },
254
- {
255
- "id": 50279,
256
- "content": "<|im_start|>",
257
- "single_word": false,
258
- "lstrip": false,
259
- "rstrip": false,
260
- "normalized": false,
261
- "special": true
262
  }
263
  ],
264
  "normalizer": {
 
232
  "rstrip": false,
233
  "normalized": true,
234
  "special": false
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
235
  }
236
  ],
237
  "normalizer": {
tokenizer_config.json CHANGED
@@ -200,41 +200,13 @@
200
  "rstrip": false,
201
  "single_word": false,
202
  "special": false
203
- },
204
- "50277": {
205
- "content": "[PAD]",
206
- "lstrip": false,
207
- "normalized": false,
208
- "rstrip": false,
209
- "single_word": false,
210
- "special": true
211
- },
212
- "50278": {
213
- "content": "<|im_end|>",
214
- "lstrip": false,
215
- "normalized": false,
216
- "rstrip": false,
217
- "single_word": false,
218
- "special": true
219
- },
220
- "50279": {
221
- "content": "<|im_start|>",
222
- "lstrip": false,
223
- "normalized": false,
224
- "rstrip": false,
225
- "single_word": false,
226
- "special": true
227
  }
228
  },
229
- "additional_special_tokens": [
230
- "<|im_end|>",
231
- "<|im_start|>"
232
- ],
233
- "bos_token": "<|im_start|>",
234
  "clean_up_tokenization_spaces": true,
235
- "eos_token": "<|im_end|>",
236
  "model_max_length": 1000000000000000019884624838656,
237
- "pad_token": "[PAD]",
238
  "tokenizer_class": "GPTNeoXTokenizer",
239
  "unk_token": "<|endoftext|>"
240
  }
 
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
  "model_max_length": 1000000000000000019884624838656,
209
+ "pad_token": "<|endoftext|>",
210
  "tokenizer_class": "GPTNeoXTokenizer",
211
  "unk_token": "<|endoftext|>"
212
  }
trainer_state.json CHANGED
@@ -1,320 +1,164 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 0.9944064636420137,
5
  "eval_steps": 500,
6
- "global_step": 100,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
10
  "log_history": [
11
  {
12
- "epoch": 0.02,
13
  "learning_rate": 0.0002,
14
- "loss": 2.6734,
15
  "step": 2
16
  },
17
  {
18
- "epoch": 0.04,
19
  "learning_rate": 0.0002,
20
- "loss": 2.5223,
21
  "step": 4
22
  },
23
  {
24
- "epoch": 0.06,
25
  "learning_rate": 0.0002,
26
- "loss": 2.5395,
27
  "step": 6
28
  },
29
  {
30
- "epoch": 0.08,
31
  "learning_rate": 0.0002,
32
- "loss": 2.4201,
33
  "step": 8
34
  },
35
  {
36
- "epoch": 0.1,
37
  "learning_rate": 0.0002,
38
- "loss": 2.4077,
39
  "step": 10
40
  },
41
  {
42
- "epoch": 0.12,
43
  "learning_rate": 0.0002,
44
- "loss": 2.46,
45
  "step": 12
46
  },
47
  {
48
- "epoch": 0.14,
49
  "learning_rate": 0.0002,
50
- "loss": 2.3741,
51
  "step": 14
52
  },
53
  {
54
- "epoch": 0.16,
55
  "learning_rate": 0.0002,
56
- "loss": 2.5008,
57
  "step": 16
58
  },
59
  {
60
- "epoch": 0.18,
61
  "learning_rate": 0.0002,
62
- "loss": 2.3597,
63
  "step": 18
64
  },
65
  {
66
- "epoch": 0.2,
67
  "learning_rate": 0.0002,
68
- "loss": 2.1931,
69
  "step": 20
70
  },
71
  {
72
- "epoch": 0.22,
73
  "learning_rate": 0.0002,
74
- "loss": 2.3606,
75
  "step": 22
76
  },
77
  {
78
- "epoch": 0.24,
79
  "learning_rate": 0.0002,
80
- "loss": 2.4487,
81
  "step": 24
82
  },
83
  {
84
- "epoch": 0.26,
85
  "learning_rate": 0.0002,
86
- "loss": 2.2416,
87
  "step": 26
88
  },
89
  {
90
- "epoch": 0.28,
91
  "learning_rate": 0.0002,
92
- "loss": 2.3211,
93
  "step": 28
94
  },
95
  {
96
- "epoch": 0.3,
97
  "learning_rate": 0.0002,
98
- "loss": 2.3693,
99
  "step": 30
100
  },
101
  {
102
- "epoch": 0.32,
103
  "learning_rate": 0.0002,
104
- "loss": 2.3048,
105
  "step": 32
106
  },
107
  {
108
- "epoch": 0.34,
109
  "learning_rate": 0.0002,
110
- "loss": 2.2307,
111
  "step": 34
112
  },
113
  {
114
- "epoch": 0.36,
115
  "learning_rate": 0.0002,
116
- "loss": 2.3252,
117
  "step": 36
118
  },
119
  {
120
- "epoch": 0.38,
121
  "learning_rate": 0.0002,
122
- "loss": 2.3334,
123
  "step": 38
124
  },
125
  {
126
- "epoch": 0.4,
127
  "learning_rate": 0.0002,
128
- "loss": 2.1768,
129
  "step": 40
130
  },
131
  {
132
- "epoch": 0.42,
133
  "learning_rate": 0.0002,
134
- "loss": 2.1346,
135
  "step": 42
136
  },
137
  {
138
- "epoch": 0.44,
139
  "learning_rate": 0.0002,
140
- "loss": 2.1112,
141
  "step": 44
142
  },
143
  {
144
- "epoch": 0.46,
145
  "learning_rate": 0.0002,
146
- "loss": 2.1268,
147
  "step": 46
148
  },
149
  {
150
- "epoch": 0.48,
151
  "learning_rate": 0.0002,
152
- "loss": 2.0301,
153
  "step": 48
154
- },
155
- {
156
- "epoch": 0.5,
157
- "learning_rate": 0.0002,
158
- "loss": 2.104,
159
- "step": 50
160
- },
161
- {
162
- "epoch": 0.52,
163
- "learning_rate": 0.0002,
164
- "loss": 2.1416,
165
- "step": 52
166
- },
167
- {
168
- "epoch": 0.54,
169
- "learning_rate": 0.0002,
170
- "loss": 2.2677,
171
- "step": 54
172
- },
173
- {
174
- "epoch": 0.56,
175
- "learning_rate": 0.0002,
176
- "loss": 2.2711,
177
- "step": 56
178
- },
179
- {
180
- "epoch": 0.58,
181
- "learning_rate": 0.0002,
182
- "loss": 2.1959,
183
- "step": 58
184
- },
185
- {
186
- "epoch": 0.6,
187
- "learning_rate": 0.0002,
188
- "loss": 2.2885,
189
- "step": 60
190
- },
191
- {
192
- "epoch": 0.62,
193
- "learning_rate": 0.0002,
194
- "loss": 2.293,
195
- "step": 62
196
- },
197
- {
198
- "epoch": 0.64,
199
- "learning_rate": 0.0002,
200
- "loss": 2.3157,
201
- "step": 64
202
- },
203
- {
204
- "epoch": 0.66,
205
- "learning_rate": 0.0002,
206
- "loss": 2.2223,
207
- "step": 66
208
- },
209
- {
210
- "epoch": 0.68,
211
- "learning_rate": 0.0002,
212
- "loss": 2.1248,
213
- "step": 68
214
- },
215
- {
216
- "epoch": 0.7,
217
- "learning_rate": 0.0002,
218
- "loss": 2.0144,
219
- "step": 70
220
- },
221
- {
222
- "epoch": 0.72,
223
- "learning_rate": 0.0002,
224
- "loss": 2.1136,
225
- "step": 72
226
- },
227
- {
228
- "epoch": 0.74,
229
- "learning_rate": 0.0002,
230
- "loss": 2.2022,
231
- "step": 74
232
- },
233
- {
234
- "epoch": 0.76,
235
- "learning_rate": 0.0002,
236
- "loss": 2.0508,
237
- "step": 76
238
- },
239
- {
240
- "epoch": 0.78,
241
- "learning_rate": 0.0002,
242
- "loss": 2.1912,
243
- "step": 78
244
- },
245
- {
246
- "epoch": 0.8,
247
- "learning_rate": 0.0002,
248
- "loss": 2.3011,
249
- "step": 80
250
- },
251
- {
252
- "epoch": 0.82,
253
- "learning_rate": 0.0002,
254
- "loss": 2.1513,
255
- "step": 82
256
- },
257
- {
258
- "epoch": 0.84,
259
- "learning_rate": 0.0002,
260
- "loss": 2.2956,
261
- "step": 84
262
- },
263
- {
264
- "epoch": 0.86,
265
- "learning_rate": 0.0002,
266
- "loss": 2.1961,
267
- "step": 86
268
- },
269
- {
270
- "epoch": 0.88,
271
- "learning_rate": 0.0002,
272
- "loss": 2.1879,
273
- "step": 88
274
- },
275
- {
276
- "epoch": 0.89,
277
- "learning_rate": 0.0002,
278
- "loss": 2.0191,
279
- "step": 90
280
- },
281
- {
282
- "epoch": 0.91,
283
- "learning_rate": 0.0002,
284
- "loss": 2.1988,
285
- "step": 92
286
- },
287
- {
288
- "epoch": 0.93,
289
- "learning_rate": 0.0002,
290
- "loss": 1.9186,
291
- "step": 94
292
- },
293
- {
294
- "epoch": 0.95,
295
- "learning_rate": 0.0002,
296
- "loss": 1.9487,
297
- "step": 96
298
- },
299
- {
300
- "epoch": 0.97,
301
- "learning_rate": 0.0002,
302
- "loss": 1.9328,
303
- "step": 98
304
- },
305
- {
306
- "epoch": 0.99,
307
- "learning_rate": 0.0002,
308
- "loss": 2.0568,
309
- "step": 100
310
  }
311
  ],
312
  "logging_steps": 2,
313
- "max_steps": 100,
314
  "num_input_tokens_seen": 0,
315
  "num_train_epochs": 1,
316
  "save_steps": 500,
317
- "total_flos": 8622354846867456.0,
318
  "train_batch_size": 1,
319
  "trial_name": null,
320
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.9846153846153847,
5
  "eval_steps": 500,
6
+ "global_step": 48,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
10
  "log_history": [
11
  {
12
+ "epoch": 0.04,
13
  "learning_rate": 0.0002,
14
+ "loss": 2.2696,
15
  "step": 2
16
  },
17
  {
18
+ "epoch": 0.08,
19
  "learning_rate": 0.0002,
20
+ "loss": 2.4542,
21
  "step": 4
22
  },
23
  {
24
+ "epoch": 0.12,
25
  "learning_rate": 0.0002,
26
+ "loss": 2.3623,
27
  "step": 6
28
  },
29
  {
30
+ "epoch": 0.16,
31
  "learning_rate": 0.0002,
32
+ "loss": 2.5283,
33
  "step": 8
34
  },
35
  {
36
+ "epoch": 0.21,
37
  "learning_rate": 0.0002,
38
+ "loss": 2.5501,
39
  "step": 10
40
  },
41
  {
42
+ "epoch": 0.25,
43
  "learning_rate": 0.0002,
44
+ "loss": 2.7343,
45
  "step": 12
46
  },
47
  {
48
+ "epoch": 0.29,
49
  "learning_rate": 0.0002,
50
+ "loss": 2.1721,
51
  "step": 14
52
  },
53
  {
54
+ "epoch": 0.33,
55
  "learning_rate": 0.0002,
56
+ "loss": 2.2801,
57
  "step": 16
58
  },
59
  {
60
+ "epoch": 0.37,
61
  "learning_rate": 0.0002,
62
+ "loss": 2.4526,
63
  "step": 18
64
  },
65
  {
66
+ "epoch": 0.41,
67
  "learning_rate": 0.0002,
68
+ "loss": 2.4499,
69
  "step": 20
70
  },
71
  {
72
+ "epoch": 0.45,
73
  "learning_rate": 0.0002,
74
+ "loss": 2.4254,
75
  "step": 22
76
  },
77
  {
78
+ "epoch": 0.49,
79
  "learning_rate": 0.0002,
80
+ "loss": 2.6891,
81
  "step": 24
82
  },
83
  {
84
+ "epoch": 0.53,
85
  "learning_rate": 0.0002,
86
+ "loss": 2.2323,
87
  "step": 26
88
  },
89
  {
90
+ "epoch": 0.57,
91
  "learning_rate": 0.0002,
92
+ "loss": 2.1318,
93
  "step": 28
94
  },
95
  {
96
+ "epoch": 0.62,
97
  "learning_rate": 0.0002,
98
+ "loss": 2.6934,
99
  "step": 30
100
  },
101
  {
102
+ "epoch": 0.66,
103
  "learning_rate": 0.0002,
104
+ "loss": 2.4916,
105
  "step": 32
106
  },
107
  {
108
+ "epoch": 0.7,
109
  "learning_rate": 0.0002,
110
+ "loss": 2.6042,
111
  "step": 34
112
  },
113
  {
114
+ "epoch": 0.74,
115
  "learning_rate": 0.0002,
116
+ "loss": 2.6981,
117
  "step": 36
118
  },
119
  {
120
+ "epoch": 0.78,
121
  "learning_rate": 0.0002,
122
+ "loss": 2.3111,
123
  "step": 38
124
  },
125
  {
126
+ "epoch": 0.82,
127
  "learning_rate": 0.0002,
128
+ "loss": 2.3537,
129
  "step": 40
130
  },
131
  {
132
+ "epoch": 0.86,
133
  "learning_rate": 0.0002,
134
+ "loss": 2.5255,
135
  "step": 42
136
  },
137
  {
138
+ "epoch": 0.9,
139
  "learning_rate": 0.0002,
140
+ "loss": 2.3537,
141
  "step": 44
142
  },
143
  {
144
+ "epoch": 0.94,
145
  "learning_rate": 0.0002,
146
+ "loss": 2.5072,
147
  "step": 46
148
  },
149
  {
150
+ "epoch": 0.98,
151
  "learning_rate": 0.0002,
152
+ "loss": 2.4306,
153
  "step": 48
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
154
  }
155
  ],
156
  "logging_steps": 2,
157
+ "max_steps": 48,
158
  "num_input_tokens_seen": 0,
159
  "num_train_epochs": 1,
160
  "save_steps": 500,
161
+ "total_flos": 2047338095837184.0,
162
  "train_batch_size": 1,
163
  "trial_name": null,
164
  "trial_params": null
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:52e0bf11052fc5400b27a40e0097429b7b7441842497f5cd45007f996e627210
3
  size 4728
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee130089c2b6cb201cbccea96e2e23972d6b73ac0c5bb342769e44977ea7d1af
3
  size 4728