TinyPixel commited on
Commit
1712d6a
1 Parent(s): 9f18374

Upload folder using huggingface_hub

Browse files
README.md CHANGED
@@ -1,6 +1,6 @@
1
  ---
2
  library_name: peft
3
- base_model: stabilityai/stablelm-2-1_6b
4
  ---
5
 
6
  # Model Card for Model ID
 
1
  ---
2
  library_name: peft
3
+ base_model: EleutherAI/pythia-1b
4
  ---
5
 
6
  # Model Card for Model ID
adapter_config.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
  "alpha_pattern": {},
3
  "auto_mapping": null,
4
- "base_model_name_or_path": "stabilityai/stablelm-2-1_6b",
5
  "bias": "none",
6
  "fan_in_fan_out": false,
7
  "inference_mode": true,
@@ -19,13 +19,10 @@
19
  "rank_pattern": {},
20
  "revision": null,
21
  "target_modules": [
22
- "q_proj",
23
- "up_proj",
24
- "k_proj",
25
- "o_proj",
26
- "down_proj",
27
- "v_proj",
28
- "gate_proj"
29
  ],
30
  "task_type": "CAUSAL_LM",
31
  "use_rslora": false
 
1
  {
2
  "alpha_pattern": {},
3
  "auto_mapping": null,
4
+ "base_model_name_or_path": "EleutherAI/pythia-1b",
5
  "bias": "none",
6
  "fan_in_fan_out": false,
7
  "inference_mode": true,
 
19
  "rank_pattern": {},
20
  "revision": null,
21
  "target_modules": [
22
+ "dense_4h_to_h",
23
+ "dense_h_to_4h",
24
+ "query_key_value",
25
+ "dense"
 
 
 
26
  ],
27
  "task_type": "CAUSAL_LM",
28
  "use_rslora": false
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e4e66fb4462b0ff40280c4ae317b81d9e1064aad7c18fd5fa7ac4d1727c5224a
3
- size 242266152
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:881f2340c02d4d32c10f3e9d78bb208dcbce12b61a20156f43514be608ff8250
3
+ size 134235712
optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4b80c80eb6036cfc6daca4974510f50780e5588cf83d077f6f33e61eb189fdec
3
- size 484650042
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b97ad97485f7553240a4bd1e25597aeed805c4600a59cc77473faa5f96a97efa
3
+ size 268514874
rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c083cb6a750f2d70427c0b444f5623da3f62a587f72fe5cbf7982277b15bbd34
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e5c75855cec5126735fc2188235300e2c81959c32df6ee02c5ff30127dcdc657
3
  size 14244
scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:31ea39dd85d8fdd7963ae8fca104a21064c32ab31d9951bd542c75f5d686bcc7
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b371ae767212827ffe8a91587d7467c4f40f93812413ed6571b08320a4c26332
3
  size 1064
special_tokens_map.json CHANGED
@@ -15,12 +15,32 @@
15
  "single_word": false
16
  }
17
  ],
18
- "eos_token": "<|endoftext|>",
 
 
 
 
 
 
 
 
 
 
 
 
 
19
  "pad_token": {
20
  "content": "<|endoftext|>",
21
  "lstrip": false,
22
  "normalized": false,
23
  "rstrip": false,
24
  "single_word": false
 
 
 
 
 
 
 
25
  }
26
  }
 
15
  "single_word": false
16
  }
17
  ],
18
+ "bos_token": {
19
+ "content": "<|endoftext|>",
20
+ "lstrip": false,
21
+ "normalized": false,
22
+ "rstrip": false,
23
+ "single_word": false
24
+ },
25
+ "eos_token": {
26
+ "content": "<|endoftext|>",
27
+ "lstrip": false,
28
+ "normalized": false,
29
+ "rstrip": false,
30
+ "single_word": false
31
+ },
32
  "pad_token": {
33
  "content": "<|endoftext|>",
34
  "lstrip": false,
35
  "normalized": false,
36
  "rstrip": false,
37
  "single_word": false
38
+ },
39
+ "unk_token": {
40
+ "content": "<|endoftext|>",
41
+ "lstrip": false,
42
+ "normalized": false,
43
+ "rstrip": false,
44
+ "single_word": false
45
  }
46
  }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1,19 +1,232 @@
1
  {
2
- "added_tokens_decoder": {},
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3
  "additional_special_tokens": [
4
  "<|im_end|>",
5
  "<|im_start|>"
6
  ],
7
- "auto_map": {
8
- "AutoTokenizer": [
9
- "stabilityai/stablelm-2-1_6b--tokenization_arcade100k.Arcade100kTokenizer",
10
- null
11
- ]
12
- },
13
  "clean_up_tokenization_spaces": true,
14
  "eos_token": "<|endoftext|>",
15
- "errors": "replace",
16
  "model_max_length": 1000000000000000019884624838656,
17
  "pad_token": "<|endoftext|>",
18
- "tokenizer_class": "Arcade100kTokenizer"
 
19
  }
 
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": " ",
22
+ "lstrip": false,
23
+ "normalized": true,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": false
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
+ "50277": {
205
+ "content": "<|im_end|>",
206
+ "lstrip": false,
207
+ "normalized": false,
208
+ "rstrip": false,
209
+ "single_word": false,
210
+ "special": true
211
+ },
212
+ "50278": {
213
+ "content": "<|im_start|>",
214
+ "lstrip": false,
215
+ "normalized": false,
216
+ "rstrip": false,
217
+ "single_word": false,
218
+ "special": true
219
+ }
220
+ },
221
  "additional_special_tokens": [
222
  "<|im_end|>",
223
  "<|im_start|>"
224
  ],
225
+ "bos_token": "<|endoftext|>",
 
 
 
 
 
226
  "clean_up_tokenization_spaces": true,
227
  "eos_token": "<|endoftext|>",
 
228
  "model_max_length": 1000000000000000019884624838656,
229
  "pad_token": "<|endoftext|>",
230
+ "tokenizer_class": "GPTNeoXTokenizer",
231
+ "unk_token": "<|endoftext|>"
232
  }
trainer_state.json CHANGED
@@ -1,620 +1,164 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 2.9972041006523766,
5
  "eval_steps": 500,
6
- "global_step": 201,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
10
  "log_history": [
11
  {
12
- "epoch": 0.03,
13
  "learning_rate": 0.0002,
14
- "loss": 2.9944,
15
  "step": 2
16
  },
17
  {
18
- "epoch": 0.06,
19
  "learning_rate": 0.0002,
20
- "loss": 1.9388,
21
  "step": 4
22
  },
23
  {
24
- "epoch": 0.09,
25
  "learning_rate": 0.0002,
26
- "loss": 1.7737,
27
  "step": 6
28
  },
29
  {
30
- "epoch": 0.12,
31
  "learning_rate": 0.0002,
32
- "loss": 1.6946,
33
  "step": 8
34
  },
35
  {
36
- "epoch": 0.15,
37
  "learning_rate": 0.0002,
38
- "loss": 1.6312,
39
  "step": 10
40
  },
41
  {
42
- "epoch": 0.18,
43
  "learning_rate": 0.0002,
44
- "loss": 1.8808,
45
  "step": 12
46
  },
47
  {
48
- "epoch": 0.21,
49
  "learning_rate": 0.0002,
50
- "loss": 2.0882,
51
  "step": 14
52
  },
53
  {
54
- "epoch": 0.24,
55
  "learning_rate": 0.0002,
56
- "loss": 2.6908,
57
  "step": 16
58
  },
59
  {
60
- "epoch": 0.27,
61
  "learning_rate": 0.0002,
62
- "loss": 2.8387,
63
  "step": 18
64
  },
65
  {
66
- "epoch": 0.3,
67
  "learning_rate": 0.0002,
68
- "loss": 1.8799,
69
  "step": 20
70
  },
71
  {
72
- "epoch": 0.33,
73
  "learning_rate": 0.0002,
74
- "loss": 1.5121,
75
  "step": 22
76
  },
77
  {
78
- "epoch": 0.36,
79
  "learning_rate": 0.0002,
80
- "loss": 1.4797,
81
  "step": 24
82
  },
83
  {
84
- "epoch": 0.39,
85
  "learning_rate": 0.0002,
86
- "loss": 1.3471,
87
  "step": 26
88
  },
89
  {
90
- "epoch": 0.42,
91
  "learning_rate": 0.0002,
92
- "loss": 1.5917,
93
  "step": 28
94
  },
95
  {
96
- "epoch": 0.45,
97
  "learning_rate": 0.0002,
98
- "loss": 1.8216,
99
  "step": 30
100
  },
101
  {
102
- "epoch": 0.48,
103
  "learning_rate": 0.0002,
104
- "loss": 1.9756,
105
  "step": 32
106
  },
107
  {
108
- "epoch": 0.51,
109
  "learning_rate": 0.0002,
110
- "loss": 2.1428,
111
  "step": 34
112
  },
113
  {
114
- "epoch": 0.54,
115
  "learning_rate": 0.0002,
116
- "loss": 1.7386,
117
  "step": 36
118
  },
119
  {
120
- "epoch": 0.57,
121
  "learning_rate": 0.0002,
122
- "loss": 1.3734,
123
  "step": 38
124
  },
125
  {
126
- "epoch": 0.6,
127
  "learning_rate": 0.0002,
128
- "loss": 1.6077,
129
  "step": 40
130
  },
131
  {
132
- "epoch": 0.63,
133
  "learning_rate": 0.0002,
134
- "loss": 1.1963,
135
  "step": 42
136
  },
137
  {
138
- "epoch": 0.66,
139
  "learning_rate": 0.0002,
140
- "loss": 1.4771,
141
  "step": 44
142
  },
143
  {
144
- "epoch": 0.69,
145
  "learning_rate": 0.0002,
146
- "loss": 1.5985,
147
  "step": 46
148
  },
149
- {
150
- "epoch": 0.72,
151
- "learning_rate": 0.0002,
152
- "loss": 1.791,
153
- "step": 48
154
- },
155
- {
156
- "epoch": 0.75,
157
- "learning_rate": 0.0002,
158
- "loss": 1.6919,
159
- "step": 50
160
- },
161
- {
162
- "epoch": 0.78,
163
- "learning_rate": 0.0002,
164
- "loss": 1.4632,
165
- "step": 52
166
- },
167
- {
168
- "epoch": 0.81,
169
- "learning_rate": 0.0002,
170
- "loss": 1.4936,
171
- "step": 54
172
- },
173
- {
174
- "epoch": 0.84,
175
- "learning_rate": 0.0002,
176
- "loss": 1.3692,
177
- "step": 56
178
- },
179
- {
180
- "epoch": 0.86,
181
- "learning_rate": 0.0002,
182
- "loss": 1.1492,
183
- "step": 58
184
- },
185
- {
186
- "epoch": 0.89,
187
- "learning_rate": 0.0002,
188
- "loss": 1.3765,
189
- "step": 60
190
- },
191
- {
192
- "epoch": 0.92,
193
- "learning_rate": 0.0002,
194
- "loss": 1.566,
195
- "step": 62
196
- },
197
- {
198
- "epoch": 0.95,
199
- "learning_rate": 0.0002,
200
- "loss": 1.7949,
201
- "step": 64
202
- },
203
  {
204
  "epoch": 0.98,
205
  "learning_rate": 0.0002,
206
- "loss": 1.3434,
207
- "step": 66
208
- },
209
- {
210
- "epoch": 1.01,
211
- "learning_rate": 0.0002,
212
- "loss": 2.1242,
213
- "step": 68
214
- },
215
- {
216
- "epoch": 1.04,
217
- "learning_rate": 0.0002,
218
- "loss": 2.0601,
219
- "step": 70
220
- },
221
- {
222
- "epoch": 1.07,
223
- "learning_rate": 0.0002,
224
- "loss": 1.6529,
225
- "step": 72
226
- },
227
- {
228
- "epoch": 1.1,
229
- "learning_rate": 0.0002,
230
- "loss": 1.3424,
231
- "step": 74
232
- },
233
- {
234
- "epoch": 1.13,
235
- "learning_rate": 0.0002,
236
- "loss": 1.3007,
237
- "step": 76
238
- },
239
- {
240
- "epoch": 1.16,
241
- "learning_rate": 0.0002,
242
- "loss": 1.0862,
243
- "step": 78
244
- },
245
- {
246
- "epoch": 1.19,
247
- "learning_rate": 0.0002,
248
- "loss": 1.3806,
249
- "step": 80
250
- },
251
- {
252
- "epoch": 1.22,
253
- "learning_rate": 0.0002,
254
- "loss": 1.4392,
255
- "step": 82
256
- },
257
- {
258
- "epoch": 1.25,
259
- "learning_rate": 0.0002,
260
- "loss": 1.743,
261
- "step": 84
262
- },
263
- {
264
- "epoch": 1.28,
265
- "learning_rate": 0.0002,
266
- "loss": 1.7389,
267
- "step": 86
268
- },
269
- {
270
- "epoch": 1.31,
271
- "learning_rate": 0.0002,
272
- "loss": 1.3633,
273
- "step": 88
274
- },
275
- {
276
- "epoch": 1.34,
277
- "learning_rate": 0.0002,
278
- "loss": 1.499,
279
- "step": 90
280
- },
281
- {
282
- "epoch": 1.37,
283
- "learning_rate": 0.0002,
284
- "loss": 1.0982,
285
- "step": 92
286
- },
287
- {
288
- "epoch": 1.4,
289
- "learning_rate": 0.0002,
290
- "loss": 1.1422,
291
- "step": 94
292
- },
293
- {
294
- "epoch": 1.43,
295
- "learning_rate": 0.0002,
296
- "loss": 1.3433,
297
- "step": 96
298
- },
299
- {
300
- "epoch": 1.46,
301
- "learning_rate": 0.0002,
302
- "loss": 1.5716,
303
- "step": 98
304
- },
305
- {
306
- "epoch": 1.49,
307
- "learning_rate": 0.0002,
308
- "loss": 1.8445,
309
- "step": 100
310
- },
311
- {
312
- "epoch": 1.52,
313
- "learning_rate": 0.0002,
314
- "loss": 2.0208,
315
- "step": 102
316
- },
317
- {
318
- "epoch": 1.55,
319
- "learning_rate": 0.0002,
320
- "loss": 1.3225,
321
- "step": 104
322
- },
323
- {
324
- "epoch": 1.58,
325
- "learning_rate": 0.0002,
326
- "loss": 1.3893,
327
- "step": 106
328
- },
329
- {
330
- "epoch": 1.61,
331
- "learning_rate": 0.0002,
332
- "loss": 1.2396,
333
- "step": 108
334
- },
335
- {
336
- "epoch": 1.64,
337
- "learning_rate": 0.0002,
338
- "loss": 1.1587,
339
- "step": 110
340
- },
341
- {
342
- "epoch": 1.67,
343
- "learning_rate": 0.0002,
344
- "loss": 1.292,
345
- "step": 112
346
- },
347
- {
348
- "epoch": 1.7,
349
- "learning_rate": 0.0002,
350
- "loss": 1.5348,
351
- "step": 114
352
- },
353
- {
354
- "epoch": 1.73,
355
- "learning_rate": 0.0002,
356
- "loss": 1.906,
357
- "step": 116
358
- },
359
- {
360
- "epoch": 1.76,
361
- "learning_rate": 0.0002,
362
- "loss": 1.8341,
363
- "step": 118
364
- },
365
- {
366
- "epoch": 1.79,
367
- "learning_rate": 0.0002,
368
- "loss": 1.499,
369
- "step": 120
370
- },
371
- {
372
- "epoch": 1.82,
373
- "learning_rate": 0.0002,
374
- "loss": 1.2827,
375
- "step": 122
376
- },
377
- {
378
- "epoch": 1.85,
379
- "learning_rate": 0.0002,
380
- "loss": 1.441,
381
- "step": 124
382
- },
383
- {
384
- "epoch": 1.88,
385
- "learning_rate": 0.0002,
386
- "loss": 1.1569,
387
- "step": 126
388
- },
389
- {
390
- "epoch": 1.91,
391
- "learning_rate": 0.0002,
392
- "loss": 1.4699,
393
- "step": 128
394
- },
395
- {
396
- "epoch": 1.94,
397
- "learning_rate": 0.0002,
398
- "loss": 1.4675,
399
- "step": 130
400
- },
401
- {
402
- "epoch": 1.97,
403
- "learning_rate": 0.0002,
404
- "loss": 1.4023,
405
- "step": 132
406
- },
407
- {
408
- "epoch": 2.0,
409
- "learning_rate": 0.0002,
410
- "loss": 1.353,
411
- "step": 134
412
- },
413
- {
414
- "epoch": 2.03,
415
- "learning_rate": 0.0002,
416
- "loss": 1.8645,
417
- "step": 136
418
- },
419
- {
420
- "epoch": 2.06,
421
- "learning_rate": 0.0002,
422
- "loss": 1.3303,
423
- "step": 138
424
- },
425
- {
426
- "epoch": 2.09,
427
- "learning_rate": 0.0002,
428
- "loss": 1.3192,
429
- "step": 140
430
- },
431
- {
432
- "epoch": 2.12,
433
- "learning_rate": 0.0002,
434
- "loss": 1.4044,
435
- "step": 142
436
- },
437
- {
438
- "epoch": 2.15,
439
- "learning_rate": 0.0002,
440
- "loss": 1.0026,
441
- "step": 144
442
- },
443
- {
444
- "epoch": 2.18,
445
- "learning_rate": 0.0002,
446
- "loss": 1.2984,
447
- "step": 146
448
- },
449
- {
450
- "epoch": 2.21,
451
- "learning_rate": 0.0002,
452
- "loss": 1.1825,
453
- "step": 148
454
- },
455
- {
456
- "epoch": 2.24,
457
- "learning_rate": 0.0002,
458
- "loss": 1.2081,
459
- "step": 150
460
- },
461
- {
462
- "epoch": 2.27,
463
- "learning_rate": 0.0002,
464
- "loss": 2.3909,
465
- "step": 152
466
- },
467
- {
468
- "epoch": 2.3,
469
- "learning_rate": 0.0002,
470
- "loss": 1.4779,
471
- "step": 154
472
- },
473
- {
474
- "epoch": 2.33,
475
- "learning_rate": 0.0002,
476
- "loss": 1.3218,
477
- "step": 156
478
- },
479
- {
480
- "epoch": 2.36,
481
- "learning_rate": 0.0002,
482
- "loss": 1.2386,
483
- "step": 158
484
- },
485
- {
486
- "epoch": 2.39,
487
- "learning_rate": 0.0002,
488
- "loss": 1.0851,
489
- "step": 160
490
- },
491
- {
492
- "epoch": 2.42,
493
- "learning_rate": 0.0002,
494
- "loss": 1.108,
495
- "step": 162
496
- },
497
- {
498
- "epoch": 2.45,
499
- "learning_rate": 0.0002,
500
- "loss": 1.2006,
501
- "step": 164
502
- },
503
- {
504
- "epoch": 2.48,
505
- "learning_rate": 0.0002,
506
- "loss": 1.3188,
507
- "step": 166
508
- },
509
- {
510
- "epoch": 2.51,
511
- "learning_rate": 0.0002,
512
- "loss": 2.5201,
513
- "step": 168
514
- },
515
- {
516
- "epoch": 2.53,
517
- "learning_rate": 0.0002,
518
- "loss": 1.4681,
519
- "step": 170
520
- },
521
- {
522
- "epoch": 2.56,
523
- "learning_rate": 0.0002,
524
- "loss": 1.3692,
525
- "step": 172
526
- },
527
- {
528
- "epoch": 2.59,
529
- "learning_rate": 0.0002,
530
- "loss": 1.2927,
531
- "step": 174
532
- },
533
- {
534
- "epoch": 2.62,
535
- "learning_rate": 0.0002,
536
- "loss": 1.0143,
537
- "step": 176
538
- },
539
- {
540
- "epoch": 2.65,
541
- "learning_rate": 0.0002,
542
- "loss": 1.084,
543
- "step": 178
544
- },
545
- {
546
- "epoch": 2.68,
547
- "learning_rate": 0.0002,
548
- "loss": 1.1066,
549
- "step": 180
550
- },
551
- {
552
- "epoch": 2.71,
553
- "learning_rate": 0.0002,
554
- "loss": 1.1752,
555
- "step": 182
556
- },
557
- {
558
- "epoch": 2.74,
559
- "learning_rate": 0.0002,
560
- "loss": 1.9674,
561
- "step": 184
562
- },
563
- {
564
- "epoch": 2.77,
565
- "learning_rate": 0.0002,
566
- "loss": 1.8383,
567
- "step": 186
568
- },
569
- {
570
- "epoch": 2.8,
571
- "learning_rate": 0.0002,
572
- "loss": 1.3012,
573
- "step": 188
574
- },
575
- {
576
- "epoch": 2.83,
577
- "learning_rate": 0.0002,
578
- "loss": 1.4696,
579
- "step": 190
580
- },
581
- {
582
- "epoch": 2.86,
583
- "learning_rate": 0.0002,
584
- "loss": 1.0073,
585
- "step": 192
586
- },
587
- {
588
- "epoch": 2.89,
589
- "learning_rate": 0.0002,
590
- "loss": 1.0344,
591
- "step": 194
592
- },
593
- {
594
- "epoch": 2.92,
595
- "learning_rate": 0.0002,
596
- "loss": 1.199,
597
- "step": 196
598
- },
599
- {
600
- "epoch": 2.95,
601
- "learning_rate": 0.0002,
602
- "loss": 1.167,
603
- "step": 198
604
- },
605
- {
606
- "epoch": 2.98,
607
- "learning_rate": 0.0002,
608
- "loss": 1.4507,
609
- "step": 200
610
  }
611
  ],
612
  "logging_steps": 2,
613
- "max_steps": 201,
614
  "num_input_tokens_seen": 0,
615
- "num_train_epochs": 3,
616
  "save_steps": 500,
617
- "total_flos": 1.3571443592994816e+16,
618
  "train_batch_size": 1,
619
  "trial_name": null,
620
  "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": 2.3604,
15
  "step": 2
16
  },
17
  {
18
+ "epoch": 0.08,
19
  "learning_rate": 0.0002,
20
+ "loss": 2.4466,
21
  "step": 4
22
  },
23
  {
24
+ "epoch": 0.12,
25
  "learning_rate": 0.0002,
26
+ "loss": 2.8212,
27
  "step": 6
28
  },
29
  {
30
+ "epoch": 0.16,
31
  "learning_rate": 0.0002,
32
+ "loss": 2.638,
33
  "step": 8
34
  },
35
  {
36
+ "epoch": 0.21,
37
  "learning_rate": 0.0002,
38
+ "loss": 2.8046,
39
  "step": 10
40
  },
41
  {
42
+ "epoch": 0.25,
43
  "learning_rate": 0.0002,
44
+ "loss": 3.2636,
45
  "step": 12
46
  },
47
  {
48
+ "epoch": 0.29,
49
  "learning_rate": 0.0002,
50
+ "loss": 2.2681,
51
  "step": 14
52
  },
53
  {
54
+ "epoch": 0.33,
55
  "learning_rate": 0.0002,
56
+ "loss": 2.3826,
57
  "step": 16
58
  },
59
  {
60
+ "epoch": 0.37,
61
  "learning_rate": 0.0002,
62
+ "loss": 2.6718,
63
  "step": 18
64
  },
65
  {
66
+ "epoch": 0.41,
67
  "learning_rate": 0.0002,
68
+ "loss": 2.6197,
69
  "step": 20
70
  },
71
  {
72
+ "epoch": 0.45,
73
  "learning_rate": 0.0002,
74
+ "loss": 2.573,
75
  "step": 22
76
  },
77
  {
78
+ "epoch": 0.49,
79
  "learning_rate": 0.0002,
80
+ "loss": 3.1306,
81
  "step": 24
82
  },
83
  {
84
+ "epoch": 0.53,
85
  "learning_rate": 0.0002,
86
+ "loss": 2.2594,
87
  "step": 26
88
  },
89
  {
90
+ "epoch": 0.57,
91
  "learning_rate": 0.0002,
92
+ "loss": 2.4572,
93
  "step": 28
94
  },
95
  {
96
+ "epoch": 0.62,
97
  "learning_rate": 0.0002,
98
+ "loss": 2.4869,
99
  "step": 30
100
  },
101
  {
102
+ "epoch": 0.66,
103
  "learning_rate": 0.0002,
104
+ "loss": 2.6306,
105
  "step": 32
106
  },
107
  {
108
+ "epoch": 0.7,
109
  "learning_rate": 0.0002,
110
+ "loss": 2.6139,
111
  "step": 34
112
  },
113
  {
114
+ "epoch": 0.74,
115
  "learning_rate": 0.0002,
116
+ "loss": 2.8307,
117
  "step": 36
118
  },
119
  {
120
+ "epoch": 0.78,
121
  "learning_rate": 0.0002,
122
+ "loss": 2.204,
123
  "step": 38
124
  },
125
  {
126
+ "epoch": 0.82,
127
  "learning_rate": 0.0002,
128
+ "loss": 2.2423,
129
  "step": 40
130
  },
131
  {
132
+ "epoch": 0.86,
133
  "learning_rate": 0.0002,
134
+ "loss": 2.3021,
135
  "step": 42
136
  },
137
  {
138
+ "epoch": 0.9,
139
  "learning_rate": 0.0002,
140
+ "loss": 2.3643,
141
  "step": 44
142
  },
143
  {
144
+ "epoch": 0.94,
145
  "learning_rate": 0.0002,
146
+ "loss": 2.6392,
147
  "step": 46
148
  },
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
149
  {
150
  "epoch": 0.98,
151
  "learning_rate": 0.0002,
152
+ "loss": 2.9109,
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": 2058945513185280.0,
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 sha256:505b8db6a4554d6599a7b5dedea699b7d4af0c4d98baaceb6ea124eaacbf9a0c
3
  size 4728
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e3eeebac40f73e5cebd2ccfc5dbebb5cb8c8e9abdf4f8fae6ceab6d2b7c8eb9f
3
  size 4728