ccore commited on
Commit
2faa43f
1 Parent(s): a35c284

Upload folder using huggingface_hub

Browse files
README.md CHANGED
@@ -1,3 +1,53 @@
1
  ---
2
- license: other
 
 
 
 
 
3
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
+ base_model: ./output
3
+ tags:
4
+ - generated_from_trainer
5
+ model-index:
6
+ - name: output
7
+ results: []
8
  ---
9
+
10
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
11
+ should probably proofread and complete it, then remove this comment. -->
12
+
13
+ # output
14
+
15
+ This model is a fine-tuned version of [./output](https://huggingface.co/./output) on an unknown dataset.
16
+
17
+ ## Model description
18
+
19
+ More information needed
20
+
21
+ ## Intended uses & limitations
22
+
23
+ More information needed
24
+
25
+ ## Training and evaluation data
26
+
27
+ More information needed
28
+
29
+ ## Training procedure
30
+
31
+ ### Training hyperparameters
32
+
33
+ The following hyperparameters were used during training:
34
+ - learning_rate: 0.001
35
+ - train_batch_size: 2
36
+ - eval_batch_size: 2
37
+ - seed: 42
38
+ - gradient_accumulation_steps: 128
39
+ - total_train_batch_size: 256
40
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
41
+ - lr_scheduler_type: constant
42
+ - num_epochs: 1.0
43
+
44
+ ### Training results
45
+
46
+
47
+
48
+ ### Framework versions
49
+
50
+ - Transformers 4.34.0.dev0
51
+ - Pytorch 2.0.1+cu117
52
+ - Datasets 2.14.5
53
+ - Tokenizers 0.14.0
all_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "train_loss": 4.884670708277454,
4
+ "train_runtime": 5501.4397,
5
+ "train_samples": 37518,
6
+ "train_samples_per_second": 6.82,
7
+ "train_steps_per_second": 0.027
8
+ }
checkpoint-1000/config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "./output",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "bos_token_id": 1,
7
+ "eos_token_id": 2,
8
+ "hidden_act": "silu",
9
+ "hidden_size": 256,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 512,
12
+ "max_position_embeddings": 8192,
13
+ "model_type": "llama",
14
+ "num_attention_heads": 4,
15
+ "num_hidden_layers": 2,
16
+ "num_key_value_heads": 4,
17
+ "pretraining_tp": 1,
18
+ "rms_norm_eps": 1e-05,
19
+ "rope_scaling": null,
20
+ "rope_theta": 10000.0,
21
+ "tie_word_embeddings": false,
22
+ "torch_dtype": "float32",
23
+ "transformers_version": "4.34.0.dev0",
24
+ "use_cache": true,
25
+ "vocab_size": 32000
26
+ }
checkpoint-1000/generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "transformers_version": "4.34.0.dev0"
6
+ }
checkpoint-1000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:01e43fe435f1ef34f45ed9c628a4b31462d9cddc926ebd8584bff10d3bc23729
3
+ size 141585770
checkpoint-1000/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9efef4e57fb2cdbaccf58e4fc6968c2f61f38f4a7f9e5161bfae929987b62ae3
3
+ size 70790896
checkpoint-1000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:77a81b11daa17ca5552ac86c1efc96365c58fc71c8d34fd48dc6220930e345d0
3
+ size 14575
checkpoint-1000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e28af83c57f2cddb6d735f7c816ebd9f24f4448153c24c61a1a5b5a0bd3955a9
3
+ size 627
checkpoint-1000/special_tokens_map.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "eos_token": "</s>",
4
+ "unk_token": "<unk>"
5
+ }
checkpoint-1000/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-1000/tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
checkpoint-1000/tokenizer_config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<unk>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<s>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ }
27
+ },
28
+ "additional_special_tokens": [],
29
+ "bos_token": "<s>",
30
+ "clean_up_tokenization_spaces": false,
31
+ "eos_token": "</s>",
32
+ "model_max_length": 8192,
33
+ "pad_token": null,
34
+ "sp_model_kwargs": {},
35
+ "tokenizer_class": "LlamaTokenizer",
36
+ "unk_token": "<unk>",
37
+ "use_default_system_prompt": true
38
+ }
checkpoint-1000/trainer_state.json ADDED
@@ -0,0 +1,1219 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 49.68944099378882,
5
+ "eval_steps": 500,
6
+ "global_step": 1000,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.25,
13
+ "learning_rate": 0.001,
14
+ "loss": 2.973,
15
+ "step": 5
16
+ },
17
+ {
18
+ "epoch": 0.5,
19
+ "learning_rate": 0.001,
20
+ "loss": 2.9669,
21
+ "step": 10
22
+ },
23
+ {
24
+ "epoch": 0.75,
25
+ "learning_rate": 0.001,
26
+ "loss": 2.8986,
27
+ "step": 15
28
+ },
29
+ {
30
+ "epoch": 0.99,
31
+ "learning_rate": 0.001,
32
+ "loss": 2.9083,
33
+ "step": 20
34
+ },
35
+ {
36
+ "epoch": 1.24,
37
+ "learning_rate": 0.001,
38
+ "loss": 2.8149,
39
+ "step": 25
40
+ },
41
+ {
42
+ "epoch": 1.49,
43
+ "learning_rate": 0.001,
44
+ "loss": 2.7961,
45
+ "step": 30
46
+ },
47
+ {
48
+ "epoch": 1.74,
49
+ "learning_rate": 0.001,
50
+ "loss": 2.7537,
51
+ "step": 35
52
+ },
53
+ {
54
+ "epoch": 1.99,
55
+ "learning_rate": 0.001,
56
+ "loss": 2.7839,
57
+ "step": 40
58
+ },
59
+ {
60
+ "epoch": 2.24,
61
+ "learning_rate": 0.001,
62
+ "loss": 2.7357,
63
+ "step": 45
64
+ },
65
+ {
66
+ "epoch": 2.48,
67
+ "learning_rate": 0.001,
68
+ "loss": 2.74,
69
+ "step": 50
70
+ },
71
+ {
72
+ "epoch": 2.73,
73
+ "learning_rate": 0.001,
74
+ "loss": 2.7264,
75
+ "step": 55
76
+ },
77
+ {
78
+ "epoch": 2.98,
79
+ "learning_rate": 0.001,
80
+ "loss": 2.6993,
81
+ "step": 60
82
+ },
83
+ {
84
+ "epoch": 3.23,
85
+ "learning_rate": 0.001,
86
+ "loss": 2.6521,
87
+ "step": 65
88
+ },
89
+ {
90
+ "epoch": 3.48,
91
+ "learning_rate": 0.001,
92
+ "loss": 2.6425,
93
+ "step": 70
94
+ },
95
+ {
96
+ "epoch": 3.73,
97
+ "learning_rate": 0.001,
98
+ "loss": 2.6921,
99
+ "step": 75
100
+ },
101
+ {
102
+ "epoch": 3.98,
103
+ "learning_rate": 0.001,
104
+ "loss": 2.695,
105
+ "step": 80
106
+ },
107
+ {
108
+ "epoch": 4.22,
109
+ "learning_rate": 0.001,
110
+ "loss": 2.5888,
111
+ "step": 85
112
+ },
113
+ {
114
+ "epoch": 4.47,
115
+ "learning_rate": 0.001,
116
+ "loss": 2.5928,
117
+ "step": 90
118
+ },
119
+ {
120
+ "epoch": 4.72,
121
+ "learning_rate": 0.001,
122
+ "loss": 2.7252,
123
+ "step": 95
124
+ },
125
+ {
126
+ "epoch": 4.97,
127
+ "learning_rate": 0.001,
128
+ "loss": 2.6456,
129
+ "step": 100
130
+ },
131
+ {
132
+ "epoch": 5.22,
133
+ "learning_rate": 0.001,
134
+ "loss": 2.6007,
135
+ "step": 105
136
+ },
137
+ {
138
+ "epoch": 5.47,
139
+ "learning_rate": 0.001,
140
+ "loss": 2.5469,
141
+ "step": 110
142
+ },
143
+ {
144
+ "epoch": 5.71,
145
+ "learning_rate": 0.001,
146
+ "loss": 2.564,
147
+ "step": 115
148
+ },
149
+ {
150
+ "epoch": 5.96,
151
+ "learning_rate": 0.001,
152
+ "loss": 2.6437,
153
+ "step": 120
154
+ },
155
+ {
156
+ "epoch": 6.21,
157
+ "learning_rate": 0.001,
158
+ "loss": 2.5038,
159
+ "step": 125
160
+ },
161
+ {
162
+ "epoch": 6.46,
163
+ "learning_rate": 0.001,
164
+ "loss": 2.6013,
165
+ "step": 130
166
+ },
167
+ {
168
+ "epoch": 6.71,
169
+ "learning_rate": 0.001,
170
+ "loss": 2.5481,
171
+ "step": 135
172
+ },
173
+ {
174
+ "epoch": 6.96,
175
+ "learning_rate": 0.001,
176
+ "loss": 2.5757,
177
+ "step": 140
178
+ },
179
+ {
180
+ "epoch": 7.2,
181
+ "learning_rate": 0.001,
182
+ "loss": 2.4941,
183
+ "step": 145
184
+ },
185
+ {
186
+ "epoch": 7.45,
187
+ "learning_rate": 0.001,
188
+ "loss": 2.4846,
189
+ "step": 150
190
+ },
191
+ {
192
+ "epoch": 7.7,
193
+ "learning_rate": 0.001,
194
+ "loss": 2.5206,
195
+ "step": 155
196
+ },
197
+ {
198
+ "epoch": 7.95,
199
+ "learning_rate": 0.001,
200
+ "loss": 2.6048,
201
+ "step": 160
202
+ },
203
+ {
204
+ "epoch": 8.2,
205
+ "learning_rate": 0.001,
206
+ "loss": 2.5142,
207
+ "step": 165
208
+ },
209
+ {
210
+ "epoch": 8.45,
211
+ "learning_rate": 0.001,
212
+ "loss": 2.4473,
213
+ "step": 170
214
+ },
215
+ {
216
+ "epoch": 8.7,
217
+ "learning_rate": 0.001,
218
+ "loss": 2.5176,
219
+ "step": 175
220
+ },
221
+ {
222
+ "epoch": 8.94,
223
+ "learning_rate": 0.001,
224
+ "loss": 2.4694,
225
+ "step": 180
226
+ },
227
+ {
228
+ "epoch": 9.19,
229
+ "learning_rate": 0.001,
230
+ "loss": 2.4416,
231
+ "step": 185
232
+ },
233
+ {
234
+ "epoch": 9.44,
235
+ "learning_rate": 0.001,
236
+ "loss": 2.4431,
237
+ "step": 190
238
+ },
239
+ {
240
+ "epoch": 9.69,
241
+ "learning_rate": 0.001,
242
+ "loss": 2.4121,
243
+ "step": 195
244
+ },
245
+ {
246
+ "epoch": 9.94,
247
+ "learning_rate": 0.001,
248
+ "loss": 2.5235,
249
+ "step": 200
250
+ },
251
+ {
252
+ "epoch": 10.19,
253
+ "learning_rate": 0.001,
254
+ "loss": 2.5051,
255
+ "step": 205
256
+ },
257
+ {
258
+ "epoch": 10.43,
259
+ "learning_rate": 0.001,
260
+ "loss": 2.4323,
261
+ "step": 210
262
+ },
263
+ {
264
+ "epoch": 10.68,
265
+ "learning_rate": 0.001,
266
+ "loss": 2.4477,
267
+ "step": 215
268
+ },
269
+ {
270
+ "epoch": 10.93,
271
+ "learning_rate": 0.001,
272
+ "loss": 2.3715,
273
+ "step": 220
274
+ },
275
+ {
276
+ "epoch": 11.18,
277
+ "learning_rate": 0.001,
278
+ "loss": 2.3412,
279
+ "step": 225
280
+ },
281
+ {
282
+ "epoch": 11.43,
283
+ "learning_rate": 0.001,
284
+ "loss": 2.3728,
285
+ "step": 230
286
+ },
287
+ {
288
+ "epoch": 11.68,
289
+ "learning_rate": 0.001,
290
+ "loss": 2.388,
291
+ "step": 235
292
+ },
293
+ {
294
+ "epoch": 11.93,
295
+ "learning_rate": 0.001,
296
+ "loss": 2.4327,
297
+ "step": 240
298
+ },
299
+ {
300
+ "epoch": 12.17,
301
+ "learning_rate": 0.001,
302
+ "loss": 2.3181,
303
+ "step": 245
304
+ },
305
+ {
306
+ "epoch": 12.42,
307
+ "learning_rate": 0.001,
308
+ "loss": 2.2734,
309
+ "step": 250
310
+ },
311
+ {
312
+ "epoch": 12.67,
313
+ "learning_rate": 0.001,
314
+ "loss": 2.3641,
315
+ "step": 255
316
+ },
317
+ {
318
+ "epoch": 12.92,
319
+ "learning_rate": 0.001,
320
+ "loss": 2.3942,
321
+ "step": 260
322
+ },
323
+ {
324
+ "epoch": 13.17,
325
+ "learning_rate": 0.001,
326
+ "loss": 2.3832,
327
+ "step": 265
328
+ },
329
+ {
330
+ "epoch": 13.42,
331
+ "learning_rate": 0.001,
332
+ "loss": 2.3198,
333
+ "step": 270
334
+ },
335
+ {
336
+ "epoch": 13.66,
337
+ "learning_rate": 0.001,
338
+ "loss": 2.2833,
339
+ "step": 275
340
+ },
341
+ {
342
+ "epoch": 13.91,
343
+ "learning_rate": 0.001,
344
+ "loss": 2.3702,
345
+ "step": 280
346
+ },
347
+ {
348
+ "epoch": 14.16,
349
+ "learning_rate": 0.001,
350
+ "loss": 2.3507,
351
+ "step": 285
352
+ },
353
+ {
354
+ "epoch": 14.41,
355
+ "learning_rate": 0.001,
356
+ "loss": 2.2932,
357
+ "step": 290
358
+ },
359
+ {
360
+ "epoch": 14.66,
361
+ "learning_rate": 0.001,
362
+ "loss": 2.3532,
363
+ "step": 295
364
+ },
365
+ {
366
+ "epoch": 14.91,
367
+ "learning_rate": 0.001,
368
+ "loss": 2.2199,
369
+ "step": 300
370
+ },
371
+ {
372
+ "epoch": 15.16,
373
+ "learning_rate": 0.001,
374
+ "loss": 2.2902,
375
+ "step": 305
376
+ },
377
+ {
378
+ "epoch": 15.4,
379
+ "learning_rate": 0.001,
380
+ "loss": 2.304,
381
+ "step": 310
382
+ },
383
+ {
384
+ "epoch": 15.65,
385
+ "learning_rate": 0.001,
386
+ "loss": 2.2705,
387
+ "step": 315
388
+ },
389
+ {
390
+ "epoch": 15.9,
391
+ "learning_rate": 0.001,
392
+ "loss": 2.2594,
393
+ "step": 320
394
+ },
395
+ {
396
+ "epoch": 16.15,
397
+ "learning_rate": 0.001,
398
+ "loss": 2.2122,
399
+ "step": 325
400
+ },
401
+ {
402
+ "epoch": 16.4,
403
+ "learning_rate": 0.001,
404
+ "loss": 2.2527,
405
+ "step": 330
406
+ },
407
+ {
408
+ "epoch": 16.65,
409
+ "learning_rate": 0.001,
410
+ "loss": 2.2212,
411
+ "step": 335
412
+ },
413
+ {
414
+ "epoch": 16.89,
415
+ "learning_rate": 0.001,
416
+ "loss": 2.2597,
417
+ "step": 340
418
+ },
419
+ {
420
+ "epoch": 17.14,
421
+ "learning_rate": 0.001,
422
+ "loss": 2.2512,
423
+ "step": 345
424
+ },
425
+ {
426
+ "epoch": 17.39,
427
+ "learning_rate": 0.001,
428
+ "loss": 2.1741,
429
+ "step": 350
430
+ },
431
+ {
432
+ "epoch": 17.64,
433
+ "learning_rate": 0.001,
434
+ "loss": 2.2029,
435
+ "step": 355
436
+ },
437
+ {
438
+ "epoch": 17.89,
439
+ "learning_rate": 0.001,
440
+ "loss": 2.2779,
441
+ "step": 360
442
+ },
443
+ {
444
+ "epoch": 18.14,
445
+ "learning_rate": 0.001,
446
+ "loss": 2.1796,
447
+ "step": 365
448
+ },
449
+ {
450
+ "epoch": 18.39,
451
+ "learning_rate": 0.001,
452
+ "loss": 2.0951,
453
+ "step": 370
454
+ },
455
+ {
456
+ "epoch": 18.63,
457
+ "learning_rate": 0.001,
458
+ "loss": 2.1963,
459
+ "step": 375
460
+ },
461
+ {
462
+ "epoch": 18.88,
463
+ "learning_rate": 0.001,
464
+ "loss": 2.3042,
465
+ "step": 380
466
+ },
467
+ {
468
+ "epoch": 19.13,
469
+ "learning_rate": 0.001,
470
+ "loss": 2.1884,
471
+ "step": 385
472
+ },
473
+ {
474
+ "epoch": 19.38,
475
+ "learning_rate": 0.001,
476
+ "loss": 2.2027,
477
+ "step": 390
478
+ },
479
+ {
480
+ "epoch": 19.63,
481
+ "learning_rate": 0.001,
482
+ "loss": 2.1516,
483
+ "step": 395
484
+ },
485
+ {
486
+ "epoch": 19.88,
487
+ "learning_rate": 0.001,
488
+ "loss": 2.1975,
489
+ "step": 400
490
+ },
491
+ {
492
+ "epoch": 20.12,
493
+ "learning_rate": 0.001,
494
+ "loss": 2.1499,
495
+ "step": 405
496
+ },
497
+ {
498
+ "epoch": 20.37,
499
+ "learning_rate": 0.001,
500
+ "loss": 2.1268,
501
+ "step": 410
502
+ },
503
+ {
504
+ "epoch": 20.62,
505
+ "learning_rate": 0.001,
506
+ "loss": 2.0978,
507
+ "step": 415
508
+ },
509
+ {
510
+ "epoch": 20.87,
511
+ "learning_rate": 0.001,
512
+ "loss": 2.1173,
513
+ "step": 420
514
+ },
515
+ {
516
+ "epoch": 21.12,
517
+ "learning_rate": 0.001,
518
+ "loss": 2.1737,
519
+ "step": 425
520
+ },
521
+ {
522
+ "epoch": 21.37,
523
+ "learning_rate": 0.001,
524
+ "loss": 2.0569,
525
+ "step": 430
526
+ },
527
+ {
528
+ "epoch": 21.61,
529
+ "learning_rate": 0.001,
530
+ "loss": 2.1043,
531
+ "step": 435
532
+ },
533
+ {
534
+ "epoch": 21.86,
535
+ "learning_rate": 0.001,
536
+ "loss": 2.0893,
537
+ "step": 440
538
+ },
539
+ {
540
+ "epoch": 22.11,
541
+ "learning_rate": 0.001,
542
+ "loss": 2.2145,
543
+ "step": 445
544
+ },
545
+ {
546
+ "epoch": 22.36,
547
+ "learning_rate": 0.001,
548
+ "loss": 2.0312,
549
+ "step": 450
550
+ },
551
+ {
552
+ "epoch": 22.61,
553
+ "learning_rate": 0.001,
554
+ "loss": 2.0685,
555
+ "step": 455
556
+ },
557
+ {
558
+ "epoch": 22.86,
559
+ "learning_rate": 0.001,
560
+ "loss": 2.0475,
561
+ "step": 460
562
+ },
563
+ {
564
+ "epoch": 23.11,
565
+ "learning_rate": 0.001,
566
+ "loss": 2.0472,
567
+ "step": 465
568
+ },
569
+ {
570
+ "epoch": 23.35,
571
+ "learning_rate": 0.001,
572
+ "loss": 2.0081,
573
+ "step": 470
574
+ },
575
+ {
576
+ "epoch": 23.6,
577
+ "learning_rate": 0.001,
578
+ "loss": 2.0543,
579
+ "step": 475
580
+ },
581
+ {
582
+ "epoch": 23.85,
583
+ "learning_rate": 0.001,
584
+ "loss": 2.093,
585
+ "step": 480
586
+ },
587
+ {
588
+ "epoch": 24.1,
589
+ "learning_rate": 0.001,
590
+ "loss": 1.9895,
591
+ "step": 485
592
+ },
593
+ {
594
+ "epoch": 24.35,
595
+ "learning_rate": 0.001,
596
+ "loss": 1.9842,
597
+ "step": 490
598
+ },
599
+ {
600
+ "epoch": 24.6,
601
+ "learning_rate": 0.001,
602
+ "loss": 2.0427,
603
+ "step": 495
604
+ },
605
+ {
606
+ "epoch": 24.84,
607
+ "learning_rate": 0.001,
608
+ "loss": 2.0707,
609
+ "step": 500
610
+ },
611
+ {
612
+ "epoch": 25.09,
613
+ "learning_rate": 0.001,
614
+ "loss": 2.0274,
615
+ "step": 505
616
+ },
617
+ {
618
+ "epoch": 25.34,
619
+ "learning_rate": 0.001,
620
+ "loss": 1.9516,
621
+ "step": 510
622
+ },
623
+ {
624
+ "epoch": 25.59,
625
+ "learning_rate": 0.001,
626
+ "loss": 2.0104,
627
+ "step": 515
628
+ },
629
+ {
630
+ "epoch": 25.84,
631
+ "learning_rate": 0.001,
632
+ "loss": 2.032,
633
+ "step": 520
634
+ },
635
+ {
636
+ "epoch": 26.09,
637
+ "learning_rate": 0.001,
638
+ "loss": 2.0103,
639
+ "step": 525
640
+ },
641
+ {
642
+ "epoch": 26.34,
643
+ "learning_rate": 0.001,
644
+ "loss": 1.9496,
645
+ "step": 530
646
+ },
647
+ {
648
+ "epoch": 26.58,
649
+ "learning_rate": 0.001,
650
+ "loss": 1.9511,
651
+ "step": 535
652
+ },
653
+ {
654
+ "epoch": 26.83,
655
+ "learning_rate": 0.001,
656
+ "loss": 2.0482,
657
+ "step": 540
658
+ },
659
+ {
660
+ "epoch": 27.08,
661
+ "learning_rate": 0.001,
662
+ "loss": 1.9065,
663
+ "step": 545
664
+ },
665
+ {
666
+ "epoch": 27.33,
667
+ "learning_rate": 0.001,
668
+ "loss": 1.9379,
669
+ "step": 550
670
+ },
671
+ {
672
+ "epoch": 27.58,
673
+ "learning_rate": 0.001,
674
+ "loss": 1.9049,
675
+ "step": 555
676
+ },
677
+ {
678
+ "epoch": 27.83,
679
+ "learning_rate": 0.001,
680
+ "loss": 1.974,
681
+ "step": 560
682
+ },
683
+ {
684
+ "epoch": 28.07,
685
+ "learning_rate": 0.001,
686
+ "loss": 1.953,
687
+ "step": 565
688
+ },
689
+ {
690
+ "epoch": 28.32,
691
+ "learning_rate": 0.001,
692
+ "loss": 1.9527,
693
+ "step": 570
694
+ },
695
+ {
696
+ "epoch": 28.57,
697
+ "learning_rate": 0.001,
698
+ "loss": 1.9382,
699
+ "step": 575
700
+ },
701
+ {
702
+ "epoch": 28.82,
703
+ "learning_rate": 0.001,
704
+ "loss": 1.8777,
705
+ "step": 580
706
+ },
707
+ {
708
+ "epoch": 29.07,
709
+ "learning_rate": 0.001,
710
+ "loss": 1.926,
711
+ "step": 585
712
+ },
713
+ {
714
+ "epoch": 29.32,
715
+ "learning_rate": 0.001,
716
+ "loss": 1.8399,
717
+ "step": 590
718
+ },
719
+ {
720
+ "epoch": 29.57,
721
+ "learning_rate": 0.001,
722
+ "loss": 1.8952,
723
+ "step": 595
724
+ },
725
+ {
726
+ "epoch": 29.81,
727
+ "learning_rate": 0.001,
728
+ "loss": 1.9779,
729
+ "step": 600
730
+ },
731
+ {
732
+ "epoch": 30.06,
733
+ "learning_rate": 0.001,
734
+ "loss": 1.8969,
735
+ "step": 605
736
+ },
737
+ {
738
+ "epoch": 30.31,
739
+ "learning_rate": 0.001,
740
+ "loss": 1.8222,
741
+ "step": 610
742
+ },
743
+ {
744
+ "epoch": 30.56,
745
+ "learning_rate": 0.001,
746
+ "loss": 1.8648,
747
+ "step": 615
748
+ },
749
+ {
750
+ "epoch": 30.81,
751
+ "learning_rate": 0.001,
752
+ "loss": 1.8852,
753
+ "step": 620
754
+ },
755
+ {
756
+ "epoch": 31.06,
757
+ "learning_rate": 0.001,
758
+ "loss": 1.9252,
759
+ "step": 625
760
+ },
761
+ {
762
+ "epoch": 31.3,
763
+ "learning_rate": 0.001,
764
+ "loss": 1.8219,
765
+ "step": 630
766
+ },
767
+ {
768
+ "epoch": 31.55,
769
+ "learning_rate": 0.001,
770
+ "loss": 1.8474,
771
+ "step": 635
772
+ },
773
+ {
774
+ "epoch": 31.8,
775
+ "learning_rate": 0.001,
776
+ "loss": 1.8013,
777
+ "step": 640
778
+ },
779
+ {
780
+ "epoch": 32.05,
781
+ "learning_rate": 0.001,
782
+ "loss": 1.9605,
783
+ "step": 645
784
+ },
785
+ {
786
+ "epoch": 32.3,
787
+ "learning_rate": 0.001,
788
+ "loss": 1.747,
789
+ "step": 650
790
+ },
791
+ {
792
+ "epoch": 32.55,
793
+ "learning_rate": 0.001,
794
+ "loss": 1.8404,
795
+ "step": 655
796
+ },
797
+ {
798
+ "epoch": 32.8,
799
+ "learning_rate": 0.001,
800
+ "loss": 1.8616,
801
+ "step": 660
802
+ },
803
+ {
804
+ "epoch": 33.04,
805
+ "learning_rate": 0.001,
806
+ "loss": 1.8597,
807
+ "step": 665
808
+ },
809
+ {
810
+ "epoch": 33.29,
811
+ "learning_rate": 0.001,
812
+ "loss": 1.8462,
813
+ "step": 670
814
+ },
815
+ {
816
+ "epoch": 33.54,
817
+ "learning_rate": 0.001,
818
+ "loss": 1.8022,
819
+ "step": 675
820
+ },
821
+ {
822
+ "epoch": 33.79,
823
+ "learning_rate": 0.001,
824
+ "loss": 1.813,
825
+ "step": 680
826
+ },
827
+ {
828
+ "epoch": 34.04,
829
+ "learning_rate": 0.001,
830
+ "loss": 1.7534,
831
+ "step": 685
832
+ },
833
+ {
834
+ "epoch": 34.29,
835
+ "learning_rate": 0.001,
836
+ "loss": 1.7472,
837
+ "step": 690
838
+ },
839
+ {
840
+ "epoch": 34.53,
841
+ "learning_rate": 0.001,
842
+ "loss": 1.7565,
843
+ "step": 695
844
+ },
845
+ {
846
+ "epoch": 34.78,
847
+ "learning_rate": 0.001,
848
+ "loss": 1.8073,
849
+ "step": 700
850
+ },
851
+ {
852
+ "epoch": 35.03,
853
+ "learning_rate": 0.001,
854
+ "loss": 1.8327,
855
+ "step": 705
856
+ },
857
+ {
858
+ "epoch": 35.28,
859
+ "learning_rate": 0.001,
860
+ "loss": 1.6831,
861
+ "step": 710
862
+ },
863
+ {
864
+ "epoch": 35.53,
865
+ "learning_rate": 0.001,
866
+ "loss": 1.7303,
867
+ "step": 715
868
+ },
869
+ {
870
+ "epoch": 35.78,
871
+ "learning_rate": 0.001,
872
+ "loss": 1.7749,
873
+ "step": 720
874
+ },
875
+ {
876
+ "epoch": 36.02,
877
+ "learning_rate": 0.001,
878
+ "loss": 1.8673,
879
+ "step": 725
880
+ },
881
+ {
882
+ "epoch": 36.27,
883
+ "learning_rate": 0.001,
884
+ "loss": 1.6578,
885
+ "step": 730
886
+ },
887
+ {
888
+ "epoch": 36.52,
889
+ "learning_rate": 0.001,
890
+ "loss": 1.7824,
891
+ "step": 735
892
+ },
893
+ {
894
+ "epoch": 36.77,
895
+ "learning_rate": 0.001,
896
+ "loss": 1.78,
897
+ "step": 740
898
+ },
899
+ {
900
+ "epoch": 37.02,
901
+ "learning_rate": 0.001,
902
+ "loss": 1.7728,
903
+ "step": 745
904
+ },
905
+ {
906
+ "epoch": 37.27,
907
+ "learning_rate": 0.001,
908
+ "loss": 1.7088,
909
+ "step": 750
910
+ },
911
+ {
912
+ "epoch": 37.52,
913
+ "learning_rate": 0.001,
914
+ "loss": 1.7322,
915
+ "step": 755
916
+ },
917
+ {
918
+ "epoch": 37.76,
919
+ "learning_rate": 0.001,
920
+ "loss": 1.6444,
921
+ "step": 760
922
+ },
923
+ {
924
+ "epoch": 38.01,
925
+ "learning_rate": 0.001,
926
+ "loss": 1.8092,
927
+ "step": 765
928
+ },
929
+ {
930
+ "epoch": 38.26,
931
+ "learning_rate": 0.001,
932
+ "loss": 1.6969,
933
+ "step": 770
934
+ },
935
+ {
936
+ "epoch": 38.51,
937
+ "learning_rate": 0.001,
938
+ "loss": 1.6509,
939
+ "step": 775
940
+ },
941
+ {
942
+ "epoch": 38.76,
943
+ "learning_rate": 0.001,
944
+ "loss": 1.6829,
945
+ "step": 780
946
+ },
947
+ {
948
+ "epoch": 39.01,
949
+ "learning_rate": 0.001,
950
+ "loss": 1.7081,
951
+ "step": 785
952
+ },
953
+ {
954
+ "epoch": 39.25,
955
+ "learning_rate": 0.001,
956
+ "loss": 1.6356,
957
+ "step": 790
958
+ },
959
+ {
960
+ "epoch": 39.5,
961
+ "learning_rate": 0.001,
962
+ "loss": 1.6999,
963
+ "step": 795
964
+ },
965
+ {
966
+ "epoch": 39.75,
967
+ "learning_rate": 0.001,
968
+ "loss": 1.6754,
969
+ "step": 800
970
+ },
971
+ {
972
+ "epoch": 40.0,
973
+ "learning_rate": 0.001,
974
+ "loss": 1.694,
975
+ "step": 805
976
+ },
977
+ {
978
+ "epoch": 40.25,
979
+ "learning_rate": 0.001,
980
+ "loss": 1.6114,
981
+ "step": 810
982
+ },
983
+ {
984
+ "epoch": 40.5,
985
+ "learning_rate": 0.001,
986
+ "loss": 1.5831,
987
+ "step": 815
988
+ },
989
+ {
990
+ "epoch": 40.75,
991
+ "learning_rate": 0.001,
992
+ "loss": 1.7196,
993
+ "step": 820
994
+ },
995
+ {
996
+ "epoch": 40.99,
997
+ "learning_rate": 0.001,
998
+ "loss": 1.6715,
999
+ "step": 825
1000
+ },
1001
+ {
1002
+ "epoch": 41.24,
1003
+ "learning_rate": 0.001,
1004
+ "loss": 1.6569,
1005
+ "step": 830
1006
+ },
1007
+ {
1008
+ "epoch": 41.49,
1009
+ "learning_rate": 0.001,
1010
+ "loss": 1.5417,
1011
+ "step": 835
1012
+ },
1013
+ {
1014
+ "epoch": 41.74,
1015
+ "learning_rate": 0.001,
1016
+ "loss": 1.7056,
1017
+ "step": 840
1018
+ },
1019
+ {
1020
+ "epoch": 41.99,
1021
+ "learning_rate": 0.001,
1022
+ "loss": 1.6408,
1023
+ "step": 845
1024
+ },
1025
+ {
1026
+ "epoch": 42.24,
1027
+ "learning_rate": 0.001,
1028
+ "loss": 1.5832,
1029
+ "step": 850
1030
+ },
1031
+ {
1032
+ "epoch": 42.48,
1033
+ "learning_rate": 0.001,
1034
+ "loss": 1.6063,
1035
+ "step": 855
1036
+ },
1037
+ {
1038
+ "epoch": 42.73,
1039
+ "learning_rate": 0.001,
1040
+ "loss": 1.6485,
1041
+ "step": 860
1042
+ },
1043
+ {
1044
+ "epoch": 42.98,
1045
+ "learning_rate": 0.001,
1046
+ "loss": 1.6044,
1047
+ "step": 865
1048
+ },
1049
+ {
1050
+ "epoch": 43.23,
1051
+ "learning_rate": 0.001,
1052
+ "loss": 1.5439,
1053
+ "step": 870
1054
+ },
1055
+ {
1056
+ "epoch": 43.48,
1057
+ "learning_rate": 0.001,
1058
+ "loss": 1.5154,
1059
+ "step": 875
1060
+ },
1061
+ {
1062
+ "epoch": 43.73,
1063
+ "learning_rate": 0.001,
1064
+ "loss": 1.5861,
1065
+ "step": 880
1066
+ },
1067
+ {
1068
+ "epoch": 43.98,
1069
+ "learning_rate": 0.001,
1070
+ "loss": 1.7179,
1071
+ "step": 885
1072
+ },
1073
+ {
1074
+ "epoch": 44.22,
1075
+ "learning_rate": 0.001,
1076
+ "loss": 1.5343,
1077
+ "step": 890
1078
+ },
1079
+ {
1080
+ "epoch": 44.47,
1081
+ "learning_rate": 0.001,
1082
+ "loss": 1.6002,
1083
+ "step": 895
1084
+ },
1085
+ {
1086
+ "epoch": 44.72,
1087
+ "learning_rate": 0.001,
1088
+ "loss": 1.5172,
1089
+ "step": 900
1090
+ },
1091
+ {
1092
+ "epoch": 44.97,
1093
+ "learning_rate": 0.001,
1094
+ "loss": 1.6329,
1095
+ "step": 905
1096
+ },
1097
+ {
1098
+ "epoch": 45.22,
1099
+ "learning_rate": 0.001,
1100
+ "loss": 1.5021,
1101
+ "step": 910
1102
+ },
1103
+ {
1104
+ "epoch": 45.47,
1105
+ "learning_rate": 0.001,
1106
+ "loss": 1.5144,
1107
+ "step": 915
1108
+ },
1109
+ {
1110
+ "epoch": 45.71,
1111
+ "learning_rate": 0.001,
1112
+ "loss": 1.5444,
1113
+ "step": 920
1114
+ },
1115
+ {
1116
+ "epoch": 45.96,
1117
+ "learning_rate": 0.001,
1118
+ "loss": 1.6281,
1119
+ "step": 925
1120
+ },
1121
+ {
1122
+ "epoch": 46.21,
1123
+ "learning_rate": 0.001,
1124
+ "loss": 1.524,
1125
+ "step": 930
1126
+ },
1127
+ {
1128
+ "epoch": 46.46,
1129
+ "learning_rate": 0.001,
1130
+ "loss": 1.4635,
1131
+ "step": 935
1132
+ },
1133
+ {
1134
+ "epoch": 46.71,
1135
+ "learning_rate": 0.001,
1136
+ "loss": 1.6017,
1137
+ "step": 940
1138
+ },
1139
+ {
1140
+ "epoch": 46.96,
1141
+ "learning_rate": 0.001,
1142
+ "loss": 1.5213,
1143
+ "step": 945
1144
+ },
1145
+ {
1146
+ "epoch": 47.2,
1147
+ "learning_rate": 0.001,
1148
+ "loss": 1.542,
1149
+ "step": 950
1150
+ },
1151
+ {
1152
+ "epoch": 47.45,
1153
+ "learning_rate": 0.001,
1154
+ "loss": 1.4951,
1155
+ "step": 955
1156
+ },
1157
+ {
1158
+ "epoch": 47.7,
1159
+ "learning_rate": 0.001,
1160
+ "loss": 1.4742,
1161
+ "step": 960
1162
+ },
1163
+ {
1164
+ "epoch": 47.95,
1165
+ "learning_rate": 0.001,
1166
+ "loss": 1.6,
1167
+ "step": 965
1168
+ },
1169
+ {
1170
+ "epoch": 48.2,
1171
+ "learning_rate": 0.001,
1172
+ "loss": 1.5234,
1173
+ "step": 970
1174
+ },
1175
+ {
1176
+ "epoch": 48.45,
1177
+ "learning_rate": 0.001,
1178
+ "loss": 1.4522,
1179
+ "step": 975
1180
+ },
1181
+ {
1182
+ "epoch": 48.7,
1183
+ "learning_rate": 0.001,
1184
+ "loss": 1.5727,
1185
+ "step": 980
1186
+ },
1187
+ {
1188
+ "epoch": 48.94,
1189
+ "learning_rate": 0.001,
1190
+ "loss": 1.5176,
1191
+ "step": 985
1192
+ },
1193
+ {
1194
+ "epoch": 49.19,
1195
+ "learning_rate": 0.001,
1196
+ "loss": 1.4455,
1197
+ "step": 990
1198
+ },
1199
+ {
1200
+ "epoch": 49.44,
1201
+ "learning_rate": 0.001,
1202
+ "loss": 1.4791,
1203
+ "step": 995
1204
+ },
1205
+ {
1206
+ "epoch": 49.69,
1207
+ "learning_rate": 0.001,
1208
+ "loss": 1.5225,
1209
+ "step": 1000
1210
+ }
1211
+ ],
1212
+ "logging_steps": 5,
1213
+ "max_steps": 1000,
1214
+ "num_train_epochs": 50,
1215
+ "save_steps": 1000,
1216
+ "total_flos": 7299072000000000.0,
1217
+ "trial_name": null,
1218
+ "trial_params": null
1219
+ }
checkpoint-1000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:45e7c6ff0e4648558db5c97effa6449dce181570da721cea934d3072eed3b052
3
+ size 4027
config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "./output",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "bos_token_id": 1,
7
+ "eos_token_id": 2,
8
+ "hidden_act": "silu",
9
+ "hidden_size": 256,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 512,
12
+ "max_position_embeddings": 8192,
13
+ "model_type": "llama",
14
+ "num_attention_heads": 4,
15
+ "num_hidden_layers": 2,
16
+ "num_key_value_heads": 4,
17
+ "pretraining_tp": 1,
18
+ "rms_norm_eps": 1e-05,
19
+ "rope_scaling": null,
20
+ "rope_theta": 10000.0,
21
+ "tie_word_embeddings": false,
22
+ "torch_dtype": "float32",
23
+ "transformers_version": "4.34.0.dev0",
24
+ "use_cache": true,
25
+ "vocab_size": 32000
26
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "transformers_version": "4.34.0.dev0"
6
+ }
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:875e0f9a728d0301007800091ac050f0221e86864538420278cd30c6162a297c
3
+ size 70790896
special_tokens_map.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "eos_token": "</s>",
4
+ "unk_token": "<unk>"
5
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
tokenizer_config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<unk>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<s>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ }
27
+ },
28
+ "additional_special_tokens": [],
29
+ "bos_token": "<s>",
30
+ "clean_up_tokenization_spaces": false,
31
+ "eos_token": "</s>",
32
+ "model_max_length": 8192,
33
+ "pad_token": null,
34
+ "sp_model_kwargs": {},
35
+ "tokenizer_class": "LlamaTokenizer",
36
+ "unk_token": "<unk>",
37
+ "use_default_system_prompt": true
38
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 1.0,
3
+ "train_loss": 4.884670708277454,
4
+ "train_runtime": 5501.4397,
5
+ "train_samples": 37518,
6
+ "train_samples_per_second": 6.82,
7
+ "train_steps_per_second": 0.027
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.9962151500613039,
5
+ "eval_steps": 500,
6
+ "global_step": 146,
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": 0.001,
14
+ "loss": 8.6154,
15
+ "step": 5
16
+ },
17
+ {
18
+ "epoch": 0.07,
19
+ "learning_rate": 0.001,
20
+ "loss": 6.6267,
21
+ "step": 10
22
+ },
23
+ {
24
+ "epoch": 0.1,
25
+ "learning_rate": 0.001,
26
+ "loss": 5.6959,
27
+ "step": 15
28
+ },
29
+ {
30
+ "epoch": 0.14,
31
+ "learning_rate": 0.001,
32
+ "loss": 5.3255,
33
+ "step": 20
34
+ },
35
+ {
36
+ "epoch": 0.17,
37
+ "learning_rate": 0.001,
38
+ "loss": 5.223,
39
+ "step": 25
40
+ },
41
+ {
42
+ "epoch": 0.2,
43
+ "learning_rate": 0.001,
44
+ "loss": 5.1121,
45
+ "step": 30
46
+ },
47
+ {
48
+ "epoch": 0.24,
49
+ "learning_rate": 0.001,
50
+ "loss": 5.0313,
51
+ "step": 35
52
+ },
53
+ {
54
+ "epoch": 0.27,
55
+ "learning_rate": 0.001,
56
+ "loss": 4.955,
57
+ "step": 40
58
+ },
59
+ {
60
+ "epoch": 0.31,
61
+ "learning_rate": 0.001,
62
+ "loss": 4.8758,
63
+ "step": 45
64
+ },
65
+ {
66
+ "epoch": 0.34,
67
+ "learning_rate": 0.001,
68
+ "loss": 4.8061,
69
+ "step": 50
70
+ },
71
+ {
72
+ "epoch": 0.38,
73
+ "learning_rate": 0.001,
74
+ "loss": 4.8037,
75
+ "step": 55
76
+ },
77
+ {
78
+ "epoch": 0.41,
79
+ "learning_rate": 0.001,
80
+ "loss": 4.7292,
81
+ "step": 60
82
+ },
83
+ {
84
+ "epoch": 0.44,
85
+ "learning_rate": 0.001,
86
+ "loss": 4.6936,
87
+ "step": 65
88
+ },
89
+ {
90
+ "epoch": 0.48,
91
+ "learning_rate": 0.001,
92
+ "loss": 4.6386,
93
+ "step": 70
94
+ },
95
+ {
96
+ "epoch": 0.51,
97
+ "learning_rate": 0.001,
98
+ "loss": 4.608,
99
+ "step": 75
100
+ },
101
+ {
102
+ "epoch": 0.55,
103
+ "learning_rate": 0.001,
104
+ "loss": 4.5775,
105
+ "step": 80
106
+ },
107
+ {
108
+ "epoch": 0.58,
109
+ "learning_rate": 0.001,
110
+ "loss": 4.5337,
111
+ "step": 85
112
+ },
113
+ {
114
+ "epoch": 0.61,
115
+ "learning_rate": 0.001,
116
+ "loss": 4.5108,
117
+ "step": 90
118
+ },
119
+ {
120
+ "epoch": 0.65,
121
+ "learning_rate": 0.001,
122
+ "loss": 4.5041,
123
+ "step": 95
124
+ },
125
+ {
126
+ "epoch": 0.68,
127
+ "learning_rate": 0.001,
128
+ "loss": 4.474,
129
+ "step": 100
130
+ },
131
+ {
132
+ "epoch": 0.72,
133
+ "learning_rate": 0.001,
134
+ "loss": 4.4469,
135
+ "step": 105
136
+ },
137
+ {
138
+ "epoch": 0.75,
139
+ "learning_rate": 0.001,
140
+ "loss": 4.4356,
141
+ "step": 110
142
+ },
143
+ {
144
+ "epoch": 0.78,
145
+ "learning_rate": 0.001,
146
+ "loss": 4.405,
147
+ "step": 115
148
+ },
149
+ {
150
+ "epoch": 0.82,
151
+ "learning_rate": 0.001,
152
+ "loss": 4.4047,
153
+ "step": 120
154
+ },
155
+ {
156
+ "epoch": 0.85,
157
+ "learning_rate": 0.001,
158
+ "loss": 4.3796,
159
+ "step": 125
160
+ },
161
+ {
162
+ "epoch": 0.89,
163
+ "learning_rate": 0.001,
164
+ "loss": 4.3652,
165
+ "step": 130
166
+ },
167
+ {
168
+ "epoch": 0.92,
169
+ "learning_rate": 0.001,
170
+ "loss": 4.3162,
171
+ "step": 135
172
+ },
173
+ {
174
+ "epoch": 0.96,
175
+ "learning_rate": 0.001,
176
+ "loss": 4.3448,
177
+ "step": 140
178
+ },
179
+ {
180
+ "epoch": 0.99,
181
+ "learning_rate": 0.001,
182
+ "loss": 4.329,
183
+ "step": 145
184
+ },
185
+ {
186
+ "epoch": 1.0,
187
+ "step": 146,
188
+ "total_flos": 1.7050632192e+16,
189
+ "train_loss": 4.884670708277454,
190
+ "train_runtime": 5501.4397,
191
+ "train_samples_per_second": 6.82,
192
+ "train_steps_per_second": 0.027
193
+ }
194
+ ],
195
+ "logging_steps": 5,
196
+ "max_steps": 146,
197
+ "num_train_epochs": 1,
198
+ "save_steps": 1000,
199
+ "total_flos": 1.7050632192e+16,
200
+ "trial_name": null,
201
+ "trial_params": null
202
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8306e6f1a27ab436c9dca647ecb1956a506448b5d1b0075a9575e3cb6884840
3
+ size 4027