Hugging Face's logo

ShashiVish
/
llama-7-int4-r512-cover-letter

PEFT
TensorBoard
Model card Files Metrics Community
ShashiVish commited on
Commit
2310e20
·
1 Parent(s): 1cb5bb4

Upload folder using huggingface_hub

Browse files
Files changed (19) hide show
  1. README.md +34 -0
  2. adapter_config.json +21 -0
  3. adapter_model.bin +3 -0
  4. checkpoint-400/README.md +34 -0
  5. checkpoint-400/adapter_config.json +21 -0
  6. checkpoint-400/adapter_model.bin +3 -0
  7. checkpoint-400/optimizer.pt +3 -0
  8. checkpoint-400/rng_state.pth +3 -0
  9. checkpoint-400/scheduler.pt +3 -0
  10. checkpoint-400/special_tokens_map.json +24 -0
  11. checkpoint-400/tokenizer.json +0 -0
  12. checkpoint-400/tokenizer_config.json +38 -0
  13. checkpoint-400/trainer_state.json +499 -0
  14. checkpoint-400/training_args.bin +3 -0
  15. runs/Oct24_04-26-28_203f97f492a6/events.out.tfevents.1698121638.203f97f492a6.410.0 +3 -0
  16. special_tokens_map.json +24 -0
  17. tokenizer.json +0 -0
  18. tokenizer_config.json +38 -0
  19. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ ---
4
+ ## Training procedure
5
+
6
+
7
+ The following `bitsandbytes` quantization config was used during training:
8
+ - quant_method: bitsandbytes
9
+ - load_in_8bit: False
10
+ - load_in_4bit: True
11
+ - llm_int8_threshold: 6.0
12
+ - llm_int8_skip_modules: None
13
+ - llm_int8_enable_fp32_cpu_offload: False
14
+ - llm_int8_has_fp16_weight: False
15
+ - bnb_4bit_quant_type: nf4
16
+ - bnb_4bit_use_double_quant: False
17
+ - bnb_4bit_compute_dtype: float16
18
+
19
+ The following `bitsandbytes` quantization config was used during training:
20
+ - quant_method: bitsandbytes
21
+ - load_in_8bit: False
22
+ - load_in_4bit: True
23
+ - llm_int8_threshold: 6.0
24
+ - llm_int8_skip_modules: None
25
+ - llm_int8_enable_fp32_cpu_offload: False
26
+ - llm_int8_has_fp16_weight: False
27
+ - bnb_4bit_quant_type: nf4
28
+ - bnb_4bit_use_double_quant: False
29
+ - bnb_4bit_compute_dtype: float16
30
+ ### Framework versions
31
+
32
+ - PEFT 0.5.0
33
+
34
+ - PEFT 0.5.0
adapter_config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "auto_mapping": null,
3
+ "base_model_name_or_path": null,
4
+ "bias": "none",
5
+ "fan_in_fan_out": false,
6
+ "inference_mode": true,
7
+ "init_lora_weights": true,
8
+ "layers_pattern": null,
9
+ "layers_to_transform": null,
10
+ "lora_alpha": 16,
11
+ "lora_dropout": 0.1,
12
+ "modules_to_save": null,
13
+ "peft_type": "LORA",
14
+ "r": 512,
15
+ "revision": null,
16
+ "target_modules": [
17
+ "q_proj",
18
+ "v_proj"
19
+ ],
20
+ "task_type": "CAUSAL_LM"
21
+ }
adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:50ea6fda97fbf80f5948067d51016c9395e6725c5dfe095df6a016e313b04331
3
+ size 1073797194
checkpoint-400/README.md ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ ---
4
+ ## Training procedure
5
+
6
+
7
+ The following `bitsandbytes` quantization config was used during training:
8
+ - quant_method: bitsandbytes
9
+ - load_in_8bit: False
10
+ - load_in_4bit: True
11
+ - llm_int8_threshold: 6.0
12
+ - llm_int8_skip_modules: None
13
+ - llm_int8_enable_fp32_cpu_offload: False
14
+ - llm_int8_has_fp16_weight: False
15
+ - bnb_4bit_quant_type: nf4
16
+ - bnb_4bit_use_double_quant: False
17
+ - bnb_4bit_compute_dtype: float16
18
+
19
+ The following `bitsandbytes` quantization config was used during training:
20
+ - quant_method: bitsandbytes
21
+ - load_in_8bit: False
22
+ - load_in_4bit: True
23
+ - llm_int8_threshold: 6.0
24
+ - llm_int8_skip_modules: None
25
+ - llm_int8_enable_fp32_cpu_offload: False
26
+ - llm_int8_has_fp16_weight: False
27
+ - bnb_4bit_quant_type: nf4
28
+ - bnb_4bit_use_double_quant: False
29
+ - bnb_4bit_compute_dtype: float16
30
+ ### Framework versions
31
+
32
+ - PEFT 0.5.0
33
+
34
+ - PEFT 0.5.0
checkpoint-400/adapter_config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "auto_mapping": null,
3
+ "base_model_name_or_path": null,
4
+ "bias": "none",
5
+ "fan_in_fan_out": false,
6
+ "inference_mode": true,
7
+ "init_lora_weights": true,
8
+ "layers_pattern": null,
9
+ "layers_to_transform": null,
10
+ "lora_alpha": 16,
11
+ "lora_dropout": 0.1,
12
+ "modules_to_save": null,
13
+ "peft_type": "LORA",
14
+ "r": 512,
15
+ "revision": null,
16
+ "target_modules": [
17
+ "q_proj",
18
+ "v_proj"
19
+ ],
20
+ "task_type": "CAUSAL_LM"
21
+ }
checkpoint-400/adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:50ea6fda97fbf80f5948067d51016c9395e6725c5dfe095df6a016e313b04331
3
+ size 1073797194
checkpoint-400/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c4115cc293dd9ba3d9c472bc6150905ed6cc54f8c2dfeffa987224cdfa2f297
3
+ size 2147563578
checkpoint-400/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:210e63fcffc5d797c86e674f3de723687a4e6517907b4134f8d7c75241ae5a2f
3
+ size 14244
checkpoint-400/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a3dedf52aaea6588501a76bbcc0db7c74d91e0049f19cb86f239096b664186d
3
+ size 1064
checkpoint-400/special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "</s>",
17
+ "unk_token": {
18
+ "content": "<unk>",
19
+ "lstrip": false,
20
+ "normalized": true,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
checkpoint-400/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-400/tokenizer_config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<unk>",
5
+ "lstrip": false,
6
+ "normalized": true,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<s>",
13
+ "lstrip": false,
14
+ "normalized": true,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": true,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ }
27
+ },
28
+ "bos_token": "<s>",
29
+ "clean_up_tokenization_spaces": false,
30
+ "eos_token": "</s>",
31
+ "legacy": false,
32
+ "model_max_length": 1000000000000000019884624838656,
33
+ "pad_token": "</s>",
34
+ "sp_model_kwargs": {},
35
+ "tokenizer_class": "LlamaTokenizer",
36
+ "unk_token": "<unk>",
37
+ "use_default_system_prompt": true
38
+ }
checkpoint-400/trainer_state.json ADDED
@@ -0,0 +1,499 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 3.9215686274509802,
5
+ "eval_steps": 500,
6
+ "global_step": 400,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.05,
13
+ "learning_rate": 0.0002,
14
+ "loss": 1.5924,
15
+ "step": 5
16
+ },
17
+ {
18
+ "epoch": 0.1,
19
+ "learning_rate": 0.0002,
20
+ "loss": 1.4347,
21
+ "step": 10
22
+ },
23
+ {
24
+ "epoch": 0.15,
25
+ "learning_rate": 0.0002,
26
+ "loss": 1.2385,
27
+ "step": 15
28
+ },
29
+ {
30
+ "epoch": 0.2,
31
+ "learning_rate": 0.0002,
32
+ "loss": 1.0533,
33
+ "step": 20
34
+ },
35
+ {
36
+ "epoch": 0.25,
37
+ "learning_rate": 0.0002,
38
+ "loss": 0.964,
39
+ "step": 25
40
+ },
41
+ {
42
+ "epoch": 0.29,
43
+ "learning_rate": 0.0002,
44
+ "loss": 0.9148,
45
+ "step": 30
46
+ },
47
+ {
48
+ "epoch": 0.34,
49
+ "learning_rate": 0.0002,
50
+ "loss": 0.8783,
51
+ "step": 35
52
+ },
53
+ {
54
+ "epoch": 0.39,
55
+ "learning_rate": 0.0002,
56
+ "loss": 0.9033,
57
+ "step": 40
58
+ },
59
+ {
60
+ "epoch": 0.44,
61
+ "learning_rate": 0.0002,
62
+ "loss": 0.8137,
63
+ "step": 45
64
+ },
65
+ {
66
+ "epoch": 0.49,
67
+ "learning_rate": 0.0002,
68
+ "loss": 0.8156,
69
+ "step": 50
70
+ },
71
+ {
72
+ "epoch": 0.54,
73
+ "learning_rate": 0.0002,
74
+ "loss": 0.8076,
75
+ "step": 55
76
+ },
77
+ {
78
+ "epoch": 0.59,
79
+ "learning_rate": 0.0002,
80
+ "loss": 0.6955,
81
+ "step": 60
82
+ },
83
+ {
84
+ "epoch": 0.64,
85
+ "learning_rate": 0.0002,
86
+ "loss": 0.7675,
87
+ "step": 65
88
+ },
89
+ {
90
+ "epoch": 0.69,
91
+ "learning_rate": 0.0002,
92
+ "loss": 0.7195,
93
+ "step": 70
94
+ },
95
+ {
96
+ "epoch": 0.74,
97
+ "learning_rate": 0.0002,
98
+ "loss": 0.6537,
99
+ "step": 75
100
+ },
101
+ {
102
+ "epoch": 0.78,
103
+ "learning_rate": 0.0002,
104
+ "loss": 0.7573,
105
+ "step": 80
106
+ },
107
+ {
108
+ "epoch": 0.83,
109
+ "learning_rate": 0.0002,
110
+ "loss": 0.7327,
111
+ "step": 85
112
+ },
113
+ {
114
+ "epoch": 0.88,
115
+ "learning_rate": 0.0002,
116
+ "loss": 0.6761,
117
+ "step": 90
118
+ },
119
+ {
120
+ "epoch": 0.93,
121
+ "learning_rate": 0.0002,
122
+ "loss": 0.6961,
123
+ "step": 95
124
+ },
125
+ {
126
+ "epoch": 0.98,
127
+ "learning_rate": 0.0002,
128
+ "loss": 0.7175,
129
+ "step": 100
130
+ },
131
+ {
132
+ "epoch": 1.03,
133
+ "learning_rate": 0.0002,
134
+ "loss": 0.7002,
135
+ "step": 105
136
+ },
137
+ {
138
+ "epoch": 1.08,
139
+ "learning_rate": 0.0002,
140
+ "loss": 0.6312,
141
+ "step": 110
142
+ },
143
+ {
144
+ "epoch": 1.13,
145
+ "learning_rate": 0.0002,
146
+ "loss": 0.6407,
147
+ "step": 115
148
+ },
149
+ {
150
+ "epoch": 1.18,
151
+ "learning_rate": 0.0002,
152
+ "loss": 0.6514,
153
+ "step": 120
154
+ },
155
+ {
156
+ "epoch": 1.23,
157
+ "learning_rate": 0.0002,
158
+ "loss": 0.6612,
159
+ "step": 125
160
+ },
161
+ {
162
+ "epoch": 1.27,
163
+ "learning_rate": 0.0002,
164
+ "loss": 0.6577,
165
+ "step": 130
166
+ },
167
+ {
168
+ "epoch": 1.32,
169
+ "learning_rate": 0.0002,
170
+ "loss": 0.6884,
171
+ "step": 135
172
+ },
173
+ {
174
+ "epoch": 1.37,
175
+ "learning_rate": 0.0002,
176
+ "loss": 0.6752,
177
+ "step": 140
178
+ },
179
+ {
180
+ "epoch": 1.42,
181
+ "learning_rate": 0.0002,
182
+ "loss": 0.7016,
183
+ "step": 145
184
+ },
185
+ {
186
+ "epoch": 1.47,
187
+ "learning_rate": 0.0002,
188
+ "loss": 0.6581,
189
+ "step": 150
190
+ },
191
+ {
192
+ "epoch": 1.52,
193
+ "learning_rate": 0.0002,
194
+ "loss": 0.686,
195
+ "step": 155
196
+ },
197
+ {
198
+ "epoch": 1.57,
199
+ "learning_rate": 0.0002,
200
+ "loss": 0.6226,
201
+ "step": 160
202
+ },
203
+ {
204
+ "epoch": 1.62,
205
+ "learning_rate": 0.0002,
206
+ "loss": 0.6379,
207
+ "step": 165
208
+ },
209
+ {
210
+ "epoch": 1.67,
211
+ "learning_rate": 0.0002,
212
+ "loss": 0.6378,
213
+ "step": 170
214
+ },
215
+ {
216
+ "epoch": 1.72,
217
+ "learning_rate": 0.0002,
218
+ "loss": 0.6072,
219
+ "step": 175
220
+ },
221
+ {
222
+ "epoch": 1.76,
223
+ "learning_rate": 0.0002,
224
+ "loss": 0.6809,
225
+ "step": 180
226
+ },
227
+ {
228
+ "epoch": 1.81,
229
+ "learning_rate": 0.0002,
230
+ "loss": 0.6157,
231
+ "step": 185
232
+ },
233
+ {
234
+ "epoch": 1.86,
235
+ "learning_rate": 0.0002,
236
+ "loss": 0.6624,
237
+ "step": 190
238
+ },
239
+ {
240
+ "epoch": 1.91,
241
+ "learning_rate": 0.0002,
242
+ "loss": 0.6259,
243
+ "step": 195
244
+ },
245
+ {
246
+ "epoch": 1.96,
247
+ "learning_rate": 0.0002,
248
+ "loss": 0.6699,
249
+ "step": 200
250
+ },
251
+ {
252
+ "epoch": 2.01,
253
+ "learning_rate": 0.0002,
254
+ "loss": 0.6384,
255
+ "step": 205
256
+ },
257
+ {
258
+ "epoch": 2.06,
259
+ "learning_rate": 0.0002,
260
+ "loss": 0.5782,
261
+ "step": 210
262
+ },
263
+ {
264
+ "epoch": 2.11,
265
+ "learning_rate": 0.0002,
266
+ "loss": 0.5969,
267
+ "step": 215
268
+ },
269
+ {
270
+ "epoch": 2.16,
271
+ "learning_rate": 0.0002,
272
+ "loss": 0.6542,
273
+ "step": 220
274
+ },
275
+ {
276
+ "epoch": 2.21,
277
+ "learning_rate": 0.0002,
278
+ "loss": 0.6709,
279
+ "step": 225
280
+ },
281
+ {
282
+ "epoch": 2.25,
283
+ "learning_rate": 0.0002,
284
+ "loss": 0.6428,
285
+ "step": 230
286
+ },
287
+ {
288
+ "epoch": 2.3,
289
+ "learning_rate": 0.0002,
290
+ "loss": 0.6348,
291
+ "step": 235
292
+ },
293
+ {
294
+ "epoch": 2.35,
295
+ "learning_rate": 0.0002,
296
+ "loss": 0.7218,
297
+ "step": 240
298
+ },
299
+ {
300
+ "epoch": 2.4,
301
+ "learning_rate": 0.0002,
302
+ "loss": 0.6717,
303
+ "step": 245
304
+ },
305
+ {
306
+ "epoch": 2.45,
307
+ "learning_rate": 0.0002,
308
+ "loss": 0.5902,
309
+ "step": 250
310
+ },
311
+ {
312
+ "epoch": 2.5,
313
+ "learning_rate": 0.0002,
314
+ "loss": 0.5442,
315
+ "step": 255
316
+ },
317
+ {
318
+ "epoch": 2.55,
319
+ "learning_rate": 0.0002,
320
+ "loss": 0.6592,
321
+ "step": 260
322
+ },
323
+ {
324
+ "epoch": 2.6,
325
+ "learning_rate": 0.0002,
326
+ "loss": 0.6402,
327
+ "step": 265
328
+ },
329
+ {
330
+ "epoch": 2.65,
331
+ "learning_rate": 0.0002,
332
+ "loss": 0.6211,
333
+ "step": 270
334
+ },
335
+ {
336
+ "epoch": 2.7,
337
+ "learning_rate": 0.0002,
338
+ "loss": 0.5764,
339
+ "step": 275
340
+ },
341
+ {
342
+ "epoch": 2.75,
343
+ "learning_rate": 0.0002,
344
+ "loss": 0.5981,
345
+ "step": 280
346
+ },
347
+ {
348
+ "epoch": 2.79,
349
+ "learning_rate": 0.0002,
350
+ "loss": 0.6265,
351
+ "step": 285
352
+ },
353
+ {
354
+ "epoch": 2.84,
355
+ "learning_rate": 0.0002,
356
+ "loss": 0.5404,
357
+ "step": 290
358
+ },
359
+ {
360
+ "epoch": 2.89,
361
+ "learning_rate": 0.0002,
362
+ "loss": 0.6331,
363
+ "step": 295
364
+ },
365
+ {
366
+ "epoch": 2.94,
367
+ "learning_rate": 0.0002,
368
+ "loss": 0.5695,
369
+ "step": 300
370
+ },
371
+ {
372
+ "epoch": 2.99,
373
+ "learning_rate": 0.0002,
374
+ "loss": 0.5621,
375
+ "step": 305
376
+ },
377
+ {
378
+ "epoch": 3.04,
379
+ "learning_rate": 0.0002,
380
+ "loss": 0.5629,
381
+ "step": 310
382
+ },
383
+ {
384
+ "epoch": 3.09,
385
+ "learning_rate": 0.0002,
386
+ "loss": 0.6017,
387
+ "step": 315
388
+ },
389
+ {
390
+ "epoch": 3.14,
391
+ "learning_rate": 0.0002,
392
+ "loss": 0.6198,
393
+ "step": 320
394
+ },
395
+ {
396
+ "epoch": 3.19,
397
+ "learning_rate": 0.0002,
398
+ "loss": 0.591,
399
+ "step": 325
400
+ },
401
+ {
402
+ "epoch": 3.24,
403
+ "learning_rate": 0.0002,
404
+ "loss": 0.5915,
405
+ "step": 330
406
+ },
407
+ {
408
+ "epoch": 3.28,
409
+ "learning_rate": 0.0002,
410
+ "loss": 0.5562,
411
+ "step": 335
412
+ },
413
+ {
414
+ "epoch": 3.33,
415
+ "learning_rate": 0.0002,
416
+ "loss": 0.599,
417
+ "step": 340
418
+ },
419
+ {
420
+ "epoch": 3.38,
421
+ "learning_rate": 0.0002,
422
+ "loss": 0.613,
423
+ "step": 345
424
+ },
425
+ {
426
+ "epoch": 3.43,
427
+ "learning_rate": 0.0002,
428
+ "loss": 0.5082,
429
+ "step": 350
430
+ },
431
+ {
432
+ "epoch": 3.48,
433
+ "learning_rate": 0.0002,
434
+ "loss": 0.562,
435
+ "step": 355
436
+ },
437
+ {
438
+ "epoch": 3.53,
439
+ "learning_rate": 0.0002,
440
+ "loss": 0.6301,
441
+ "step": 360
442
+ },
443
+ {
444
+ "epoch": 3.58,
445
+ "learning_rate": 0.0002,
446
+ "loss": 0.5913,
447
+ "step": 365
448
+ },
449
+ {
450
+ "epoch": 3.63,
451
+ "learning_rate": 0.0002,
452
+ "loss": 0.5582,
453
+ "step": 370
454
+ },
455
+ {
456
+ "epoch": 3.68,
457
+ "learning_rate": 0.0002,
458
+ "loss": 0.587,
459
+ "step": 375
460
+ },
461
+ {
462
+ "epoch": 3.73,
463
+ "learning_rate": 0.0002,
464
+ "loss": 0.5286,
465
+ "step": 380
466
+ },
467
+ {
468
+ "epoch": 3.77,
469
+ "learning_rate": 0.0002,
470
+ "loss": 0.5204,
471
+ "step": 385
472
+ },
473
+ {
474
+ "epoch": 3.82,
475
+ "learning_rate": 0.0002,
476
+ "loss": 0.5629,
477
+ "step": 390
478
+ },
479
+ {
480
+ "epoch": 3.87,
481
+ "learning_rate": 0.0002,
482
+ "loss": 0.4857,
483
+ "step": 395
484
+ },
485
+ {
486
+ "epoch": 3.92,
487
+ "learning_rate": 0.0002,
488
+ "loss": 0.5976,
489
+ "step": 400
490
+ }
491
+ ],
492
+ "logging_steps": 5,
493
+ "max_steps": 400,
494
+ "num_train_epochs": 4,
495
+ "save_steps": 500,
496
+ "total_flos": 6.75916585893888e+16,
497
+ "trial_name": null,
498
+ "trial_params": null
499
+ }
checkpoint-400/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87fa502bde7007fa237c33e2877eddedb52400e91ff8d6221970d2a24ae184ff
3
+ size 4536
runs/Oct24_04-26-28_203f97f492a6/events.out.tfevents.1698121638.203f97f492a6.410.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:00d5c1ec101987b8091cda5c821b79214bbf935de6f8e63fa2cbd422484286fe
3
+ size 17428
special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "</s>",
17
+ "unk_token": {
18
+ "content": "<unk>",
19
+ "lstrip": false,
20
+ "normalized": true,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<unk>",
5
+ "lstrip": false,
6
+ "normalized": true,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<s>",
13
+ "lstrip": false,
14
+ "normalized": true,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": true,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ }
27
+ },
28
+ "bos_token": "<s>",
29
+ "clean_up_tokenization_spaces": false,
30
+ "eos_token": "</s>",
31
+ "legacy": false,
32
+ "model_max_length": 1000000000000000019884624838656,
33
+ "pad_token": "</s>",
34
+ "sp_model_kwargs": {},
35
+ "tokenizer_class": "LlamaTokenizer",
36
+ "unk_token": "<unk>",
37
+ "use_default_system_prompt": true
38
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87fa502bde7007fa237c33e2877eddedb52400e91ff8d6221970d2a24ae184ff
3
+ size 4536