tyzhu commited on
Commit
6ce3ba5
1 Parent(s): ecff266

Training in progress, epoch 9, checkpoint

Browse files
checkpoint-2250/README.md ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ ---
4
+ ## Training procedure
5
+
6
+ ### Framework versions
7
+
8
+
9
+ - PEFT 0.5.0
checkpoint-2250/adapter_config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "auto_mapping": null,
3
+ "base_model_name_or_path": "Qwen/Qwen1.5-4B",
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": 0.05,
12
+ "modules_to_save": null,
13
+ "peft_type": "LORA",
14
+ "r": 16,
15
+ "revision": null,
16
+ "target_modules": [
17
+ "q_proj",
18
+ "k_proj",
19
+ "v_proj",
20
+ "down_proj",
21
+ "gate_proj",
22
+ "up_proj"
23
+ ],
24
+ "task_type": "CAUSAL_LM"
25
+ }
checkpoint-2250/adapter_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:32558df6740529cae070140a31e5dfae3be1fd0f9cd10efb9f5190cd7b645485
3
+ size 112130416
checkpoint-2250/added_tokens.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "<|endoftext|>": 151643,
3
+ "<|im_end|>": 151645,
4
+ "<|im_start|>": 151644
5
+ }
checkpoint-2250/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-2250/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:78fe3202be230f3a827c44be9c321e03821488d1d6425c1beb225ff9bdf26c0f
3
+ size 224537202
checkpoint-2250/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:10ad9d3c8da575eab4dce1d0fd27faae8881ed2f8b7d824ea91554972be14202
3
+ size 15024
checkpoint-2250/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc2e1e7c7596fa8ac9a427794b880699469ff72097fa6a7045634b6b2a1944eb
3
+ size 15024
checkpoint-2250/rng_state_2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b5c3866d0d8c1601c3bbe0f09e3030991510b4b05cd9d8334e676828f55455e
3
+ size 15024
checkpoint-2250/rng_state_3.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bcbaf3716a263b8a7d4f7d20c10c643931b00647e2ea4628fb6fa5b762283d73
3
+ size 15024
checkpoint-2250/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ace85184e5181c091acd969e0e6dc4555c0508b7bb923fbe08a7168f85e67169
3
+ size 1064
checkpoint-2250/special_tokens_map.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>"
5
+ ],
6
+ "eos_token": {
7
+ "content": "<|endoftext|>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false
12
+ },
13
+ "pad_token": "<|endoftext|>"
14
+ }
checkpoint-2250/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-2250/tokenizer_config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "151643": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "151644": {
13
+ "content": "<|im_start|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "151645": {
21
+ "content": "<|im_end|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ }
28
+ },
29
+ "additional_special_tokens": [
30
+ "<|im_start|>",
31
+ "<|im_end|>"
32
+ ],
33
+ "bos_token": null,
34
+ "chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
35
+ "clean_up_tokenization_spaces": false,
36
+ "eos_token": "<|endoftext|>",
37
+ "errors": "replace",
38
+ "model_max_length": 32768,
39
+ "pad_token": "<|endoftext|>",
40
+ "split_special_tokens": false,
41
+ "tokenizer_class": "Qwen2Tokenizer",
42
+ "unk_token": null
43
+ }
checkpoint-2250/trainer_state.json ADDED
@@ -0,0 +1,322 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 9.0,
5
+ "eval_steps": 500,
6
+ "global_step": 2250,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.4,
13
+ "grad_norm": 0.5897082090377808,
14
+ "learning_rate": 0.0001,
15
+ "loss": 2.3566,
16
+ "step": 100
17
+ },
18
+ {
19
+ "epoch": 0.8,
20
+ "grad_norm": 0.5390245914459229,
21
+ "learning_rate": 0.0001,
22
+ "loss": 2.2503,
23
+ "step": 200
24
+ },
25
+ {
26
+ "epoch": 1.0,
27
+ "eval_accuracy": 0.5155873015873016,
28
+ "eval_loss": 2.3237216472625732,
29
+ "eval_runtime": 6.3164,
30
+ "eval_samples_per_second": 79.159,
31
+ "eval_steps_per_second": 9.974,
32
+ "step": 250
33
+ },
34
+ {
35
+ "epoch": 1.0,
36
+ "eval_exact_match": 17.2,
37
+ "eval_f1": 25.586581359816655,
38
+ "step": 250
39
+ },
40
+ {
41
+ "epoch": 1.2,
42
+ "grad_norm": 0.7468857169151306,
43
+ "learning_rate": 0.0001,
44
+ "loss": 2.1798,
45
+ "step": 300
46
+ },
47
+ {
48
+ "epoch": 1.6,
49
+ "grad_norm": 0.9109599590301514,
50
+ "learning_rate": 0.0001,
51
+ "loss": 2.1094,
52
+ "step": 400
53
+ },
54
+ {
55
+ "epoch": 2.0,
56
+ "grad_norm": 0.8458774089813232,
57
+ "learning_rate": 0.0001,
58
+ "loss": 2.087,
59
+ "step": 500
60
+ },
61
+ {
62
+ "epoch": 2.0,
63
+ "eval_accuracy": 0.5163809523809524,
64
+ "eval_loss": 2.3309242725372314,
65
+ "eval_runtime": 5.1896,
66
+ "eval_samples_per_second": 96.347,
67
+ "eval_steps_per_second": 12.14,
68
+ "step": 500
69
+ },
70
+ {
71
+ "epoch": 2.0,
72
+ "eval_exact_match": 18.6,
73
+ "eval_f1": 26.043196248196264,
74
+ "step": 500
75
+ },
76
+ {
77
+ "epoch": 2.4,
78
+ "grad_norm": 1.171212077140808,
79
+ "learning_rate": 0.0001,
80
+ "loss": 1.8413,
81
+ "step": 600
82
+ },
83
+ {
84
+ "epoch": 2.8,
85
+ "grad_norm": 1.1294909715652466,
86
+ "learning_rate": 0.0001,
87
+ "loss": 1.849,
88
+ "step": 700
89
+ },
90
+ {
91
+ "epoch": 3.0,
92
+ "eval_accuracy": 0.5144761904761905,
93
+ "eval_loss": 2.401942253112793,
94
+ "eval_runtime": 5.5775,
95
+ "eval_samples_per_second": 89.646,
96
+ "eval_steps_per_second": 11.295,
97
+ "step": 750
98
+ },
99
+ {
100
+ "epoch": 3.0,
101
+ "eval_exact_match": 18.4,
102
+ "eval_f1": 26.966370002546494,
103
+ "step": 750
104
+ },
105
+ {
106
+ "epoch": 3.2,
107
+ "grad_norm": 1.5013824701309204,
108
+ "learning_rate": 0.0001,
109
+ "loss": 1.7322,
110
+ "step": 800
111
+ },
112
+ {
113
+ "epoch": 3.6,
114
+ "grad_norm": 1.4516321420669556,
115
+ "learning_rate": 0.0001,
116
+ "loss": 1.5908,
117
+ "step": 900
118
+ },
119
+ {
120
+ "epoch": 4.0,
121
+ "grad_norm": 1.6037466526031494,
122
+ "learning_rate": 0.0001,
123
+ "loss": 1.6193,
124
+ "step": 1000
125
+ },
126
+ {
127
+ "epoch": 4.0,
128
+ "eval_accuracy": 0.5103809523809524,
129
+ "eval_loss": 2.5039021968841553,
130
+ "eval_runtime": 5.1568,
131
+ "eval_samples_per_second": 96.96,
132
+ "eval_steps_per_second": 12.217,
133
+ "step": 1000
134
+ },
135
+ {
136
+ "epoch": 4.0,
137
+ "eval_exact_match": 18.4,
138
+ "eval_f1": 26.892813852813866,
139
+ "step": 1000
140
+ },
141
+ {
142
+ "epoch": 4.4,
143
+ "grad_norm": 1.7909170389175415,
144
+ "learning_rate": 0.0001,
145
+ "loss": 1.3298,
146
+ "step": 1100
147
+ },
148
+ {
149
+ "epoch": 4.8,
150
+ "grad_norm": 1.9236161708831787,
151
+ "learning_rate": 0.0001,
152
+ "loss": 1.3666,
153
+ "step": 1200
154
+ },
155
+ {
156
+ "epoch": 5.0,
157
+ "eval_accuracy": 0.505015873015873,
158
+ "eval_loss": 2.6543924808502197,
159
+ "eval_runtime": 5.5115,
160
+ "eval_samples_per_second": 90.719,
161
+ "eval_steps_per_second": 11.431,
162
+ "step": 1250
163
+ },
164
+ {
165
+ "epoch": 5.0,
166
+ "eval_exact_match": 18.4,
167
+ "eval_f1": 25.875286609941792,
168
+ "step": 1250
169
+ },
170
+ {
171
+ "epoch": 5.2,
172
+ "grad_norm": 1.8524874448776245,
173
+ "learning_rate": 0.0001,
174
+ "loss": 1.2381,
175
+ "step": 1300
176
+ },
177
+ {
178
+ "epoch": 5.6,
179
+ "grad_norm": 2.1092071533203125,
180
+ "learning_rate": 0.0001,
181
+ "loss": 1.1141,
182
+ "step": 1400
183
+ },
184
+ {
185
+ "epoch": 6.0,
186
+ "grad_norm": 2.065767288208008,
187
+ "learning_rate": 0.0001,
188
+ "loss": 1.1435,
189
+ "step": 1500
190
+ },
191
+ {
192
+ "epoch": 6.0,
193
+ "eval_accuracy": 0.5010793650793651,
194
+ "eval_loss": 2.843566656112671,
195
+ "eval_runtime": 5.1394,
196
+ "eval_samples_per_second": 97.287,
197
+ "eval_steps_per_second": 12.258,
198
+ "step": 1500
199
+ },
200
+ {
201
+ "epoch": 6.0,
202
+ "eval_exact_match": 17.4,
203
+ "eval_f1": 24.31514874014875,
204
+ "step": 1500
205
+ },
206
+ {
207
+ "epoch": 6.4,
208
+ "grad_norm": 2.329406261444092,
209
+ "learning_rate": 0.0001,
210
+ "loss": 0.8887,
211
+ "step": 1600
212
+ },
213
+ {
214
+ "epoch": 6.8,
215
+ "grad_norm": 2.489598274230957,
216
+ "learning_rate": 0.0001,
217
+ "loss": 0.9171,
218
+ "step": 1700
219
+ },
220
+ {
221
+ "epoch": 7.0,
222
+ "eval_accuracy": 0.49707936507936507,
223
+ "eval_loss": 3.0319864749908447,
224
+ "eval_runtime": 5.3015,
225
+ "eval_samples_per_second": 94.313,
226
+ "eval_steps_per_second": 11.883,
227
+ "step": 1750
228
+ },
229
+ {
230
+ "epoch": 7.0,
231
+ "eval_exact_match": 16.0,
232
+ "eval_f1": 22.824985569985575,
233
+ "step": 1750
234
+ },
235
+ {
236
+ "epoch": 7.2,
237
+ "grad_norm": 2.764033794403076,
238
+ "learning_rate": 0.0001,
239
+ "loss": 0.8093,
240
+ "step": 1800
241
+ },
242
+ {
243
+ "epoch": 7.6,
244
+ "grad_norm": 2.5643441677093506,
245
+ "learning_rate": 0.0001,
246
+ "loss": 0.724,
247
+ "step": 1900
248
+ },
249
+ {
250
+ "epoch": 8.0,
251
+ "grad_norm": 2.074833631515503,
252
+ "learning_rate": 0.0001,
253
+ "loss": 0.7531,
254
+ "step": 2000
255
+ },
256
+ {
257
+ "epoch": 8.0,
258
+ "eval_accuracy": 0.49304761904761907,
259
+ "eval_loss": 3.2584712505340576,
260
+ "eval_runtime": 5.2945,
261
+ "eval_samples_per_second": 94.438,
262
+ "eval_steps_per_second": 11.899,
263
+ "step": 2000
264
+ },
265
+ {
266
+ "epoch": 8.0,
267
+ "eval_exact_match": 15.0,
268
+ "eval_f1": 21.895264180264185,
269
+ "step": 2000
270
+ },
271
+ {
272
+ "epoch": 8.4,
273
+ "grad_norm": 2.649679660797119,
274
+ "learning_rate": 0.0001,
275
+ "loss": 0.5777,
276
+ "step": 2100
277
+ },
278
+ {
279
+ "epoch": 8.8,
280
+ "grad_norm": 2.1969234943389893,
281
+ "learning_rate": 0.0001,
282
+ "loss": 0.6101,
283
+ "step": 2200
284
+ },
285
+ {
286
+ "epoch": 9.0,
287
+ "eval_accuracy": 0.4925079365079365,
288
+ "eval_loss": 3.3418095111846924,
289
+ "eval_runtime": 5.1381,
290
+ "eval_samples_per_second": 97.312,
291
+ "eval_steps_per_second": 12.261,
292
+ "step": 2250
293
+ },
294
+ {
295
+ "epoch": 9.0,
296
+ "eval_exact_match": 14.4,
297
+ "eval_f1": 21.76202020202021,
298
+ "step": 2250
299
+ }
300
+ ],
301
+ "logging_steps": 100,
302
+ "max_steps": 12500,
303
+ "num_input_tokens_seen": 0,
304
+ "num_train_epochs": 50,
305
+ "save_steps": 500,
306
+ "stateful_callbacks": {
307
+ "TrainerControl": {
308
+ "args": {
309
+ "should_epoch_stop": false,
310
+ "should_evaluate": false,
311
+ "should_log": false,
312
+ "should_save": true,
313
+ "should_training_stop": false
314
+ },
315
+ "attributes": {}
316
+ }
317
+ },
318
+ "total_flos": 6.881574399875482e+16,
319
+ "train_batch_size": 2,
320
+ "trial_name": null,
321
+ "trial_params": null
322
+ }
checkpoint-2250/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3414153f69372b550d629c900d05ab7510b14d218f2d8546142e7b41d948d3e
3
+ size 5304
checkpoint-2250/vocab.json ADDED
The diff for this file is too large to render. See raw diff