Hugging Face's logo

tyzhu
/
lmind_nq_train6000_eval6489_v1_qa_1e-4_lora2

Safetensors
Generated from Trainer
Eval Results
Model card Files Community
tyzhu commited on
Commit
7e0511a
•
1 Parent(s): 1304c47

Training in progress, epoch 10, checkpoint

Browse files
Files changed (14) hide show
  1. checkpoint-1875/adapter_config.json +1 -1
  2. checkpoint-1875/adapter_model.bin +3 -0
  3. checkpoint-1875/added_tokens.json +3 -3
  4. checkpoint-1875/optimizer.pt +2 -2
  5. checkpoint-1875/rng_state_0.pth +1 -1
  6. checkpoint-1875/rng_state_1.pth +1 -1
  7. checkpoint-1875/rng_state_2.pth +1 -1
  8. checkpoint-1875/rng_state_3.pth +1 -1
  9. checkpoint-1875/special_tokens_map.json +4 -12
  10. checkpoint-1875/tokenizer.json +0 -0
  11. checkpoint-1875/tokenizer.model +3 -0
  12. checkpoint-1875/tokenizer_config.json +17 -20
  13. checkpoint-1875/trainer_state.json +111 -143
  14. checkpoint-1875/training_args.bin +2 -2
checkpoint-1875/adapter_config.json CHANGED
@@ -1,6 +1,6 @@
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,
 
1
  {
2
  "auto_mapping": null,
3
+ "base_model_name_or_path": "meta-llama/Llama-2-7b-hf",
4
  "bias": "none",
5
  "fan_in_fan_out": false,
6
  "inference_mode": true,
checkpoint-1875/adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:600cae0286546c9dd213883720ba0920b1925ec0f6d90add926ec6db80f69d2a
3
+ size 143269386
checkpoint-1875/added_tokens.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "<|endoftext|>": 151643,
3
- "<|im_end|>": 151645,
4
- "<|im_start|>": 151644
5
  }
 
1
  {
2
+ "</s>": 2,
3
+ "<s>": 1,
4
+ "<unk>": 0
5
  }
checkpoint-1875/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:76f8138ec141c252beb80054b9199ff677cf3e5225aab350c6aec246730f540b
3
- size 224537202
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:98348c26ef8d0ee454ac9047d502d5e6da99eda71217d39a5f1c12e63c6f8ab8
3
+ size 286585234
checkpoint-1875/rng_state_0.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:192d3490bd98629e056807c394a41c35c66c7208c1ae21fdaadcdd42e2219a8a
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f282b6f37417c2152a18ec3d7d93bbffd9476c18fe712ef2bed7c09582a2004e
3
  size 15024
checkpoint-1875/rng_state_1.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:741c468e729a0382b4dd8ae903ec0c9b437f3431c443f15393a482a59a037726
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a493ae3942e0784e9712efc767dcac191577c79fe6d0a76ab9b3576b613bcc3a
3
  size 15024
checkpoint-1875/rng_state_2.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6b78177d1bb56647516e37f71b9fed879d0df2a0b492ae7643b2aec87445e4fb
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a9298cd9df2c70e18feb83f14bd485b19cca3b29a0e21467b39c3a10f8b9d41
3
  size 15024
checkpoint-1875/rng_state_3.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a2b39dff08fa3d20bc153847317b409245c670e19438ab595925555b269ebe5a
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:46be0b4e22f45eef82f42e9d3bc12820a0f0274e257800bc539479fd70250e93
3
  size 15024
checkpoint-1875/special_tokens_map.json CHANGED
@@ -1,14 +1,6 @@
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
  }
 
1
  {
2
+ "bos_token": "<s>",
3
+ "eos_token": "</s>",
4
+ "pad_token": "</s>",
5
+ "unk_token": "<unk>"
 
 
 
 
 
 
 
 
6
  }
checkpoint-1875/tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
checkpoint-1875/tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
checkpoint-1875/tokenizer_config.json CHANGED
@@ -1,24 +1,23 @@
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,
@@ -26,18 +25,16 @@
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
  }
 
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,
 
25
  "special": true
26
  }
27
  },
28
+ "additional_special_tokens": [],
29
+ "bos_token": "<s>",
 
 
 
 
30
  "clean_up_tokenization_spaces": false,
31
+ "eos_token": "</s>",
32
+ "legacy": false,
33
+ "model_max_length": 1000000000000000019884624838656,
34
+ "pad_token": "</s>",
35
+ "padding_side": "left",
36
+ "sp_model_kwargs": {},
37
+ "tokenizer_class": "LlamaTokenizer",
38
+ "unk_token": "<unk>",
39
+ "use_default_system_prompt": true
40
  }
checkpoint-1875/trainer_state.json CHANGED
@@ -9,301 +9,269 @@
9
  "is_world_process_zero": true,
10
  "log_history": [
11
  {
12
- "epoch": 0.5333333333333333,
13
- "grad_norm": 0.64143306016922,
14
  "learning_rate": 0.0001,
15
- "loss": 1.7779,
16
  "step": 100
17
  },
18
  {
19
- "epoch": 0.9973333333333333,
20
- "eval_accuracy": 0.5734871794871795,
21
- "eval_loss": 1.6191272735595703,
22
- "eval_runtime": 5.393,
23
- "eval_samples_per_second": 92.713,
24
- "eval_steps_per_second": 11.682,
25
  "step": 187
26
  },
27
  {
28
- "epoch": 0.9973333333333333,
29
- "eval_exact_match": 18.0,
30
- "eval_f1": 28.280476190476193,
31
  "step": 187
32
  },
33
  {
34
- "epoch": 1.0666666666666667,
35
- "grad_norm": 0.7118939161300659,
36
  "learning_rate": 0.0001,
37
- "loss": 1.6349,
38
  "step": 200
39
  },
40
  {
41
  "epoch": 1.6,
42
- "grad_norm": 1.0694799423217773,
43
  "learning_rate": 0.0001,
44
- "loss": 1.4887,
45
  "step": 300
46
  },
47
  {
48
  "epoch": 2.0,
49
- "eval_accuracy": 0.5735897435897436,
50
- "eval_loss": 1.6172032356262207,
51
- "eval_runtime": 5.0425,
52
- "eval_samples_per_second": 99.158,
53
- "eval_steps_per_second": 12.494,
54
  "step": 375
55
  },
56
  {
57
  "epoch": 2.0,
58
- "eval_exact_match": 19.8,
59
- "eval_f1": 28.77095238095238,
60
  "step": 375
61
  },
62
  {
63
- "epoch": 2.1333333333333333,
64
- "grad_norm": 1.28153395652771,
65
  "learning_rate": 0.0001,
66
- "loss": 1.4304,
67
  "step": 400
68
  },
69
  {
70
- "epoch": 2.6666666666666665,
71
- "grad_norm": 1.3190444707870483,
72
  "learning_rate": 0.0001,
73
- "loss": 1.2346,
74
  "step": 500
75
  },
76
  {
77
- "epoch": 2.997333333333333,
78
- "eval_accuracy": 0.5706153846153846,
79
- "eval_loss": 1.6950472593307495,
80
- "eval_runtime": 5.1981,
81
- "eval_samples_per_second": 96.188,
82
- "eval_steps_per_second": 12.12,
83
  "step": 562
84
  },
85
  {
86
- "epoch": 2.997333333333333,
87
- "eval_exact_match": 19.4,
88
- "eval_f1": 28.241904761904756,
89
  "step": 562
90
  },
91
  {
92
  "epoch": 3.2,
93
- "grad_norm": 1.5040416717529297,
94
  "learning_rate": 0.0001,
95
- "loss": 1.1583,
96
  "step": 600
97
  },
98
  {
99
- "epoch": 3.7333333333333334,
100
- "grad_norm": 1.512290358543396,
101
  "learning_rate": 0.0001,
102
- "loss": 1.0104,
103
  "step": 700
104
  },
105
  {
106
  "epoch": 4.0,
107
- "eval_accuracy": 0.5655897435897436,
108
- "eval_loss": 1.7944799661636353,
109
- "eval_runtime": 5.3441,
110
- "eval_samples_per_second": 93.561,
111
- "eval_steps_per_second": 11.789,
112
  "step": 750
113
  },
114
  {
115
  "epoch": 4.0,
116
- "eval_exact_match": 15.8,
117
- "eval_f1": 23.639523809523823,
118
  "step": 750
119
  },
120
  {
121
- "epoch": 4.266666666666667,
122
- "grad_norm": 1.698282241821289,
123
  "learning_rate": 0.0001,
124
- "loss": 0.9275,
125
  "step": 800
126
  },
127
  {
128
  "epoch": 4.8,
129
- "grad_norm": 1.6007401943206787,
130
  "learning_rate": 0.0001,
131
- "loss": 0.843,
132
  "step": 900
133
  },
134
  {
135
- "epoch": 4.997333333333334,
136
- "eval_accuracy": 0.5632820512820513,
137
- "eval_loss": 1.9219905138015747,
138
- "eval_runtime": 5.2659,
139
- "eval_samples_per_second": 94.951,
140
- "eval_steps_per_second": 11.964,
141
  "step": 937
142
  },
143
  {
144
- "epoch": 4.997333333333334,
145
- "eval_exact_match": 15.8,
146
- "eval_f1": 24.631904761904778,
147
  "step": 937
148
  },
149
  {
150
- "epoch": 5.333333333333333,
151
- "grad_norm": 1.5375592708587646,
152
  "learning_rate": 0.0001,
153
- "loss": 0.7516,
154
  "step": 1000
155
  },
156
  {
157
- "epoch": 5.866666666666667,
158
- "grad_norm": 1.718989372253418,
159
  "learning_rate": 0.0001,
160
- "loss": 0.7199,
161
  "step": 1100
162
  },
163
  {
164
  "epoch": 6.0,
165
- "eval_accuracy": 0.5616923076923077,
166
- "eval_loss": 2.016322612762451,
167
- "eval_runtime": 5.116,
168
- "eval_samples_per_second": 97.734,
169
- "eval_steps_per_second": 12.314,
170
  "step": 1125
171
  },
172
  {
173
  "epoch": 6.0,
174
- "eval_exact_match": 14.4,
175
- "eval_f1": 22.39285714285715,
176
  "step": 1125
177
  },
178
  {
179
  "epoch": 6.4,
180
- "grad_norm": 1.8337936401367188,
181
  "learning_rate": 0.0001,
182
- "loss": 0.6378,
183
  "step": 1200
184
  },
185
  {
186
- "epoch": 6.933333333333334,
187
- "grad_norm": 1.9019217491149902,
188
  "learning_rate": 0.0001,
189
- "loss": 0.6432,
190
  "step": 1300
191
  },
192
  {
193
- "epoch": 6.997333333333334,
194
- "eval_accuracy": 0.5616410256410257,
195
- "eval_loss": 2.1283841133117676,
196
- "eval_runtime": 5.1352,
197
- "eval_samples_per_second": 97.367,
198
- "eval_steps_per_second": 12.268,
199
  "step": 1312
200
  },
201
  {
202
- "epoch": 6.997333333333334,
203
- "eval_exact_match": 13.8,
204
- "eval_f1": 22.042857142857148,
205
  "step": 1312
206
  },
207
  {
208
- "epoch": 7.466666666666667,
209
- "grad_norm": 1.246907114982605,
210
  "learning_rate": 0.0001,
211
- "loss": 0.578,
212
  "step": 1400
213
  },
214
  {
215
  "epoch": 8.0,
216
- "grad_norm": 1.6256760358810425,
217
  "learning_rate": 0.0001,
218
- "loss": 0.596,
219
  "step": 1500
220
  },
221
  {
222
  "epoch": 8.0,
223
- "eval_accuracy": 0.5603589743589743,
224
- "eval_loss": 2.170966386795044,
225
- "eval_runtime": 5.0636,
226
- "eval_samples_per_second": 98.744,
227
- "eval_steps_per_second": 12.442,
228
  "step": 1500
229
  },
230
  {
231
  "epoch": 8.0,
232
- "eval_exact_match": 14.4,
233
- "eval_f1": 21.71636363636364,
234
  "step": 1500
235
  },
236
  {
237
- "epoch": 8.533333333333333,
238
- "grad_norm": 1.3106721639633179,
239
  "learning_rate": 0.0001,
240
- "loss": 0.543,
241
  "step": 1600
242
  },
243
  {
244
- "epoch": 8.997333333333334,
245
- "eval_accuracy": 0.5595384615384615,
246
- "eval_loss": 2.262348175048828,
247
- "eval_runtime": 5.3198,
248
- "eval_samples_per_second": 93.989,
249
- "eval_steps_per_second": 11.843,
250
  "step": 1687
251
  },
252
  {
253
- "epoch": 8.997333333333334,
254
- "eval_exact_match": 16.0,
255
- "eval_f1": 24.34507936507938,
256
  "step": 1687
257
  },
258
  {
259
- "epoch": 9.066666666666666,
260
- "grad_norm": 1.0499460697174072,
261
  "learning_rate": 0.0001,
262
- "loss": 0.5644,
263
  "step": 1700
264
  },
265
  {
266
  "epoch": 9.6,
267
- "grad_norm": 0.9217801690101624,
268
  "learning_rate": 0.0001,
269
- "loss": 0.5314,
270
  "step": 1800
271
  },
272
  {
273
  "epoch": 10.0,
274
- "eval_accuracy": 0.5583589743589744,
275
- "eval_loss": 2.268125057220459,
276
- "eval_runtime": 5.457,
277
- "eval_samples_per_second": 91.626,
278
- "eval_steps_per_second": 11.545,
279
  "step": 1875
280
  },
281
  {
282
  "epoch": 10.0,
283
- "eval_exact_match": 15.4,
284
- "eval_f1": 23.46095238095238,
285
  "step": 1875
286
  }
287
  ],
288
  "logging_steps": 100,
289
  "max_steps": 9350,
290
- "num_input_tokens_seen": 0,
291
  "num_train_epochs": 50,
292
  "save_steps": 500,
293
- "stateful_callbacks": {
294
- "TrainerControl": {
295
- "args": {
296
- "should_epoch_stop": false,
297
- "should_evaluate": false,
298
- "should_log": false,
299
- "should_save": true,
300
- "should_training_stop": false
301
- },
302
- "attributes": {}
303
- }
304
- },
305
- "total_flos": 3.4335509031419904e+16,
306
- "train_batch_size": 2,
307
  "trial_name": null,
308
  "trial_params": null
309
  }
 
9
  "is_world_process_zero": true,
10
  "log_history": [
11
  {
12
+ "epoch": 0.53,
 
13
  "learning_rate": 0.0001,
14
+ "loss": 1.598,
15
  "step": 100
16
  },
17
  {
18
+ "epoch": 1.0,
19
+ "eval_accuracy": 0.6146666666666667,
20
+ "eval_loss": 1.2691738605499268,
21
+ "eval_runtime": 4.3939,
22
+ "eval_samples_per_second": 113.793,
23
+ "eval_steps_per_second": 14.338,
24
  "step": 187
25
  },
26
  {
27
+ "epoch": 1.0,
28
+ "eval_exact_match": 24.8,
29
+ "eval_f1": 38.10857142857143,
30
  "step": 187
31
  },
32
  {
33
+ "epoch": 1.07,
 
34
  "learning_rate": 0.0001,
35
+ "loss": 1.2894,
36
  "step": 200
37
  },
38
  {
39
  "epoch": 1.6,
 
40
  "learning_rate": 0.0001,
41
+ "loss": 1.1923,
42
  "step": 300
43
  },
44
  {
45
  "epoch": 2.0,
46
+ "eval_accuracy": 0.6175897435897436,
47
+ "eval_loss": 1.2732893228530884,
48
+ "eval_runtime": 4.5482,
49
+ "eval_samples_per_second": 109.934,
50
+ "eval_steps_per_second": 13.852,
51
  "step": 375
52
  },
53
  {
54
  "epoch": 2.0,
55
+ "eval_exact_match": 25.6,
56
+ "eval_f1": 39.04746031746033,
57
  "step": 375
58
  },
59
  {
60
+ "epoch": 2.13,
 
61
  "learning_rate": 0.0001,
62
+ "loss": 1.1174,
63
  "step": 400
64
  },
65
  {
66
+ "epoch": 2.67,
 
67
  "learning_rate": 0.0001,
68
+ "loss": 0.9732,
69
  "step": 500
70
  },
71
  {
72
+ "epoch": 3.0,
73
+ "eval_accuracy": 0.6135897435897436,
74
+ "eval_loss": 1.33958101272583,
75
+ "eval_runtime": 4.0988,
76
+ "eval_samples_per_second": 121.986,
77
+ "eval_steps_per_second": 15.37,
78
  "step": 562
79
  },
80
  {
81
+ "epoch": 3.0,
82
+ "eval_exact_match": 25.4,
83
+ "eval_f1": 37.65698412698413,
84
  "step": 562
85
  },
86
  {
87
  "epoch": 3.2,
 
88
  "learning_rate": 0.0001,
89
+ "loss": 0.9111,
90
  "step": 600
91
  },
92
  {
93
+ "epoch": 3.73,
 
94
  "learning_rate": 0.0001,
95
+ "loss": 0.7763,
96
  "step": 700
97
  },
98
  {
99
  "epoch": 4.0,
100
+ "eval_accuracy": 0.6104102564102564,
101
+ "eval_loss": 1.4358161687850952,
102
+ "eval_runtime": 4.4028,
103
+ "eval_samples_per_second": 113.565,
104
+ "eval_steps_per_second": 14.309,
105
  "step": 750
106
  },
107
  {
108
  "epoch": 4.0,
109
+ "eval_exact_match": 25.2,
110
+ "eval_f1": 37.8809523809524,
111
  "step": 750
112
  },
113
  {
114
+ "epoch": 4.27,
 
115
  "learning_rate": 0.0001,
116
+ "loss": 0.7118,
117
  "step": 800
118
  },
119
  {
120
  "epoch": 4.8,
 
121
  "learning_rate": 0.0001,
122
+ "loss": 0.6498,
123
  "step": 900
124
  },
125
  {
126
+ "epoch": 5.0,
127
+ "eval_accuracy": 0.6051794871794872,
128
+ "eval_loss": 1.5630384683609009,
129
+ "eval_runtime": 4.1079,
130
+ "eval_samples_per_second": 121.717,
131
+ "eval_steps_per_second": 15.336,
132
  "step": 937
133
  },
134
  {
135
+ "epoch": 5.0,
136
+ "eval_exact_match": 23.4,
137
+ "eval_f1": 35.55111111111113,
138
  "step": 937
139
  },
140
  {
141
+ "epoch": 5.33,
 
142
  "learning_rate": 0.0001,
143
+ "loss": 0.5911,
144
  "step": 1000
145
  },
146
  {
147
+ "epoch": 5.87,
 
148
  "learning_rate": 0.0001,
149
+ "loss": 0.57,
150
  "step": 1100
151
  },
152
  {
153
  "epoch": 6.0,
154
+ "eval_accuracy": 0.6031282051282051,
155
+ "eval_loss": 1.6599360704421997,
156
+ "eval_runtime": 4.2005,
157
+ "eval_samples_per_second": 119.033,
158
+ "eval_steps_per_second": 14.998,
159
  "step": 1125
160
  },
161
  {
162
  "epoch": 6.0,
163
+ "eval_exact_match": 22.6,
164
+ "eval_f1": 34.44650793650795,
165
  "step": 1125
166
  },
167
  {
168
  "epoch": 6.4,
 
169
  "learning_rate": 0.0001,
170
+ "loss": 0.517,
171
  "step": 1200
172
  },
173
  {
174
+ "epoch": 6.93,
 
175
  "learning_rate": 0.0001,
176
+ "loss": 0.5253,
177
  "step": 1300
178
  },
179
  {
180
+ "epoch": 7.0,
181
+ "eval_accuracy": 0.6027179487179487,
182
+ "eval_loss": 1.7479698657989502,
183
+ "eval_runtime": 4.4276,
184
+ "eval_samples_per_second": 112.929,
185
+ "eval_steps_per_second": 14.229,
186
  "step": 1312
187
  },
188
  {
189
+ "epoch": 7.0,
190
+ "eval_exact_match": 22.2,
191
+ "eval_f1": 33.87303030303032,
192
  "step": 1312
193
  },
194
  {
195
+ "epoch": 7.47,
 
196
  "learning_rate": 0.0001,
197
+ "loss": 0.4784,
198
  "step": 1400
199
  },
200
  {
201
  "epoch": 8.0,
 
202
  "learning_rate": 0.0001,
203
+ "loss": 0.4958,
204
  "step": 1500
205
  },
206
  {
207
  "epoch": 8.0,
208
+ "eval_accuracy": 0.602051282051282,
209
+ "eval_loss": 1.8059930801391602,
210
+ "eval_runtime": 4.1898,
211
+ "eval_samples_per_second": 119.337,
212
+ "eval_steps_per_second": 15.036,
213
  "step": 1500
214
  },
215
  {
216
  "epoch": 8.0,
217
+ "eval_exact_match": 21.8,
218
+ "eval_f1": 32.95365079365081,
219
  "step": 1500
220
  },
221
  {
222
+ "epoch": 8.53,
 
223
  "learning_rate": 0.0001,
224
+ "loss": 0.4521,
225
  "step": 1600
226
  },
227
  {
228
+ "epoch": 9.0,
229
+ "eval_accuracy": 0.6013333333333334,
230
+ "eval_loss": 1.8598920106887817,
231
+ "eval_runtime": 4.9021,
232
+ "eval_samples_per_second": 101.996,
233
+ "eval_steps_per_second": 12.852,
234
  "step": 1687
235
  },
236
  {
237
+ "epoch": 9.0,
238
+ "eval_exact_match": 22.6,
239
+ "eval_f1": 33.89858585858587,
240
  "step": 1687
241
  },
242
  {
243
+ "epoch": 9.07,
 
244
  "learning_rate": 0.0001,
245
+ "loss": 0.4694,
246
  "step": 1700
247
  },
248
  {
249
  "epoch": 9.6,
 
250
  "learning_rate": 0.0001,
251
+ "loss": 0.443,
252
  "step": 1800
253
  },
254
  {
255
  "epoch": 10.0,
256
+ "eval_accuracy": 0.6013333333333334,
257
+ "eval_loss": 1.9468085765838623,
258
+ "eval_runtime": 4.4033,
259
+ "eval_samples_per_second": 113.552,
260
+ "eval_steps_per_second": 14.308,
261
  "step": 1875
262
  },
263
  {
264
  "epoch": 10.0,
265
+ "eval_exact_match": 21.8,
266
+ "eval_f1": 32.7704761904762,
267
  "step": 1875
268
  }
269
  ],
270
  "logging_steps": 100,
271
  "max_steps": 9350,
 
272
  "num_train_epochs": 50,
273
  "save_steps": 500,
274
+ "total_flos": 6.997539694628045e+16,
 
 
 
 
 
 
 
 
 
 
 
 
 
275
  "trial_name": null,
276
  "trial_params": null
277
  }
checkpoint-1875/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d667d5e0e40fe951f9fe0d2cd7fb4682a608b09af78a113a245307211adedfbc
3
- size 5304
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dfdad39e2291c20f000713e6b820dbeb747acc6873c9eec22bd69c854755aa38
3
+ size 4728