charlieCs commited on
Commit
76248e6
1 Parent(s): ec74d58

upload model

Browse files
.ipynb_checkpoints/config-checkpoint.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/data/recoteam_583/mlapp/foundation_models/Qwen1.5-14B",
3
+ "architectures": [
4
+ "Qwen2ForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 151643,
8
+ "eos_token_id": 151643,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 5120,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 13696,
13
+ "max_position_embeddings": 32768,
14
+ "max_window_layers": 35,
15
+ "model_type": "qwen2",
16
+ "num_attention_heads": 40,
17
+ "num_hidden_layers": 40,
18
+ "num_key_value_heads": 40,
19
+ "rms_norm_eps": 1e-06,
20
+ "rope_theta": 1000000.0,
21
+ "sliding_window": 32768,
22
+ "tie_word_embeddings": false,
23
+ "torch_dtype": "bfloat16",
24
+ "transformers_version": "4.38.2",
25
+ "use_cache": false,
26
+ "use_sliding_window": false,
27
+ "vocab_size": 152064
28
+ }
added_tokens.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "<|endoftext|>": 151643,
3
+ "<|im_end|>": 151645,
4
+ "<|im_start|>": 151644
5
+ }
config.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
- "_name_or_path": "/data/recoteam_583/charlie/finetuned_models/qwen-14b-merged_ss_bm_gm-subm/checkpoint-153",
3
  "architectures": [
4
- "Qwen2Model"
5
  ],
6
  "attention_dropout": 0.0,
7
  "bos_token_id": 151643,
@@ -20,7 +20,7 @@
20
  "rope_theta": 1000000.0,
21
  "sliding_window": 32768,
22
  "tie_word_embeddings": false,
23
- "torch_dtype": "float32",
24
  "transformers_version": "4.38.2",
25
  "use_cache": false,
26
  "use_sliding_window": false,
 
1
  {
2
+ "_name_or_path": "/data/recoteam_583/mlapp/foundation_models/Qwen1.5-14B",
3
  "architectures": [
4
+ "Qwen2ForCausalLM"
5
  ],
6
  "attention_dropout": 0.0,
7
  "bos_token_id": 151643,
 
20
  "rope_theta": 1000000.0,
21
  "sliding_window": 32768,
22
  "tie_word_embeddings": false,
23
+ "torch_dtype": "bfloat16",
24
  "transformers_version": "4.38.2",
25
  "use_cache": false,
26
  "use_sliding_window": false,
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 151643,
3
+ "eos_token_id": 151643,
4
+ "max_new_tokens": 2048,
5
+ "transformers_version": "4.38.2"
6
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>"
5
+ ],
6
+ "eos_token": {
7
+ "content": "<|im_end|>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false
12
+ },
13
+ "pad_token": {
14
+ "content": "<|endoftext|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false
19
+ }
20
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,44 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "{% set system_message = 'You are a helpful assistant.' %}{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ '<|im_start|>system\\n' + system_message + '<|im_end|>\\n' }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|im_start|>user\\n' + content + '<|im_end|>\\n<|im_start|>assistant\\n' }}{% elif message['role'] == 'assistant' %}{{ content + '<|im_end|>' + '\\n' }}{% endif %}{% endfor %}",
35
+ "clean_up_tokenization_spaces": false,
36
+ "eos_token": "<|im_end|>",
37
+ "errors": "replace",
38
+ "model_max_length": 32768,
39
+ "pad_token": "<|endoftext|>",
40
+ "padding_side": "right",
41
+ "split_special_tokens": false,
42
+ "tokenizer_class": "Qwen2Tokenizer",
43
+ "unk_token": null
44
+ }
trainer_state.json ADDED
@@ -0,0 +1,1092 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 153,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.02,
13
+ "grad_norm": 7.385727144574295,
14
+ "learning_rate": 1.8181818181818183e-06,
15
+ "loss": 1.7526,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.04,
20
+ "grad_norm": 7.407346233892389,
21
+ "learning_rate": 3.6363636363636366e-06,
22
+ "loss": 1.7086,
23
+ "step": 2
24
+ },
25
+ {
26
+ "epoch": 0.06,
27
+ "grad_norm": 7.453240159782491,
28
+ "learning_rate": 5.4545454545454545e-06,
29
+ "loss": 1.6948,
30
+ "step": 3
31
+ },
32
+ {
33
+ "epoch": 0.08,
34
+ "grad_norm": 5.231881985607868,
35
+ "learning_rate": 7.272727272727273e-06,
36
+ "loss": 1.6844,
37
+ "step": 4
38
+ },
39
+ {
40
+ "epoch": 0.1,
41
+ "grad_norm": 4.290775811530979,
42
+ "learning_rate": 9.090909090909091e-06,
43
+ "loss": 1.6481,
44
+ "step": 5
45
+ },
46
+ {
47
+ "epoch": 0.12,
48
+ "grad_norm": 4.865595819070934,
49
+ "learning_rate": 1.0909090909090909e-05,
50
+ "loss": 1.559,
51
+ "step": 6
52
+ },
53
+ {
54
+ "epoch": 0.14,
55
+ "grad_norm": 4.787864348488922,
56
+ "learning_rate": 1.2727272727272728e-05,
57
+ "loss": 1.5407,
58
+ "step": 7
59
+ },
60
+ {
61
+ "epoch": 0.16,
62
+ "grad_norm": 5.343516383725201,
63
+ "learning_rate": 1.4545454545454546e-05,
64
+ "loss": 1.5289,
65
+ "step": 8
66
+ },
67
+ {
68
+ "epoch": 0.18,
69
+ "grad_norm": 5.876818436372016,
70
+ "learning_rate": 1.6363636363636366e-05,
71
+ "loss": 1.4746,
72
+ "step": 9
73
+ },
74
+ {
75
+ "epoch": 0.2,
76
+ "grad_norm": 5.090544083750136,
77
+ "learning_rate": 1.8181818181818182e-05,
78
+ "loss": 1.3829,
79
+ "step": 10
80
+ },
81
+ {
82
+ "epoch": 0.22,
83
+ "grad_norm": 4.736310405894691,
84
+ "learning_rate": 2e-05,
85
+ "loss": 1.4213,
86
+ "step": 11
87
+ },
88
+ {
89
+ "epoch": 0.24,
90
+ "grad_norm": 4.585247241293968,
91
+ "learning_rate": 1.999867521457224e-05,
92
+ "loss": 1.3315,
93
+ "step": 12
94
+ },
95
+ {
96
+ "epoch": 0.25,
97
+ "grad_norm": 4.247578099135077,
98
+ "learning_rate": 1.9994701209300245e-05,
99
+ "loss": 1.269,
100
+ "step": 13
101
+ },
102
+ {
103
+ "epoch": 0.27,
104
+ "grad_norm": 4.100439299332423,
105
+ "learning_rate": 1.9988079037124866e-05,
106
+ "loss": 1.237,
107
+ "step": 14
108
+ },
109
+ {
110
+ "epoch": 0.29,
111
+ "grad_norm": 3.900696491747024,
112
+ "learning_rate": 1.9978810452637544e-05,
113
+ "loss": 1.206,
114
+ "step": 15
115
+ },
116
+ {
117
+ "epoch": 0.31,
118
+ "grad_norm": 3.7254601213601424,
119
+ "learning_rate": 1.9966897911615417e-05,
120
+ "loss": 1.1384,
121
+ "step": 16
122
+ },
123
+ {
124
+ "epoch": 0.33,
125
+ "grad_norm": 3.4594232764317203,
126
+ "learning_rate": 1.995234457037063e-05,
127
+ "loss": 1.1137,
128
+ "step": 17
129
+ },
130
+ {
131
+ "epoch": 0.35,
132
+ "grad_norm": 3.479977282965165,
133
+ "learning_rate": 1.9935154284914063e-05,
134
+ "loss": 1.0582,
135
+ "step": 18
136
+ },
137
+ {
138
+ "epoch": 0.37,
139
+ "grad_norm": 3.089440166288491,
140
+ "learning_rate": 1.991533160993366e-05,
141
+ "loss": 1.0306,
142
+ "step": 19
143
+ },
144
+ {
145
+ "epoch": 0.39,
146
+ "grad_norm": 3.296297140236444,
147
+ "learning_rate": 1.98928817975876e-05,
148
+ "loss": 1.0031,
149
+ "step": 20
150
+ },
151
+ {
152
+ "epoch": 0.41,
153
+ "grad_norm": 3.092912502793922,
154
+ "learning_rate": 1.9867810796112742e-05,
155
+ "loss": 1.0027,
156
+ "step": 21
157
+ },
158
+ {
159
+ "epoch": 0.43,
160
+ "grad_norm": 2.8301743306090144,
161
+ "learning_rate": 1.9840125248248564e-05,
162
+ "loss": 0.915,
163
+ "step": 22
164
+ },
165
+ {
166
+ "epoch": 0.45,
167
+ "grad_norm": 2.700584849840672,
168
+ "learning_rate": 1.9809832489477144e-05,
169
+ "loss": 0.8695,
170
+ "step": 23
171
+ },
172
+ {
173
+ "epoch": 0.47,
174
+ "grad_norm": 2.9985312999308578,
175
+ "learning_rate": 1.9776940546079552e-05,
176
+ "loss": 0.8793,
177
+ "step": 24
178
+ },
179
+ {
180
+ "epoch": 0.49,
181
+ "grad_norm": 2.865876357974003,
182
+ "learning_rate": 1.9741458133009258e-05,
183
+ "loss": 0.8702,
184
+ "step": 25
185
+ },
186
+ {
187
+ "epoch": 0.51,
188
+ "grad_norm": 2.7813509804899423,
189
+ "learning_rate": 1.970339465158301e-05,
190
+ "loss": 0.8633,
191
+ "step": 26
192
+ },
193
+ {
194
+ "epoch": 0.53,
195
+ "grad_norm": 2.778002439526667,
196
+ "learning_rate": 1.9662760186989914e-05,
197
+ "loss": 0.8495,
198
+ "step": 27
199
+ },
200
+ {
201
+ "epoch": 0.55,
202
+ "grad_norm": 2.65981269219971,
203
+ "learning_rate": 1.9619565505619288e-05,
204
+ "loss": 0.8463,
205
+ "step": 28
206
+ },
207
+ {
208
+ "epoch": 0.57,
209
+ "grad_norm": 2.7575466470931684,
210
+ "learning_rate": 1.9573822052208013e-05,
211
+ "loss": 0.8125,
212
+ "step": 29
213
+ },
214
+ {
215
+ "epoch": 0.59,
216
+ "grad_norm": 2.359003505133353,
217
+ "learning_rate": 1.9525541946808187e-05,
218
+ "loss": 0.7691,
219
+ "step": 30
220
+ },
221
+ {
222
+ "epoch": 0.61,
223
+ "grad_norm": 2.362088089814385,
224
+ "learning_rate": 1.9474737981575833e-05,
225
+ "loss": 0.7924,
226
+ "step": 31
227
+ },
228
+ {
229
+ "epoch": 0.63,
230
+ "grad_norm": 2.446279901118075,
231
+ "learning_rate": 1.942142361738151e-05,
232
+ "loss": 0.6905,
233
+ "step": 32
234
+ },
235
+ {
236
+ "epoch": 0.65,
237
+ "grad_norm": 2.575618103062542,
238
+ "learning_rate": 1.936561298024377e-05,
239
+ "loss": 0.7403,
240
+ "step": 33
241
+ },
242
+ {
243
+ "epoch": 0.67,
244
+ "grad_norm": 2.4765301530813417,
245
+ "learning_rate": 1.9307320857586377e-05,
246
+ "loss": 0.6781,
247
+ "step": 34
248
+ },
249
+ {
250
+ "epoch": 0.69,
251
+ "grad_norm": 2.514368537213703,
252
+ "learning_rate": 1.9246562694320258e-05,
253
+ "loss": 0.6946,
254
+ "step": 35
255
+ },
256
+ {
257
+ "epoch": 0.71,
258
+ "grad_norm": 2.4362145971600135,
259
+ "learning_rate": 1.9183354588751274e-05,
260
+ "loss": 0.7167,
261
+ "step": 36
262
+ },
263
+ {
264
+ "epoch": 0.73,
265
+ "grad_norm": 2.497750987289733,
266
+ "learning_rate": 1.9117713288314864e-05,
267
+ "loss": 0.7087,
268
+ "step": 37
269
+ },
270
+ {
271
+ "epoch": 0.75,
272
+ "grad_norm": 2.4766895730904745,
273
+ "learning_rate": 1.904965618513868e-05,
274
+ "loss": 0.6525,
275
+ "step": 38
276
+ },
277
+ {
278
+ "epoch": 0.76,
279
+ "grad_norm": 2.738681388493496,
280
+ "learning_rate": 1.8979201311434434e-05,
281
+ "loss": 0.6883,
282
+ "step": 39
283
+ },
284
+ {
285
+ "epoch": 0.78,
286
+ "grad_norm": 2.3966146991738966,
287
+ "learning_rate": 1.8906367334720125e-05,
288
+ "loss": 0.65,
289
+ "step": 40
290
+ },
291
+ {
292
+ "epoch": 0.8,
293
+ "grad_norm": 2.3250167887091786,
294
+ "learning_rate": 1.8831173552873946e-05,
295
+ "loss": 0.6635,
296
+ "step": 41
297
+ },
298
+ {
299
+ "epoch": 0.82,
300
+ "grad_norm": 2.4981823035208532,
301
+ "learning_rate": 1.8753639889021197e-05,
302
+ "loss": 0.6694,
303
+ "step": 42
304
+ },
305
+ {
306
+ "epoch": 0.84,
307
+ "grad_norm": 2.193667735760868,
308
+ "learning_rate": 1.8673786886255478e-05,
309
+ "loss": 0.5838,
310
+ "step": 43
311
+ },
312
+ {
313
+ "epoch": 0.86,
314
+ "grad_norm": 2.2455740949475835,
315
+ "learning_rate": 1.8591635702195672e-05,
316
+ "loss": 0.5871,
317
+ "step": 44
318
+ },
319
+ {
320
+ "epoch": 0.88,
321
+ "grad_norm": 2.2660780881135194,
322
+ "learning_rate": 1.8507208103380093e-05,
323
+ "loss": 0.6389,
324
+ "step": 45
325
+ },
326
+ {
327
+ "epoch": 0.9,
328
+ "grad_norm": 2.1782462437953147,
329
+ "learning_rate": 1.8420526459499252e-05,
330
+ "loss": 0.5775,
331
+ "step": 46
332
+ },
333
+ {
334
+ "epoch": 0.92,
335
+ "grad_norm": 2.300815653260401,
336
+ "learning_rate": 1.8331613737468888e-05,
337
+ "loss": 0.6236,
338
+ "step": 47
339
+ },
340
+ {
341
+ "epoch": 0.94,
342
+ "grad_norm": 2.0552955568974483,
343
+ "learning_rate": 1.8240493495344695e-05,
344
+ "loss": 0.5946,
345
+ "step": 48
346
+ },
347
+ {
348
+ "epoch": 0.96,
349
+ "grad_norm": 2.3014809235970017,
350
+ "learning_rate": 1.8147189876080463e-05,
351
+ "loss": 0.6149,
352
+ "step": 49
353
+ },
354
+ {
355
+ "epoch": 0.98,
356
+ "grad_norm": 2.0483445577828654,
357
+ "learning_rate": 1.8051727601131228e-05,
358
+ "loss": 0.5565,
359
+ "step": 50
360
+ },
361
+ {
362
+ "epoch": 1.0,
363
+ "grad_norm": 2.1431784888417904,
364
+ "learning_rate": 1.7954131963903134e-05,
365
+ "loss": 0.5689,
366
+ "step": 51
367
+ },
368
+ {
369
+ "epoch": 1.02,
370
+ "grad_norm": 1.870213438898714,
371
+ "learning_rate": 1.785442882305179e-05,
372
+ "loss": 0.3835,
373
+ "step": 52
374
+ },
375
+ {
376
+ "epoch": 1.04,
377
+ "grad_norm": 1.7742745864796516,
378
+ "learning_rate": 1.775264459563081e-05,
379
+ "loss": 0.381,
380
+ "step": 53
381
+ },
382
+ {
383
+ "epoch": 1.06,
384
+ "grad_norm": 1.85913693482777,
385
+ "learning_rate": 1.764880625009245e-05,
386
+ "loss": 0.3634,
387
+ "step": 54
388
+ },
389
+ {
390
+ "epoch": 1.08,
391
+ "grad_norm": 1.8223835701505764,
392
+ "learning_rate": 1.7542941299142113e-05,
393
+ "loss": 0.3964,
394
+ "step": 55
395
+ },
396
+ {
397
+ "epoch": 1.1,
398
+ "grad_norm": 2.0376834810173623,
399
+ "learning_rate": 1.7435077792448666e-05,
400
+ "loss": 0.3912,
401
+ "step": 56
402
+ },
403
+ {
404
+ "epoch": 1.12,
405
+ "grad_norm": 1.9367444811085355,
406
+ "learning_rate": 1.7325244309212476e-05,
407
+ "loss": 0.3652,
408
+ "step": 57
409
+ },
410
+ {
411
+ "epoch": 1.14,
412
+ "grad_norm": 2.0044934340131806,
413
+ "learning_rate": 1.7213469950593156e-05,
414
+ "loss": 0.406,
415
+ "step": 58
416
+ },
417
+ {
418
+ "epoch": 1.16,
419
+ "grad_norm": 1.7651282767994878,
420
+ "learning_rate": 1.709978433199901e-05,
421
+ "loss": 0.3607,
422
+ "step": 59
423
+ },
424
+ {
425
+ "epoch": 1.18,
426
+ "grad_norm": 1.9042056017789768,
427
+ "learning_rate": 1.6984217575240212e-05,
428
+ "loss": 0.3984,
429
+ "step": 60
430
+ },
431
+ {
432
+ "epoch": 1.2,
433
+ "grad_norm": 1.8589445625686343,
434
+ "learning_rate": 1.6866800300547814e-05,
435
+ "loss": 0.3906,
436
+ "step": 61
437
+ },
438
+ {
439
+ "epoch": 1.22,
440
+ "grad_norm": 2.0540269145149384,
441
+ "learning_rate": 1.674756361846071e-05,
442
+ "loss": 0.4072,
443
+ "step": 62
444
+ },
445
+ {
446
+ "epoch": 1.24,
447
+ "grad_norm": 1.8054523911306564,
448
+ "learning_rate": 1.6626539121582687e-05,
449
+ "loss": 0.3643,
450
+ "step": 63
451
+ },
452
+ {
453
+ "epoch": 1.25,
454
+ "grad_norm": 1.8676585477146084,
455
+ "learning_rate": 1.650375887621171e-05,
456
+ "loss": 0.4015,
457
+ "step": 64
458
+ },
459
+ {
460
+ "epoch": 1.27,
461
+ "grad_norm": 1.819143157098772,
462
+ "learning_rate": 1.637925541384375e-05,
463
+ "loss": 0.3769,
464
+ "step": 65
465
+ },
466
+ {
467
+ "epoch": 1.29,
468
+ "grad_norm": 1.7391959194884734,
469
+ "learning_rate": 1.6253061722553353e-05,
470
+ "loss": 0.3937,
471
+ "step": 66
472
+ },
473
+ {
474
+ "epoch": 1.31,
475
+ "grad_norm": 1.8992984530610373,
476
+ "learning_rate": 1.612521123825317e-05,
477
+ "loss": 0.3879,
478
+ "step": 67
479
+ },
480
+ {
481
+ "epoch": 1.33,
482
+ "grad_norm": 1.8399116519781489,
483
+ "learning_rate": 1.5995737835834905e-05,
484
+ "loss": 0.3796,
485
+ "step": 68
486
+ },
487
+ {
488
+ "epoch": 1.35,
489
+ "grad_norm": 1.744045618081832,
490
+ "learning_rate": 1.586467582019392e-05,
491
+ "loss": 0.3615,
492
+ "step": 69
493
+ },
494
+ {
495
+ "epoch": 1.37,
496
+ "grad_norm": 1.732449536710179,
497
+ "learning_rate": 1.5732059917139912e-05,
498
+ "loss": 0.3807,
499
+ "step": 70
500
+ },
501
+ {
502
+ "epoch": 1.39,
503
+ "grad_norm": 1.8491352122059705,
504
+ "learning_rate": 1.5597925264196048e-05,
505
+ "loss": 0.3554,
506
+ "step": 71
507
+ },
508
+ {
509
+ "epoch": 1.41,
510
+ "grad_norm": 1.7969522210818722,
511
+ "learning_rate": 1.546230740128904e-05,
512
+ "loss": 0.369,
513
+ "step": 72
514
+ },
515
+ {
516
+ "epoch": 1.43,
517
+ "grad_norm": 1.8026036373190188,
518
+ "learning_rate": 1.53252422613326e-05,
519
+ "loss": 0.3757,
520
+ "step": 73
521
+ },
522
+ {
523
+ "epoch": 1.45,
524
+ "grad_norm": 1.7840199265885361,
525
+ "learning_rate": 1.5186766160706738e-05,
526
+ "loss": 0.4167,
527
+ "step": 74
528
+ },
529
+ {
530
+ "epoch": 1.47,
531
+ "grad_norm": 1.7787153715407427,
532
+ "learning_rate": 1.504691578963549e-05,
533
+ "loss": 0.3474,
534
+ "step": 75
535
+ },
536
+ {
537
+ "epoch": 1.49,
538
+ "grad_norm": 1.8175150450617676,
539
+ "learning_rate": 1.4905728202465596e-05,
540
+ "loss": 0.3764,
541
+ "step": 76
542
+ },
543
+ {
544
+ "epoch": 1.51,
545
+ "grad_norm": 1.8592965886869042,
546
+ "learning_rate": 1.4763240807848667e-05,
547
+ "loss": 0.3993,
548
+ "step": 77
549
+ },
550
+ {
551
+ "epoch": 1.53,
552
+ "grad_norm": 1.861633852080652,
553
+ "learning_rate": 1.4619491358829502e-05,
554
+ "loss": 0.3844,
555
+ "step": 78
556
+ },
557
+ {
558
+ "epoch": 1.55,
559
+ "grad_norm": 1.7028160864977242,
560
+ "learning_rate": 1.4474517942843173e-05,
561
+ "loss": 0.3896,
562
+ "step": 79
563
+ },
564
+ {
565
+ "epoch": 1.57,
566
+ "grad_norm": 1.7419533336971356,
567
+ "learning_rate": 1.4328358971623455e-05,
568
+ "loss": 0.3558,
569
+ "step": 80
570
+ },
571
+ {
572
+ "epoch": 1.59,
573
+ "grad_norm": 1.663271147203201,
574
+ "learning_rate": 1.4181053171025392e-05,
575
+ "loss": 0.3551,
576
+ "step": 81
577
+ },
578
+ {
579
+ "epoch": 1.61,
580
+ "grad_norm": 1.6863853163892444,
581
+ "learning_rate": 1.4032639570764595e-05,
582
+ "loss": 0.3337,
583
+ "step": 82
584
+ },
585
+ {
586
+ "epoch": 1.63,
587
+ "grad_norm": 1.793591094205731,
588
+ "learning_rate": 1.3883157494076048e-05,
589
+ "loss": 0.3781,
590
+ "step": 83
591
+ },
592
+ {
593
+ "epoch": 1.65,
594
+ "grad_norm": 1.6945142844490944,
595
+ "learning_rate": 1.3732646547295128e-05,
596
+ "loss": 0.4093,
597
+ "step": 84
598
+ },
599
+ {
600
+ "epoch": 1.67,
601
+ "grad_norm": 1.8592456163542173,
602
+ "learning_rate": 1.358114660936364e-05,
603
+ "loss": 0.3814,
604
+ "step": 85
605
+ },
606
+ {
607
+ "epoch": 1.69,
608
+ "grad_norm": 1.6574433544024902,
609
+ "learning_rate": 1.34286978212636e-05,
610
+ "loss": 0.3578,
611
+ "step": 86
612
+ },
613
+ {
614
+ "epoch": 1.71,
615
+ "grad_norm": 1.7633364539067733,
616
+ "learning_rate": 1.32753405753816e-05,
617
+ "loss": 0.3856,
618
+ "step": 87
619
+ },
620
+ {
621
+ "epoch": 1.73,
622
+ "grad_norm": 1.8239540708598452,
623
+ "learning_rate": 1.3121115504806554e-05,
624
+ "loss": 0.3644,
625
+ "step": 88
626
+ },
627
+ {
628
+ "epoch": 1.75,
629
+ "grad_norm": 1.7596504605594738,
630
+ "learning_rate": 1.2966063472563686e-05,
631
+ "loss": 0.3591,
632
+ "step": 89
633
+ },
634
+ {
635
+ "epoch": 1.76,
636
+ "grad_norm": 1.5895053962743115,
637
+ "learning_rate": 1.2810225560787561e-05,
638
+ "loss": 0.3588,
639
+ "step": 90
640
+ },
641
+ {
642
+ "epoch": 1.78,
643
+ "grad_norm": 1.6063701391748393,
644
+ "learning_rate": 1.2653643059837109e-05,
645
+ "loss": 0.3653,
646
+ "step": 91
647
+ },
648
+ {
649
+ "epoch": 1.8,
650
+ "grad_norm": 1.635228537006481,
651
+ "learning_rate": 1.2496357457355423e-05,
652
+ "loss": 0.3827,
653
+ "step": 92
654
+ },
655
+ {
656
+ "epoch": 1.82,
657
+ "grad_norm": 1.5414929249094127,
658
+ "learning_rate": 1.2338410427277342e-05,
659
+ "loss": 0.3378,
660
+ "step": 93
661
+ },
662
+ {
663
+ "epoch": 1.84,
664
+ "grad_norm": 1.4758404777924012,
665
+ "learning_rate": 1.2179843818787625e-05,
666
+ "loss": 0.3325,
667
+ "step": 94
668
+ },
669
+ {
670
+ "epoch": 1.86,
671
+ "grad_norm": 1.6415892900669684,
672
+ "learning_rate": 1.202069964523272e-05,
673
+ "loss": 0.3811,
674
+ "step": 95
675
+ },
676
+ {
677
+ "epoch": 1.88,
678
+ "grad_norm": 1.523419893603189,
679
+ "learning_rate": 1.186102007298904e-05,
680
+ "loss": 0.3241,
681
+ "step": 96
682
+ },
683
+ {
684
+ "epoch": 1.9,
685
+ "grad_norm": 1.6484777075035715,
686
+ "learning_rate": 1.1700847410290667e-05,
687
+ "loss": 0.3702,
688
+ "step": 97
689
+ },
690
+ {
691
+ "epoch": 1.92,
692
+ "grad_norm": 1.5525179346249605,
693
+ "learning_rate": 1.1540224096019495e-05,
694
+ "loss": 0.3619,
695
+ "step": 98
696
+ },
697
+ {
698
+ "epoch": 1.94,
699
+ "grad_norm": 1.516882070329218,
700
+ "learning_rate": 1.137919268846074e-05,
701
+ "loss": 0.3581,
702
+ "step": 99
703
+ },
704
+ {
705
+ "epoch": 1.96,
706
+ "grad_norm": 1.56335517369179,
707
+ "learning_rate": 1.121779585402684e-05,
708
+ "loss": 0.3549,
709
+ "step": 100
710
+ },
711
+ {
712
+ "epoch": 1.98,
713
+ "grad_norm": 1.521782470020805,
714
+ "learning_rate": 1.105607635595266e-05,
715
+ "loss": 0.3477,
716
+ "step": 101
717
+ },
718
+ {
719
+ "epoch": 2.0,
720
+ "grad_norm": 1.3640551624778041,
721
+ "learning_rate": 1.0894077042965084e-05,
722
+ "loss": 0.2394,
723
+ "step": 102
724
+ },
725
+ {
726
+ "epoch": 2.02,
727
+ "grad_norm": 1.444257443908557,
728
+ "learning_rate": 1.0731840837929946e-05,
729
+ "loss": 0.1767,
730
+ "step": 103
731
+ },
732
+ {
733
+ "epoch": 2.04,
734
+ "grad_norm": 1.482114013548794,
735
+ "learning_rate": 1.0569410726479301e-05,
736
+ "loss": 0.183,
737
+ "step": 104
738
+ },
739
+ {
740
+ "epoch": 2.06,
741
+ "grad_norm": 1.3296971608762402,
742
+ "learning_rate": 1.0406829745622085e-05,
743
+ "loss": 0.1774,
744
+ "step": 105
745
+ },
746
+ {
747
+ "epoch": 2.08,
748
+ "grad_norm": 1.2009794251635362,
749
+ "learning_rate": 1.0244140972341155e-05,
750
+ "loss": 0.1712,
751
+ "step": 106
752
+ },
753
+ {
754
+ "epoch": 2.1,
755
+ "grad_norm": 1.14191410951918,
756
+ "learning_rate": 1.008138751217973e-05,
757
+ "loss": 0.1463,
758
+ "step": 107
759
+ },
760
+ {
761
+ "epoch": 2.12,
762
+ "grad_norm": 1.2767421227177214,
763
+ "learning_rate": 9.918612487820274e-06,
764
+ "loss": 0.1701,
765
+ "step": 108
766
+ },
767
+ {
768
+ "epoch": 2.14,
769
+ "grad_norm": 1.1705901668353922,
770
+ "learning_rate": 9.755859027658848e-06,
771
+ "loss": 0.1435,
772
+ "step": 109
773
+ },
774
+ {
775
+ "epoch": 2.16,
776
+ "grad_norm": 1.3281334820644817,
777
+ "learning_rate": 9.593170254377915e-06,
778
+ "loss": 0.1743,
779
+ "step": 110
780
+ },
781
+ {
782
+ "epoch": 2.18,
783
+ "grad_norm": 1.280366732691976,
784
+ "learning_rate": 9.430589273520704e-06,
785
+ "loss": 0.1508,
786
+ "step": 111
787
+ },
788
+ {
789
+ "epoch": 2.2,
790
+ "grad_norm": 1.3111725861250203,
791
+ "learning_rate": 9.268159162070058e-06,
792
+ "loss": 0.1544,
793
+ "step": 112
794
+ },
795
+ {
796
+ "epoch": 2.22,
797
+ "grad_norm": 1.3647916018519441,
798
+ "learning_rate": 9.105922957034921e-06,
799
+ "loss": 0.1679,
800
+ "step": 113
801
+ },
802
+ {
803
+ "epoch": 2.24,
804
+ "grad_norm": 1.2719254204880934,
805
+ "learning_rate": 8.943923644047343e-06,
806
+ "loss": 0.1553,
807
+ "step": 114
808
+ },
809
+ {
810
+ "epoch": 2.25,
811
+ "grad_norm": 1.3747641621255784,
812
+ "learning_rate": 8.782204145973162e-06,
813
+ "loss": 0.1753,
814
+ "step": 115
815
+ },
816
+ {
817
+ "epoch": 2.27,
818
+ "grad_norm": 1.2489287077269695,
819
+ "learning_rate": 8.620807311539258e-06,
820
+ "loss": 0.164,
821
+ "step": 116
822
+ },
823
+ {
824
+ "epoch": 2.29,
825
+ "grad_norm": 1.1953887915106376,
826
+ "learning_rate": 8.45977590398051e-06,
827
+ "loss": 0.1537,
828
+ "step": 117
829
+ },
830
+ {
831
+ "epoch": 2.31,
832
+ "grad_norm": 1.2483013054915837,
833
+ "learning_rate": 8.299152589709336e-06,
834
+ "loss": 0.1627,
835
+ "step": 118
836
+ },
837
+ {
838
+ "epoch": 2.33,
839
+ "grad_norm": 1.1082607637515602,
840
+ "learning_rate": 8.138979927010964e-06,
841
+ "loss": 0.1505,
842
+ "step": 119
843
+ },
844
+ {
845
+ "epoch": 2.35,
846
+ "grad_norm": 1.1877785406198442,
847
+ "learning_rate": 7.979300354767282e-06,
848
+ "loss": 0.1718,
849
+ "step": 120
850
+ },
851
+ {
852
+ "epoch": 2.37,
853
+ "grad_norm": 1.2007862495511872,
854
+ "learning_rate": 7.82015618121238e-06,
855
+ "loss": 0.1796,
856
+ "step": 121
857
+ },
858
+ {
859
+ "epoch": 2.39,
860
+ "grad_norm": 1.268623285589921,
861
+ "learning_rate": 7.66158957272266e-06,
862
+ "loss": 0.1713,
863
+ "step": 122
864
+ },
865
+ {
866
+ "epoch": 2.41,
867
+ "grad_norm": 1.2625050648502694,
868
+ "learning_rate": 7.503642542644581e-06,
869
+ "loss": 0.1719,
870
+ "step": 123
871
+ },
872
+ {
873
+ "epoch": 2.43,
874
+ "grad_norm": 1.1282996425547969,
875
+ "learning_rate": 7.346356940162895e-06,
876
+ "loss": 0.1598,
877
+ "step": 124
878
+ },
879
+ {
880
+ "epoch": 2.45,
881
+ "grad_norm": 1.138917768830711,
882
+ "learning_rate": 7.189774439212442e-06,
883
+ "loss": 0.1576,
884
+ "step": 125
885
+ },
886
+ {
887
+ "epoch": 2.47,
888
+ "grad_norm": 1.1962501488409478,
889
+ "learning_rate": 7.033936527436318e-06,
890
+ "loss": 0.1762,
891
+ "step": 126
892
+ },
893
+ {
894
+ "epoch": 2.49,
895
+ "grad_norm": 1.19112885794854,
896
+ "learning_rate": 6.878884495193448e-06,
897
+ "loss": 0.1749,
898
+ "step": 127
899
+ },
900
+ {
901
+ "epoch": 2.51,
902
+ "grad_norm": 1.173014938321161,
903
+ "learning_rate": 6.724659424618401e-06,
904
+ "loss": 0.1596,
905
+ "step": 128
906
+ },
907
+ {
908
+ "epoch": 2.53,
909
+ "grad_norm": 1.177107256530893,
910
+ "learning_rate": 6.571302178736404e-06,
911
+ "loss": 0.1646,
912
+ "step": 129
913
+ },
914
+ {
915
+ "epoch": 2.55,
916
+ "grad_norm": 1.050951011586738,
917
+ "learning_rate": 6.418853390636363e-06,
918
+ "loss": 0.1592,
919
+ "step": 130
920
+ },
921
+ {
922
+ "epoch": 2.57,
923
+ "grad_norm": 1.1776390226869722,
924
+ "learning_rate": 6.267353452704876e-06,
925
+ "loss": 0.1567,
926
+ "step": 131
927
+ },
928
+ {
929
+ "epoch": 2.59,
930
+ "grad_norm": 1.0758437748665028,
931
+ "learning_rate": 6.116842505923955e-06,
932
+ "loss": 0.154,
933
+ "step": 132
934
+ },
935
+ {
936
+ "epoch": 2.61,
937
+ "grad_norm": 1.0784529587978813,
938
+ "learning_rate": 5.967360429235407e-06,
939
+ "loss": 0.1561,
940
+ "step": 133
941
+ },
942
+ {
943
+ "epoch": 2.63,
944
+ "grad_norm": 1.1696386233204266,
945
+ "learning_rate": 5.8189468289746075e-06,
946
+ "loss": 0.159,
947
+ "step": 134
948
+ },
949
+ {
950
+ "epoch": 2.65,
951
+ "grad_norm": 1.1371629509054215,
952
+ "learning_rate": 5.671641028376547e-06,
953
+ "loss": 0.1574,
954
+ "step": 135
955
+ },
956
+ {
957
+ "epoch": 2.67,
958
+ "grad_norm": 1.0887944902862232,
959
+ "learning_rate": 5.525482057156833e-06,
960
+ "loss": 0.1547,
961
+ "step": 136
962
+ },
963
+ {
964
+ "epoch": 2.69,
965
+ "grad_norm": 1.207419126341501,
966
+ "learning_rate": 5.380508641170499e-06,
967
+ "loss": 0.162,
968
+ "step": 137
969
+ },
970
+ {
971
+ "epoch": 2.71,
972
+ "grad_norm": 1.0198211842292424,
973
+ "learning_rate": 5.236759192151336e-06,
974
+ "loss": 0.1537,
975
+ "step": 138
976
+ },
977
+ {
978
+ "epoch": 2.73,
979
+ "grad_norm": 1.1458982044698929,
980
+ "learning_rate": 5.094271797534404e-06,
981
+ "loss": 0.1521,
982
+ "step": 139
983
+ },
984
+ {
985
+ "epoch": 2.75,
986
+ "grad_norm": 1.099882752498822,
987
+ "learning_rate": 4.953084210364508e-06,
988
+ "loss": 0.15,
989
+ "step": 140
990
+ },
991
+ {
992
+ "epoch": 2.76,
993
+ "grad_norm": 1.139969519826751,
994
+ "learning_rate": 4.813233839293265e-06,
995
+ "loss": 0.1593,
996
+ "step": 141
997
+ },
998
+ {
999
+ "epoch": 2.78,
1000
+ "grad_norm": 1.0693934037605295,
1001
+ "learning_rate": 4.674757738667405e-06,
1002
+ "loss": 0.154,
1003
+ "step": 142
1004
+ },
1005
+ {
1006
+ "epoch": 2.8,
1007
+ "grad_norm": 1.1635281149070174,
1008
+ "learning_rate": 4.537692598710962e-06,
1009
+ "loss": 0.1692,
1010
+ "step": 143
1011
+ },
1012
+ {
1013
+ "epoch": 2.82,
1014
+ "grad_norm": 1.04490476219924,
1015
+ "learning_rate": 4.402074735803955e-06,
1016
+ "loss": 0.147,
1017
+ "step": 144
1018
+ },
1019
+ {
1020
+ "epoch": 2.84,
1021
+ "grad_norm": 1.0932888148614304,
1022
+ "learning_rate": 4.267940082860088e-06,
1023
+ "loss": 0.1498,
1024
+ "step": 145
1025
+ },
1026
+ {
1027
+ "epoch": 2.86,
1028
+ "grad_norm": 1.1168758784687194,
1029
+ "learning_rate": 4.135324179806079e-06,
1030
+ "loss": 0.1499,
1031
+ "step": 146
1032
+ },
1033
+ {
1034
+ "epoch": 2.88,
1035
+ "grad_norm": 1.1217893774994945,
1036
+ "learning_rate": 4.004262164165098e-06,
1037
+ "loss": 0.1596,
1038
+ "step": 147
1039
+ },
1040
+ {
1041
+ "epoch": 2.9,
1042
+ "grad_norm": 1.0376730211600298,
1043
+ "learning_rate": 3.874788761746836e-06,
1044
+ "loss": 0.1524,
1045
+ "step": 148
1046
+ },
1047
+ {
1048
+ "epoch": 2.92,
1049
+ "grad_norm": 1.1181081966120519,
1050
+ "learning_rate": 3.74693827744665e-06,
1051
+ "loss": 0.1426,
1052
+ "step": 149
1053
+ },
1054
+ {
1055
+ "epoch": 2.94,
1056
+ "grad_norm": 1.158024328625209,
1057
+ "learning_rate": 3.6207445861562497e-06,
1058
+ "loss": 0.1673,
1059
+ "step": 150
1060
+ },
1061
+ {
1062
+ "epoch": 2.96,
1063
+ "grad_norm": 1.1391490636515222,
1064
+ "learning_rate": 3.4962411237882945e-06,
1065
+ "loss": 0.1486,
1066
+ "step": 151
1067
+ },
1068
+ {
1069
+ "epoch": 2.98,
1070
+ "grad_norm": 1.0483715121883341,
1071
+ "learning_rate": 3.373460878417315e-06,
1072
+ "loss": 0.1563,
1073
+ "step": 152
1074
+ },
1075
+ {
1076
+ "epoch": 3.0,
1077
+ "grad_norm": 0.8483422663230202,
1078
+ "learning_rate": 3.252436381539291e-06,
1079
+ "loss": 0.1084,
1080
+ "step": 153
1081
+ }
1082
+ ],
1083
+ "logging_steps": 1,
1084
+ "max_steps": 204,
1085
+ "num_input_tokens_seen": 0,
1086
+ "num_train_epochs": 4,
1087
+ "save_steps": 500,
1088
+ "total_flos": 46868594688000.0,
1089
+ "train_batch_size": 16,
1090
+ "trial_name": null,
1091
+ "trial_params": null
1092
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:11384a5af87d4c9a05623cd50f836aed6f147d515b61d9fb4acdf73cdd442f1e
3
+ size 7160
vocab.json ADDED
The diff for this file is too large to render. See raw diff