cminja commited on
Commit
10834c6
1 Parent(s): 893d107

Upload directory using huggingface_hub lfs

Browse files
all_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "train_loss": 0.6362597953351998,
4
+ "train_runtime": 82257.6345,
5
+ "train_samples": 1226825,
6
+ "train_samples_per_second": 0.673,
7
+ "train_steps_per_second": 0.011
8
+ }
config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "mistral-community/Mixtral-8x22B-v0.1",
3
+ "architectures": [
4
+ "MixtralForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 2,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 6144,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 16384,
13
+ "max_position_embeddings": 65536,
14
+ "model_type": "mixtral",
15
+ "num_attention_heads": 48,
16
+ "num_experts_per_tok": 2,
17
+ "num_hidden_layers": 56,
18
+ "num_key_value_heads": 8,
19
+ "num_local_experts": 8,
20
+ "output_router_logits": false,
21
+ "rms_norm_eps": 1e-05,
22
+ "rope_theta": 1000000,
23
+ "router_aux_loss_coef": 0.001,
24
+ "router_jitter_noise": 0.0,
25
+ "sliding_window": null,
26
+ "tie_word_embeddings": false,
27
+ "torch_dtype": "bfloat16",
28
+ "transformers_version": "4.39.3",
29
+ "use_cache": true,
30
+ "vocab_size": 32000
31
+ }
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": "4.39.3"
6
+ }
model-00051-of-00059.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:81b486ba3607a9262fcaad605039882e7c1b25cabeb116ad46ec836f779d24a7
3
+ size 4806799152
model-00052-of-00059.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d07969c7cb6c3af9f9b27d175c028d21c619540dd4e37e13dd2e7152009d3f27
3
+ size 4932529864
model-00053-of-00059.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd62978178c01dc9882c729bc9e074cee99fbfc65139d673791bf519c1ececdc
3
+ size 4995542848
model-00054-of-00059.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7dc49deda94d6751a576ee05e8387ba1918849b722b14ea42ec3dbdc0739d456
3
+ size 4995542848
model-00055-of-00059.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:904d647e9031f4cc2523aa7a5fe399ad18d76780234bb00550dd1d2a7a5248f7
3
+ size 4932628288
model-00056-of-00059.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b1eecf512d491f7030ff30e90d607a7ef33397f8d40933ce5b30d3da3202608
3
+ size 4806774344
model-00057-of-00059.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c922476a8513e690cd220da6641ac2f48c9b0e64159762a6e72b32dd73e3c8d2
3
+ size 4806799144
model-00058-of-00059.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad1f36357d70adb3f10eeb1d93edca733b10d388fe41f04aa5292dd64e287b77
3
+ size 4806799144
model-00059-of-00059.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d5c1638c7da286c33ce46569a0100877da1beae9432e346b194e10b86deac439
3
+ size 997233472
model.safetensors.index.json ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "</s>",
17
+ "unk_token": {
18
+ "content": "<unk>",
19
+ "lstrip": false,
20
+ "normalized": false,
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.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
3
+ size 493443
tokenizer_config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<unk>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ }
29
+ },
30
+ "additional_special_tokens": [],
31
+ "bos_token": "<s>",
32
+ "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n' + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
33
+ "clean_up_tokenization_spaces": false,
34
+ "eos_token": "</s>",
35
+ "legacy": true,
36
+ "model_max_length": 1000000000000000019884624838656,
37
+ "pad_token": "</s>",
38
+ "sp_model_kwargs": {},
39
+ "spaces_between_special_tokens": false,
40
+ "tokenizer_class": "LlamaTokenizer",
41
+ "unk_token": "<unk>",
42
+ "use_default_system_prompt": false
43
+ }
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 3.0,
3
+ "train_loss": 0.6362597953351998,
4
+ "train_runtime": 82257.6345,
5
+ "train_samples": 1226825,
6
+ "train_samples_per_second": 0.673,
7
+ "train_steps_per_second": 0.011
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,639 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 867,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.0,
13
+ "grad_norm": 2302102470656.0,
14
+ "learning_rate": 2.0000000000000002e-07,
15
+ "loss": 1.4692,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.03,
20
+ "grad_norm": 64.5,
21
+ "learning_rate": 2.0000000000000003e-06,
22
+ "loss": 1.3652,
23
+ "step": 10
24
+ },
25
+ {
26
+ "epoch": 0.07,
27
+ "grad_norm": 31.75,
28
+ "learning_rate": 4.000000000000001e-06,
29
+ "loss": 1.0755,
30
+ "step": 20
31
+ },
32
+ {
33
+ "epoch": 0.1,
34
+ "grad_norm": 13.875,
35
+ "learning_rate": 6e-06,
36
+ "loss": 0.9346,
37
+ "step": 30
38
+ },
39
+ {
40
+ "epoch": 0.14,
41
+ "grad_norm": 5.6875,
42
+ "learning_rate": 8.000000000000001e-06,
43
+ "loss": 0.8498,
44
+ "step": 40
45
+ },
46
+ {
47
+ "epoch": 0.17,
48
+ "grad_norm": 2.15625,
49
+ "learning_rate": 1e-05,
50
+ "loss": 0.7883,
51
+ "step": 50
52
+ },
53
+ {
54
+ "epoch": 0.21,
55
+ "grad_norm": 0.609375,
56
+ "learning_rate": 9.996303913492409e-06,
57
+ "loss": 0.7522,
58
+ "step": 60
59
+ },
60
+ {
61
+ "epoch": 0.24,
62
+ "grad_norm": 0.390625,
63
+ "learning_rate": 9.98522111839182e-06,
64
+ "loss": 0.7332,
65
+ "step": 70
66
+ },
67
+ {
68
+ "epoch": 0.28,
69
+ "grad_norm": 0.515625,
70
+ "learning_rate": 9.966767999886013e-06,
71
+ "loss": 0.719,
72
+ "step": 80
73
+ },
74
+ {
75
+ "epoch": 0.31,
76
+ "grad_norm": 0.341796875,
77
+ "learning_rate": 9.940971839703916e-06,
78
+ "loss": 0.7081,
79
+ "step": 90
80
+ },
81
+ {
82
+ "epoch": 0.35,
83
+ "grad_norm": 0.328125,
84
+ "learning_rate": 9.907870775781371e-06,
85
+ "loss": 0.698,
86
+ "step": 100
87
+ },
88
+ {
89
+ "epoch": 0.38,
90
+ "grad_norm": 0.400390625,
91
+ "learning_rate": 9.867513745876677e-06,
92
+ "loss": 0.6932,
93
+ "step": 110
94
+ },
95
+ {
96
+ "epoch": 0.42,
97
+ "grad_norm": 0.33984375,
98
+ "learning_rate": 9.819960415219321e-06,
99
+ "loss": 0.6926,
100
+ "step": 120
101
+ },
102
+ {
103
+ "epoch": 0.45,
104
+ "grad_norm": 0.330078125,
105
+ "learning_rate": 9.765281088298837e-06,
106
+ "loss": 0.6933,
107
+ "step": 130
108
+ },
109
+ {
110
+ "epoch": 0.48,
111
+ "grad_norm": 0.349609375,
112
+ "learning_rate": 9.703556604924217e-06,
113
+ "loss": 0.6853,
114
+ "step": 140
115
+ },
116
+ {
117
+ "epoch": 0.52,
118
+ "grad_norm": 0.345703125,
119
+ "learning_rate": 9.634878220707531e-06,
120
+ "loss": 0.6788,
121
+ "step": 150
122
+ },
123
+ {
124
+ "epoch": 0.55,
125
+ "grad_norm": 0.349609375,
126
+ "learning_rate": 9.55934747214849e-06,
127
+ "loss": 0.6755,
128
+ "step": 160
129
+ },
130
+ {
131
+ "epoch": 0.59,
132
+ "grad_norm": 0.36328125,
133
+ "learning_rate": 9.477076026519357e-06,
134
+ "loss": 0.673,
135
+ "step": 170
136
+ },
137
+ {
138
+ "epoch": 0.62,
139
+ "grad_norm": 0.32421875,
140
+ "learning_rate": 9.38818551677219e-06,
141
+ "loss": 0.6742,
142
+ "step": 180
143
+ },
144
+ {
145
+ "epoch": 0.66,
146
+ "grad_norm": 0.326171875,
147
+ "learning_rate": 9.292807361712482e-06,
148
+ "loss": 0.667,
149
+ "step": 190
150
+ },
151
+ {
152
+ "epoch": 0.69,
153
+ "grad_norm": 0.32421875,
154
+ "learning_rate": 9.191082571705047e-06,
155
+ "loss": 0.6642,
156
+ "step": 200
157
+ },
158
+ {
159
+ "epoch": 0.73,
160
+ "grad_norm": 1.015625,
161
+ "learning_rate": 9.083161540199417e-06,
162
+ "loss": 0.658,
163
+ "step": 210
164
+ },
165
+ {
166
+ "epoch": 0.76,
167
+ "grad_norm": 0.34375,
168
+ "learning_rate": 8.969203821382969e-06,
169
+ "loss": 0.6579,
170
+ "step": 220
171
+ },
172
+ {
173
+ "epoch": 0.8,
174
+ "grad_norm": 0.88671875,
175
+ "learning_rate": 8.849377894290481e-06,
176
+ "loss": 0.6584,
177
+ "step": 230
178
+ },
179
+ {
180
+ "epoch": 0.83,
181
+ "grad_norm": 0.345703125,
182
+ "learning_rate": 8.72386091371891e-06,
183
+ "loss": 0.6539,
184
+ "step": 240
185
+ },
186
+ {
187
+ "epoch": 0.87,
188
+ "grad_norm": 0.3125,
189
+ "learning_rate": 8.5928384483156e-06,
190
+ "loss": 0.6503,
191
+ "step": 250
192
+ },
193
+ {
194
+ "epoch": 0.9,
195
+ "grad_norm": 0.32421875,
196
+ "learning_rate": 8.456504206227178e-06,
197
+ "loss": 0.649,
198
+ "step": 260
199
+ },
200
+ {
201
+ "epoch": 0.93,
202
+ "grad_norm": 0.322265625,
203
+ "learning_rate": 8.315059748714728e-06,
204
+ "loss": 0.6478,
205
+ "step": 270
206
+ },
207
+ {
208
+ "epoch": 0.97,
209
+ "grad_norm": 0.337890625,
210
+ "learning_rate": 8.168714192158645e-06,
211
+ "loss": 0.648,
212
+ "step": 280
213
+ },
214
+ {
215
+ "epoch": 1.0,
216
+ "grad_norm": 0.65234375,
217
+ "learning_rate": 8.017683898893739e-06,
218
+ "loss": 0.6462,
219
+ "step": 290
220
+ },
221
+ {
222
+ "epoch": 1.04,
223
+ "grad_norm": 0.388671875,
224
+ "learning_rate": 7.86219215733168e-06,
225
+ "loss": 0.6114,
226
+ "step": 300
227
+ },
228
+ {
229
+ "epoch": 1.07,
230
+ "grad_norm": 0.34375,
231
+ "learning_rate": 7.702468851843681e-06,
232
+ "loss": 0.6114,
233
+ "step": 310
234
+ },
235
+ {
236
+ "epoch": 1.11,
237
+ "grad_norm": 0.4140625,
238
+ "learning_rate": 7.538750122891489e-06,
239
+ "loss": 0.6056,
240
+ "step": 320
241
+ },
242
+ {
243
+ "epoch": 1.14,
244
+ "grad_norm": 0.3359375,
245
+ "learning_rate": 7.3712780179091495e-06,
246
+ "loss": 0.6024,
247
+ "step": 330
248
+ },
249
+ {
250
+ "epoch": 1.18,
251
+ "grad_norm": 0.310546875,
252
+ "learning_rate": 7.200300133451712e-06,
253
+ "loss": 0.6029,
254
+ "step": 340
255
+ },
256
+ {
257
+ "epoch": 1.21,
258
+ "grad_norm": 0.33203125,
259
+ "learning_rate": 7.026069249139914e-06,
260
+ "loss": 0.6017,
261
+ "step": 350
262
+ },
263
+ {
264
+ "epoch": 1.25,
265
+ "grad_norm": 0.3125,
266
+ "learning_rate": 6.848842953942037e-06,
267
+ "loss": 0.6027,
268
+ "step": 360
269
+ },
270
+ {
271
+ "epoch": 1.28,
272
+ "grad_norm": 0.333984375,
273
+ "learning_rate": 6.668883265345471e-06,
274
+ "loss": 0.6033,
275
+ "step": 370
276
+ },
277
+ {
278
+ "epoch": 1.31,
279
+ "grad_norm": 0.3046875,
280
+ "learning_rate": 6.486456241980991e-06,
281
+ "loss": 0.602,
282
+ "step": 380
283
+ },
284
+ {
285
+ "epoch": 1.35,
286
+ "grad_norm": 0.30859375,
287
+ "learning_rate": 6.301831590272465e-06,
288
+ "loss": 0.5973,
289
+ "step": 390
290
+ },
291
+ {
292
+ "epoch": 1.38,
293
+ "grad_norm": 0.302734375,
294
+ "learning_rate": 6.115282265693554e-06,
295
+ "loss": 0.5944,
296
+ "step": 400
297
+ },
298
+ {
299
+ "epoch": 1.42,
300
+ "grad_norm": 0.310546875,
301
+ "learning_rate": 5.927084069220888e-06,
302
+ "loss": 0.6024,
303
+ "step": 410
304
+ },
305
+ {
306
+ "epoch": 1.45,
307
+ "grad_norm": 0.322265625,
308
+ "learning_rate": 5.737515239580362e-06,
309
+ "loss": 0.5937,
310
+ "step": 420
311
+ },
312
+ {
313
+ "epoch": 1.49,
314
+ "grad_norm": 0.318359375,
315
+ "learning_rate": 5.546856041889374e-06,
316
+ "loss": 0.5952,
317
+ "step": 430
318
+ },
319
+ {
320
+ "epoch": 1.52,
321
+ "grad_norm": 0.349609375,
322
+ "learning_rate": 5.355388353303175e-06,
323
+ "loss": 0.5964,
324
+ "step": 440
325
+ },
326
+ {
327
+ "epoch": 1.56,
328
+ "grad_norm": 0.296875,
329
+ "learning_rate": 5.163395246277938e-06,
330
+ "loss": 0.5926,
331
+ "step": 450
332
+ },
333
+ {
334
+ "epoch": 1.59,
335
+ "grad_norm": 0.296875,
336
+ "learning_rate": 4.971160570066631e-06,
337
+ "loss": 0.5947,
338
+ "step": 460
339
+ },
340
+ {
341
+ "epoch": 1.63,
342
+ "grad_norm": 0.30859375,
343
+ "learning_rate": 4.778968531066469e-06,
344
+ "loss": 0.5991,
345
+ "step": 470
346
+ },
347
+ {
348
+ "epoch": 1.66,
349
+ "grad_norm": 0.30859375,
350
+ "learning_rate": 4.587103272638339e-06,
351
+ "loss": 0.5935,
352
+ "step": 480
353
+ },
354
+ {
355
+ "epoch": 1.7,
356
+ "grad_norm": 0.298828125,
357
+ "learning_rate": 4.395848455019421e-06,
358
+ "loss": 0.5906,
359
+ "step": 490
360
+ },
361
+ {
362
+ "epoch": 1.73,
363
+ "grad_norm": 0.30078125,
364
+ "learning_rate": 4.205486835950081e-06,
365
+ "loss": 0.5977,
366
+ "step": 500
367
+ },
368
+ {
369
+ "epoch": 1.76,
370
+ "grad_norm": 0.35546875,
371
+ "learning_rate": 4.016299852635041e-06,
372
+ "loss": 0.5941,
373
+ "step": 510
374
+ },
375
+ {
376
+ "epoch": 1.8,
377
+ "grad_norm": 0.52734375,
378
+ "learning_rate": 3.828567205656877e-06,
379
+ "loss": 0.594,
380
+ "step": 520
381
+ },
382
+ {
383
+ "epoch": 1.83,
384
+ "grad_norm": 0.3125,
385
+ "learning_rate": 3.6425664454570016e-06,
386
+ "loss": 0.5967,
387
+ "step": 530
388
+ },
389
+ {
390
+ "epoch": 1.87,
391
+ "grad_norm": 0.298828125,
392
+ "learning_rate": 3.458572561995487e-06,
393
+ "loss": 0.592,
394
+ "step": 540
395
+ },
396
+ {
397
+ "epoch": 1.9,
398
+ "grad_norm": 0.3125,
399
+ "learning_rate": 3.276857578196388e-06,
400
+ "loss": 0.5952,
401
+ "step": 550
402
+ },
403
+ {
404
+ "epoch": 1.94,
405
+ "grad_norm": 0.29296875,
406
+ "learning_rate": 3.097690147779644e-06,
407
+ "loss": 0.5911,
408
+ "step": 560
409
+ },
410
+ {
411
+ "epoch": 1.97,
412
+ "grad_norm": 0.365234375,
413
+ "learning_rate": 2.9213351580741223e-06,
414
+ "loss": 0.5909,
415
+ "step": 570
416
+ },
417
+ {
418
+ "epoch": 2.01,
419
+ "grad_norm": 0.421875,
420
+ "learning_rate": 2.748053338399018e-06,
421
+ "loss": 0.5896,
422
+ "step": 580
423
+ },
424
+ {
425
+ "epoch": 2.04,
426
+ "grad_norm": 0.330078125,
427
+ "learning_rate": 2.5781008745926193e-06,
428
+ "loss": 0.5701,
429
+ "step": 590
430
+ },
431
+ {
432
+ "epoch": 2.08,
433
+ "grad_norm": 0.30078125,
434
+ "learning_rate": 2.4117290302582872e-06,
435
+ "loss": 0.577,
436
+ "step": 600
437
+ },
438
+ {
439
+ "epoch": 2.11,
440
+ "grad_norm": 0.291015625,
441
+ "learning_rate": 2.249183775287657e-06,
442
+ "loss": 0.5767,
443
+ "step": 610
444
+ },
445
+ {
446
+ "epoch": 2.15,
447
+ "grad_norm": 0.3046875,
448
+ "learning_rate": 2.0907054222102367e-06,
449
+ "loss": 0.5757,
450
+ "step": 620
451
+ },
452
+ {
453
+ "epoch": 2.18,
454
+ "grad_norm": 0.306640625,
455
+ "learning_rate": 1.936528270907049e-06,
456
+ "loss": 0.574,
457
+ "step": 630
458
+ },
459
+ {
460
+ "epoch": 2.21,
461
+ "grad_norm": 0.31640625,
462
+ "learning_rate": 1.7868802622135768e-06,
463
+ "loss": 0.5771,
464
+ "step": 640
465
+ },
466
+ {
467
+ "epoch": 2.25,
468
+ "grad_norm": 0.29296875,
469
+ "learning_rate": 1.6419826409241486e-06,
470
+ "loss": 0.5759,
471
+ "step": 650
472
+ },
473
+ {
474
+ "epoch": 2.28,
475
+ "grad_norm": 0.287109375,
476
+ "learning_rate": 1.5020496286959752e-06,
477
+ "loss": 0.5736,
478
+ "step": 660
479
+ },
480
+ {
481
+ "epoch": 2.32,
482
+ "grad_norm": 0.294921875,
483
+ "learning_rate": 1.3672881073364453e-06,
484
+ "loss": 0.5724,
485
+ "step": 670
486
+ },
487
+ {
488
+ "epoch": 2.35,
489
+ "grad_norm": 0.306640625,
490
+ "learning_rate": 1.2378973129418926e-06,
491
+ "loss": 0.5768,
492
+ "step": 680
493
+ },
494
+ {
495
+ "epoch": 2.39,
496
+ "grad_norm": 0.298828125,
497
+ "learning_rate": 1.1140685413400649e-06,
498
+ "loss": 0.5736,
499
+ "step": 690
500
+ },
501
+ {
502
+ "epoch": 2.42,
503
+ "grad_norm": 0.298828125,
504
+ "learning_rate": 9.95984865271749e-07,
505
+ "loss": 0.5768,
506
+ "step": 700
507
+ },
508
+ {
509
+ "epoch": 2.46,
510
+ "grad_norm": 0.30078125,
511
+ "learning_rate": 8.838208637296991e-07,
512
+ "loss": 0.5741,
513
+ "step": 710
514
+ },
515
+ {
516
+ "epoch": 2.49,
517
+ "grad_norm": 0.291015625,
518
+ "learning_rate": 7.777423638550097e-07,
519
+ "loss": 0.5779,
520
+ "step": 720
521
+ },
522
+ {
523
+ "epoch": 2.53,
524
+ "grad_norm": 0.291015625,
525
+ "learning_rate": 6.779061957725336e-07,
526
+ "loss": 0.5759,
527
+ "step": 730
528
+ },
529
+ {
530
+ "epoch": 2.56,
531
+ "grad_norm": 0.28125,
532
+ "learning_rate": 5.844599607277984e-07,
533
+ "loss": 0.5732,
534
+ "step": 740
535
+ },
536
+ {
537
+ "epoch": 2.6,
538
+ "grad_norm": 0.296875,
539
+ "learning_rate": 4.975418128682186e-07,
540
+ "loss": 0.5739,
541
+ "step": 750
542
+ },
543
+ {
544
+ "epoch": 2.63,
545
+ "grad_norm": 0.294921875,
546
+ "learning_rate": 4.1728025499122025e-07,
547
+ "loss": 0.5688,
548
+ "step": 760
549
+ },
550
+ {
551
+ "epoch": 2.66,
552
+ "grad_norm": 0.3125,
553
+ "learning_rate": 3.43793948561264e-07,
554
+ "loss": 0.5733,
555
+ "step": 770
556
+ },
557
+ {
558
+ "epoch": 2.7,
559
+ "grad_norm": 0.287109375,
560
+ "learning_rate": 2.7719153827662384e-07,
561
+ "loss": 0.5742,
562
+ "step": 780
563
+ },
564
+ {
565
+ "epoch": 2.73,
566
+ "grad_norm": 0.2890625,
567
+ "learning_rate": 2.1757149144531142e-07,
568
+ "loss": 0.5732,
569
+ "step": 790
570
+ },
571
+ {
572
+ "epoch": 2.77,
573
+ "grad_norm": 0.306640625,
574
+ "learning_rate": 1.650219524075952e-07,
575
+ "loss": 0.5747,
576
+ "step": 800
577
+ },
578
+ {
579
+ "epoch": 2.8,
580
+ "grad_norm": 0.296875,
581
+ "learning_rate": 1.196206122203647e-07,
582
+ "loss": 0.5773,
583
+ "step": 810
584
+ },
585
+ {
586
+ "epoch": 2.84,
587
+ "grad_norm": 0.287109375,
588
+ "learning_rate": 8.14345937959743e-08,
589
+ "loss": 0.5778,
590
+ "step": 820
591
+ },
592
+ {
593
+ "epoch": 2.87,
594
+ "grad_norm": 0.296875,
595
+ "learning_rate": 5.0520352665416886e-08,
596
+ "loss": 0.5744,
597
+ "step": 830
598
+ },
599
+ {
600
+ "epoch": 2.91,
601
+ "grad_norm": 0.29296875,
602
+ "learning_rate": 2.6923593512505063e-08,
603
+ "loss": 0.5774,
604
+ "step": 840
605
+ },
606
+ {
607
+ "epoch": 2.94,
608
+ "grad_norm": 0.3046875,
609
+ "learning_rate": 1.0679202602491e-08,
610
+ "loss": 0.5789,
611
+ "step": 850
612
+ },
613
+ {
614
+ "epoch": 2.98,
615
+ "grad_norm": 0.31640625,
616
+ "learning_rate": 1.8111962050010311e-09,
617
+ "loss": 0.5777,
618
+ "step": 860
619
+ },
620
+ {
621
+ "epoch": 3.0,
622
+ "step": 867,
623
+ "total_flos": 2.393655748461173e+19,
624
+ "train_loss": 0.6362597953351998,
625
+ "train_runtime": 82257.6345,
626
+ "train_samples_per_second": 0.673,
627
+ "train_steps_per_second": 0.011
628
+ }
629
+ ],
630
+ "logging_steps": 10,
631
+ "max_steps": 867,
632
+ "num_input_tokens_seen": 0,
633
+ "num_train_epochs": 3,
634
+ "save_steps": 500,
635
+ "total_flos": 2.393655748461173e+19,
636
+ "train_batch_size": 1,
637
+ "trial_name": null,
638
+ "trial_params": null
639
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a1f7b4f047a40a1f13178d6c90a3e637ac6b3fe06cdc12d1dfb58853cdc5e0c7
3
+ size 5048