luodian commited on
Commit
8549925
1 Parent(s): 824059c

b32dba3f6f8b8e0379aaa7a70b857fcd0310cf0fe7050e0b5b792782760bc510

Browse files
added_tokens.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "<|endoftext|>": 151643,
3
+ "<|im_end|>": 151645,
4
+ "<|im_start|>": 151644
5
+ }
config.json ADDED
@@ -0,0 +1,198 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/mnt/bn/vl-research-cn-boli01-hl/checkpoints/llavanext-google_siglip-so400m-patch14-384-Qwen_Qwen2-72B-Instruct-mid_to_final_next_3m_am9_july13",
3
+ "architectures": [
4
+ "LlavaQwenForCausalLM"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 151643,
8
+ "eos_token_id": 151645,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 8192,
11
+ "image_aspect_ratio": "anyres_max_9",
12
+ "image_crop_resolution": null,
13
+ "image_grid_pinpoints": [
14
+ [
15
+ 384,
16
+ 384
17
+ ],
18
+ [
19
+ 384,
20
+ 768
21
+ ],
22
+ [
23
+ 384,
24
+ 1152
25
+ ],
26
+ [
27
+ 384,
28
+ 1536
29
+ ],
30
+ [
31
+ 384,
32
+ 1920
33
+ ],
34
+ [
35
+ 384,
36
+ 2304
37
+ ],
38
+ [
39
+ 768,
40
+ 384
41
+ ],
42
+ [
43
+ 768,
44
+ 768
45
+ ],
46
+ [
47
+ 768,
48
+ 1152
49
+ ],
50
+ [
51
+ 768,
52
+ 1536
53
+ ],
54
+ [
55
+ 768,
56
+ 1920
57
+ ],
58
+ [
59
+ 768,
60
+ 2304
61
+ ],
62
+ [
63
+ 1152,
64
+ 384
65
+ ],
66
+ [
67
+ 1152,
68
+ 768
69
+ ],
70
+ [
71
+ 1152,
72
+ 1152
73
+ ],
74
+ [
75
+ 1152,
76
+ 1536
77
+ ],
78
+ [
79
+ 1152,
80
+ 1920
81
+ ],
82
+ [
83
+ 1152,
84
+ 2304
85
+ ],
86
+ [
87
+ 1536,
88
+ 384
89
+ ],
90
+ [
91
+ 1536,
92
+ 768
93
+ ],
94
+ [
95
+ 1536,
96
+ 1152
97
+ ],
98
+ [
99
+ 1536,
100
+ 1536
101
+ ],
102
+ [
103
+ 1536,
104
+ 1920
105
+ ],
106
+ [
107
+ 1536,
108
+ 2304
109
+ ],
110
+ [
111
+ 1920,
112
+ 384
113
+ ],
114
+ [
115
+ 1920,
116
+ 768
117
+ ],
118
+ [
119
+ 1920,
120
+ 1152
121
+ ],
122
+ [
123
+ 1920,
124
+ 1536
125
+ ],
126
+ [
127
+ 1920,
128
+ 1920
129
+ ],
130
+ [
131
+ 1920,
132
+ 2304
133
+ ],
134
+ [
135
+ 2304,
136
+ 384
137
+ ],
138
+ [
139
+ 2304,
140
+ 768
141
+ ],
142
+ [
143
+ 2304,
144
+ 1152
145
+ ],
146
+ [
147
+ 2304,
148
+ 1536
149
+ ],
150
+ [
151
+ 2304,
152
+ 1920
153
+ ],
154
+ [
155
+ 2304,
156
+ 2304
157
+ ]
158
+ ],
159
+ "image_split_resolution": null,
160
+ "image_token_index": 151646,
161
+ "initializer_range": 0.02,
162
+ "intermediate_size": 29568,
163
+ "max_position_embeddings": 32768,
164
+ "max_window_layers": 80,
165
+ "mm_hidden_size": 1152,
166
+ "mm_patch_merge_type": "spatial_unpad",
167
+ "mm_projector_lr": null,
168
+ "mm_projector_type": "mlp2x_gelu",
169
+ "mm_resampler_type": null,
170
+ "mm_spatial_pool_mode": "bilinear",
171
+ "mm_tunable_parts": "mm_vision_tower,mm_mlp_adapter,mm_language_model",
172
+ "mm_use_im_patch_token": false,
173
+ "mm_use_im_start_end": false,
174
+ "mm_vision_select_feature": "patch",
175
+ "mm_vision_select_layer": -2,
176
+ "mm_vision_tower": "google/siglip-so400m-patch14-384",
177
+ "mm_vision_tower_lr": 2e-07,
178
+ "model_type": "llava",
179
+ "num_attention_heads": 64,
180
+ "num_hidden_layers": 80,
181
+ "num_key_value_heads": 8,
182
+ "pos_skipping_range": 4096,
183
+ "rms_norm_eps": 1e-06,
184
+ "rope_scaling": null,
185
+ "rope_theta": 1000000.0,
186
+ "sliding_window": 131072,
187
+ "tie_word_embeddings": false,
188
+ "tokenizer_model_max_length": 32768,
189
+ "tokenizer_padding_side": "right",
190
+ "torch_dtype": "bfloat16",
191
+ "transformers_version": "4.40.0.dev0",
192
+ "use_cache": true,
193
+ "use_mm_proj": true,
194
+ "use_pos_skipping": false,
195
+ "use_sliding_window": false,
196
+ "vision_tower_pretrained": null,
197
+ "vocab_size": 152064
198
+ }
generation_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token_id": 151643,
3
+ "do_sample": true,
4
+ "eos_token_id": [
5
+ 151645,
6
+ 151643
7
+ ],
8
+ "pad_token_id": 151643,
9
+ "repetition_penalty": 1.05,
10
+ "temperature": 0.7,
11
+ "top_k": 20,
12
+ "top_p": 0.8,
13
+ "transformers_version": "4.40.0.dev0"
14
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
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 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "{% 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": "<|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 +1,457 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 61,
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": 3.765191996253847,
14
+ "learning_rate": 2.5e-07,
15
+ "loss": 1.0461,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.03,
20
+ "grad_norm": 4.0641282279063455,
21
+ "learning_rate": 5e-07,
22
+ "loss": 1.0458,
23
+ "step": 2
24
+ },
25
+ {
26
+ "epoch": 0.05,
27
+ "grad_norm": 3.7765443388481783,
28
+ "learning_rate": 4.996456739191904e-07,
29
+ "loss": 1.0684,
30
+ "step": 3
31
+ },
32
+ {
33
+ "epoch": 0.07,
34
+ "grad_norm": 3.4137815575539796,
35
+ "learning_rate": 4.985837000525343e-07,
36
+ "loss": 1.0314,
37
+ "step": 4
38
+ },
39
+ {
40
+ "epoch": 0.08,
41
+ "grad_norm": 3.3692459406727107,
42
+ "learning_rate": 4.968170886803361e-07,
43
+ "loss": 1.0465,
44
+ "step": 5
45
+ },
46
+ {
47
+ "epoch": 0.1,
48
+ "grad_norm": 3.41903215526812,
49
+ "learning_rate": 4.943508474544666e-07,
50
+ "loss": 0.9973,
51
+ "step": 6
52
+ },
53
+ {
54
+ "epoch": 0.11,
55
+ "grad_norm": 3.5409185994032644,
56
+ "learning_rate": 4.91191967203629e-07,
57
+ "loss": 1.0003,
58
+ "step": 7
59
+ },
60
+ {
61
+ "epoch": 0.13,
62
+ "grad_norm": 3.2875389190594584,
63
+ "learning_rate": 4.873494021170954e-07,
64
+ "loss": 1.0126,
65
+ "step": 8
66
+ },
67
+ {
68
+ "epoch": 0.15,
69
+ "grad_norm": 3.1966679962173004,
70
+ "learning_rate": 4.828340443630846e-07,
71
+ "loss": 1.0149,
72
+ "step": 9
73
+ },
74
+ {
75
+ "epoch": 0.16,
76
+ "grad_norm": 3.220278106251628,
77
+ "learning_rate": 4.776586932137283e-07,
78
+ "loss": 1.0149,
79
+ "step": 10
80
+ },
81
+ {
82
+ "epoch": 0.18,
83
+ "grad_norm": 5.120652614407811,
84
+ "learning_rate": 4.7183801876414286e-07,
85
+ "loss": 1.0208,
86
+ "step": 11
87
+ },
88
+ {
89
+ "epoch": 0.2,
90
+ "grad_norm": 3.428077957669144,
91
+ "learning_rate": 4.653885203484515e-07,
92
+ "loss": 1.0378,
93
+ "step": 12
94
+ },
95
+ {
96
+ "epoch": 0.21,
97
+ "grad_norm": 3.7962383367663906,
98
+ "learning_rate": 4.583284797706287e-07,
99
+ "loss": 1.0135,
100
+ "step": 13
101
+ },
102
+ {
103
+ "epoch": 0.23,
104
+ "grad_norm": 2.9907595309256267,
105
+ "learning_rate": 4.5067790948274085e-07,
106
+ "loss": 0.9998,
107
+ "step": 14
108
+ },
109
+ {
110
+ "epoch": 0.25,
111
+ "grad_norm": 3.161110263982432,
112
+ "learning_rate": 4.4245849585747655e-07,
113
+ "loss": 1.0069,
114
+ "step": 15
115
+ },
116
+ {
117
+ "epoch": 0.26,
118
+ "grad_norm": 2.886380477987417,
119
+ "learning_rate": 4.336935377157668e-07,
120
+ "loss": 0.9827,
121
+ "step": 16
122
+ },
123
+ {
124
+ "epoch": 0.28,
125
+ "grad_norm": 3.376879009946129,
126
+ "learning_rate": 4.244078802837462e-07,
127
+ "loss": 0.9783,
128
+ "step": 17
129
+ },
130
+ {
131
+ "epoch": 0.3,
132
+ "grad_norm": 2.6892749834464516,
133
+ "learning_rate": 4.146278447662597e-07,
134
+ "loss": 0.9585,
135
+ "step": 18
136
+ },
137
+ {
138
+ "epoch": 0.31,
139
+ "grad_norm": 2.3786851686843105,
140
+ "learning_rate": 4.0438115373654795e-07,
141
+ "loss": 0.9677,
142
+ "step": 19
143
+ },
144
+ {
145
+ "epoch": 0.33,
146
+ "grad_norm": 2.1590733636497754,
147
+ "learning_rate": 3.9369685255360173e-07,
148
+ "loss": 0.9472,
149
+ "step": 20
150
+ },
151
+ {
152
+ "epoch": 0.34,
153
+ "grad_norm": 1.9865479320238961,
154
+ "learning_rate": 3.826052270299356e-07,
155
+ "loss": 0.9533,
156
+ "step": 21
157
+ },
158
+ {
159
+ "epoch": 0.36,
160
+ "grad_norm": 2.0228147756455974,
161
+ "learning_rate": 3.7113771758316255e-07,
162
+ "loss": 0.9366,
163
+ "step": 22
164
+ },
165
+ {
166
+ "epoch": 0.38,
167
+ "grad_norm": 1.9372326169891063,
168
+ "learning_rate": 3.593268301147139e-07,
169
+ "loss": 0.9316,
170
+ "step": 23
171
+ },
172
+ {
173
+ "epoch": 0.39,
174
+ "grad_norm": 1.6478279831526508,
175
+ "learning_rate": 3.472060438683302e-07,
176
+ "loss": 0.9248,
177
+ "step": 24
178
+ },
179
+ {
180
+ "epoch": 0.41,
181
+ "grad_norm": 2.1263539873072306,
182
+ "learning_rate": 3.348097165295075e-07,
183
+ "loss": 0.9232,
184
+ "step": 25
185
+ },
186
+ {
187
+ "epoch": 0.43,
188
+ "grad_norm": 4.833864927411976,
189
+ "learning_rate": 3.2217298683490525e-07,
190
+ "loss": 0.9349,
191
+ "step": 26
192
+ },
193
+ {
194
+ "epoch": 0.44,
195
+ "grad_norm": 1.821858101250319,
196
+ "learning_rate": 3.0933167496777873e-07,
197
+ "loss": 0.9038,
198
+ "step": 27
199
+ },
200
+ {
201
+ "epoch": 0.46,
202
+ "grad_norm": 3.375067752782225,
203
+ "learning_rate": 2.9632218102177856e-07,
204
+ "loss": 0.9208,
205
+ "step": 28
206
+ },
207
+ {
208
+ "epoch": 0.48,
209
+ "grad_norm": 1.6452545248116937,
210
+ "learning_rate": 2.8318138182093047e-07,
211
+ "loss": 0.9091,
212
+ "step": 29
213
+ },
214
+ {
215
+ "epoch": 0.49,
216
+ "grad_norm": 1.641648446261072,
217
+ "learning_rate": 2.6994652638827075e-07,
218
+ "loss": 0.8863,
219
+ "step": 30
220
+ },
221
+ {
222
+ "epoch": 0.51,
223
+ "grad_norm": 1.8514627902865017,
224
+ "learning_rate": 2.566551303594437e-07,
225
+ "loss": 0.9176,
226
+ "step": 31
227
+ },
228
+ {
229
+ "epoch": 0.52,
230
+ "grad_norm": 1.6398219929819895,
231
+ "learning_rate": 2.433448696405563e-07,
232
+ "loss": 0.9132,
233
+ "step": 32
234
+ },
235
+ {
236
+ "epoch": 0.54,
237
+ "grad_norm": 1.6191504043540148,
238
+ "learning_rate": 2.300534736117292e-07,
239
+ "loss": 0.9188,
240
+ "step": 33
241
+ },
242
+ {
243
+ "epoch": 0.56,
244
+ "grad_norm": 1.6846506224257867,
245
+ "learning_rate": 2.168186181790695e-07,
246
+ "loss": 0.9207,
247
+ "step": 34
248
+ },
249
+ {
250
+ "epoch": 0.57,
251
+ "grad_norm": 2.702325993164427,
252
+ "learning_rate": 2.0367781897822144e-07,
253
+ "loss": 0.917,
254
+ "step": 35
255
+ },
256
+ {
257
+ "epoch": 0.59,
258
+ "grad_norm": 4.5333338294812044,
259
+ "learning_rate": 1.9066832503222128e-07,
260
+ "loss": 0.9267,
261
+ "step": 36
262
+ },
263
+ {
264
+ "epoch": 0.61,
265
+ "grad_norm": 1.831113061882906,
266
+ "learning_rate": 1.7782701316509478e-07,
267
+ "loss": 0.9067,
268
+ "step": 37
269
+ },
270
+ {
271
+ "epoch": 0.62,
272
+ "grad_norm": 1.6699336990379,
273
+ "learning_rate": 1.651902834704924e-07,
274
+ "loss": 0.92,
275
+ "step": 38
276
+ },
277
+ {
278
+ "epoch": 0.64,
279
+ "grad_norm": 1.8690462677412756,
280
+ "learning_rate": 1.5279395613166985e-07,
281
+ "loss": 0.942,
282
+ "step": 39
283
+ },
284
+ {
285
+ "epoch": 0.66,
286
+ "grad_norm": 1.9247744555110595,
287
+ "learning_rate": 1.4067316988528616e-07,
288
+ "loss": 0.9024,
289
+ "step": 40
290
+ },
291
+ {
292
+ "epoch": 0.67,
293
+ "grad_norm": 1.453181146995208,
294
+ "learning_rate": 1.2886228241683748e-07,
295
+ "loss": 0.9064,
296
+ "step": 41
297
+ },
298
+ {
299
+ "epoch": 0.69,
300
+ "grad_norm": 2.049559625310238,
301
+ "learning_rate": 1.173947729700644e-07,
302
+ "loss": 0.9271,
303
+ "step": 42
304
+ },
305
+ {
306
+ "epoch": 0.7,
307
+ "grad_norm": 1.486378300397099,
308
+ "learning_rate": 1.0630314744639829e-07,
309
+ "loss": 0.9109,
310
+ "step": 43
311
+ },
312
+ {
313
+ "epoch": 0.72,
314
+ "grad_norm": 2.1416606235277196,
315
+ "learning_rate": 9.561884626345204e-08,
316
+ "loss": 0.904,
317
+ "step": 44
318
+ },
319
+ {
320
+ "epoch": 0.74,
321
+ "grad_norm": 1.6338101300074668,
322
+ "learning_rate": 8.537215523374037e-08,
323
+ "loss": 0.9148,
324
+ "step": 45
325
+ },
326
+ {
327
+ "epoch": 0.75,
328
+ "grad_norm": 2.3037793287537545,
329
+ "learning_rate": 7.559211971625384e-08,
330
+ "loss": 0.8772,
331
+ "step": 46
332
+ },
333
+ {
334
+ "epoch": 0.77,
335
+ "grad_norm": 1.788820498612225,
336
+ "learning_rate": 6.630646228423323e-08,
337
+ "loss": 0.9081,
338
+ "step": 47
339
+ },
340
+ {
341
+ "epoch": 0.79,
342
+ "grad_norm": 2.313616876377129,
343
+ "learning_rate": 5.75415041425234e-08,
344
+ "loss": 0.93,
345
+ "step": 48
346
+ },
347
+ {
348
+ "epoch": 0.8,
349
+ "grad_norm": 1.8442253511582427,
350
+ "learning_rate": 4.932209051725914e-08,
351
+ "loss": 0.9303,
352
+ "step": 49
353
+ },
354
+ {
355
+ "epoch": 0.82,
356
+ "grad_norm": 1.797668108469576,
357
+ "learning_rate": 4.167152022937123e-08,
358
+ "loss": 0.9046,
359
+ "step": 50
360
+ },
361
+ {
362
+ "epoch": 0.84,
363
+ "grad_norm": 2.0071094870512707,
364
+ "learning_rate": 3.461147965154845e-08,
365
+ "loss": 0.8853,
366
+ "step": 51
367
+ },
368
+ {
369
+ "epoch": 0.85,
370
+ "grad_norm": 1.5091131315393522,
371
+ "learning_rate": 2.816198123585714e-08,
372
+ "loss": 0.893,
373
+ "step": 52
374
+ },
375
+ {
376
+ "epoch": 0.87,
377
+ "grad_norm": 2.291025373137871,
378
+ "learning_rate": 2.234130678627169e-08,
379
+ "loss": 0.9102,
380
+ "step": 53
381
+ },
382
+ {
383
+ "epoch": 0.89,
384
+ "grad_norm": 1.975139175162289,
385
+ "learning_rate": 1.7165955636915392e-08,
386
+ "loss": 0.9448,
387
+ "step": 54
388
+ },
389
+ {
390
+ "epoch": 0.9,
391
+ "grad_norm": 1.9662365790545857,
392
+ "learning_rate": 1.265059788290468e-08,
393
+ "loss": 0.9126,
394
+ "step": 55
395
+ },
396
+ {
397
+ "epoch": 0.92,
398
+ "grad_norm": 1.5860718910737048,
399
+ "learning_rate": 8.808032796371017e-09,
400
+ "loss": 0.9008,
401
+ "step": 56
402
+ },
403
+ {
404
+ "epoch": 0.93,
405
+ "grad_norm": 5.824152576947844,
406
+ "learning_rate": 5.649152545533331e-09,
407
+ "loss": 0.9104,
408
+ "step": 57
409
+ },
410
+ {
411
+ "epoch": 0.95,
412
+ "grad_norm": 1.8084725184982782,
413
+ "learning_rate": 3.1829113196638613e-09,
414
+ "loss": 0.9108,
415
+ "step": 58
416
+ },
417
+ {
418
+ "epoch": 0.97,
419
+ "grad_norm": 2.4499467355310878,
420
+ "learning_rate": 1.4162999474657266e-09,
421
+ "loss": 0.9218,
422
+ "step": 59
423
+ },
424
+ {
425
+ "epoch": 0.98,
426
+ "grad_norm": 1.7234130969562493,
427
+ "learning_rate": 3.5432608080951386e-10,
428
+ "loss": 0.913,
429
+ "step": 60
430
+ },
431
+ {
432
+ "epoch": 1.0,
433
+ "grad_norm": 1.5468535844514548,
434
+ "learning_rate": 0.0,
435
+ "loss": 0.9164,
436
+ "step": 61
437
+ },
438
+ {
439
+ "epoch": 1.0,
440
+ "step": 61,
441
+ "total_flos": 57696792150016.0,
442
+ "train_loss": 0.9464570713824914,
443
+ "train_runtime": 1092.378,
444
+ "train_samples_per_second": 14.334,
445
+ "train_steps_per_second": 0.056
446
+ }
447
+ ],
448
+ "logging_steps": 1.0,
449
+ "max_steps": 61,
450
+ "num_input_tokens_seen": 0,
451
+ "num_train_epochs": 1,
452
+ "save_steps": 1000,
453
+ "total_flos": 57696792150016.0,
454
+ "train_batch_size": 1,
455
+ "trial_name": null,
456
+ "trial_params": null
457
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ceab2d9e97a5fdd56677e40f3d5a857675f74b9cbaae3c92d2ff81d15ec4a7e
3
+ size 7928
vocab.json ADDED
The diff for this file is too large to render. See raw diff