peihaowang commited on
Commit
17e5b04
1 Parent(s): 9529a60

Upload folder using huggingface_hub

Browse files
config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "./configs/diff_llama-410m.json",
3
+ "architectures": [
4
+ "DiffLlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "attn_family": "mha",
9
+ "bos_token_id": 1,
10
+ "eos_token_id": 2,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 1024,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 4096,
15
+ "max_position_embeddings": 2048,
16
+ "model_type": "diff_llama",
17
+ "num_attention_heads": 8,
18
+ "num_hidden_layers": 24,
19
+ "num_key_value_heads": 8,
20
+ "pretraining_tp": 1,
21
+ "rms_norm_eps": 1e-05,
22
+ "rope_scaling": null,
23
+ "rope_theta": 10000.0,
24
+ "tie_word_embeddings": false,
25
+ "torch_dtype": "bfloat16",
26
+ "transformers_version": "4.36.1",
27
+ "use_cache": false,
28
+ "vocab_size": 50277
29
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "transformers_version": "4.36.1",
6
+ "use_cache": false
7
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c301a6c1fdd18dbc1c96337c4dd1b5b200ce4708f9db62dc3c0ce5a7b68844f
3
+ size 1011366272
special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|endoftext|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|endoftext|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "unk_token": {
17
+ "content": "<|endoftext|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,212 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<|padding|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "50254": {
21
+ "content": " ",
22
+ "lstrip": false,
23
+ "normalized": true,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": false
27
+ },
28
+ "50255": {
29
+ "content": " ",
30
+ "lstrip": false,
31
+ "normalized": true,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": false
35
+ },
36
+ "50256": {
37
+ "content": " ",
38
+ "lstrip": false,
39
+ "normalized": true,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": false
43
+ },
44
+ "50257": {
45
+ "content": " ",
46
+ "lstrip": false,
47
+ "normalized": true,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": false
51
+ },
52
+ "50258": {
53
+ "content": " ",
54
+ "lstrip": false,
55
+ "normalized": true,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": false
59
+ },
60
+ "50259": {
61
+ "content": " ",
62
+ "lstrip": false,
63
+ "normalized": true,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": false
67
+ },
68
+ "50260": {
69
+ "content": " ",
70
+ "lstrip": false,
71
+ "normalized": true,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": false
75
+ },
76
+ "50261": {
77
+ "content": " ",
78
+ "lstrip": false,
79
+ "normalized": true,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": false
83
+ },
84
+ "50262": {
85
+ "content": " ",
86
+ "lstrip": false,
87
+ "normalized": true,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": false
91
+ },
92
+ "50263": {
93
+ "content": " ",
94
+ "lstrip": false,
95
+ "normalized": true,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": false
99
+ },
100
+ "50264": {
101
+ "content": " ",
102
+ "lstrip": false,
103
+ "normalized": true,
104
+ "rstrip": false,
105
+ "single_word": false,
106
+ "special": false
107
+ },
108
+ "50265": {
109
+ "content": " ",
110
+ "lstrip": false,
111
+ "normalized": true,
112
+ "rstrip": false,
113
+ "single_word": false,
114
+ "special": false
115
+ },
116
+ "50266": {
117
+ "content": " ",
118
+ "lstrip": false,
119
+ "normalized": true,
120
+ "rstrip": false,
121
+ "single_word": false,
122
+ "special": false
123
+ },
124
+ "50267": {
125
+ "content": " ",
126
+ "lstrip": false,
127
+ "normalized": true,
128
+ "rstrip": false,
129
+ "single_word": false,
130
+ "special": false
131
+ },
132
+ "50268": {
133
+ "content": " ",
134
+ "lstrip": false,
135
+ "normalized": true,
136
+ "rstrip": false,
137
+ "single_word": false,
138
+ "special": false
139
+ },
140
+ "50269": {
141
+ "content": " ",
142
+ "lstrip": false,
143
+ "normalized": true,
144
+ "rstrip": false,
145
+ "single_word": false,
146
+ "special": false
147
+ },
148
+ "50270": {
149
+ "content": " ",
150
+ "lstrip": false,
151
+ "normalized": true,
152
+ "rstrip": false,
153
+ "single_word": false,
154
+ "special": false
155
+ },
156
+ "50271": {
157
+ "content": " ",
158
+ "lstrip": false,
159
+ "normalized": true,
160
+ "rstrip": false,
161
+ "single_word": false,
162
+ "special": false
163
+ },
164
+ "50272": {
165
+ "content": " ",
166
+ "lstrip": false,
167
+ "normalized": true,
168
+ "rstrip": false,
169
+ "single_word": false,
170
+ "special": false
171
+ },
172
+ "50273": {
173
+ "content": " ",
174
+ "lstrip": false,
175
+ "normalized": true,
176
+ "rstrip": false,
177
+ "single_word": false,
178
+ "special": false
179
+ },
180
+ "50274": {
181
+ "content": " ",
182
+ "lstrip": false,
183
+ "normalized": true,
184
+ "rstrip": false,
185
+ "single_word": false,
186
+ "special": false
187
+ },
188
+ "50275": {
189
+ "content": " ",
190
+ "lstrip": false,
191
+ "normalized": true,
192
+ "rstrip": false,
193
+ "single_word": false,
194
+ "special": false
195
+ },
196
+ "50276": {
197
+ "content": " ",
198
+ "lstrip": false,
199
+ "normalized": true,
200
+ "rstrip": false,
201
+ "single_word": false,
202
+ "special": false
203
+ }
204
+ },
205
+ "bos_token": "<|endoftext|>",
206
+ "clean_up_tokenization_spaces": true,
207
+ "eos_token": "<|endoftext|>",
208
+ "model_max_length": 2048,
209
+ "padding_side": "right",
210
+ "tokenizer_class": "GPTNeoXTokenizer",
211
+ "unk_token": "<|endoftext|>"
212
+ }
trainer_state.json ADDED
@@ -0,0 +1,246 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 3.168581008911133,
3
+ "best_model_checkpoint": "./snap_diff_llama/diff_llama_410m_mha_nh8/checkpoint-14000",
4
+ "epoch": 0.03757142857142857,
5
+ "eval_steps": 1000,
6
+ "global_step": 14000,
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
+ "learning_rate": 2.1428571428571426e-07,
14
+ "loss": 11.0346,
15
+ "step": 1
16
+ },
17
+ {
18
+ "epoch": 0.07,
19
+ "learning_rate": 0.00021428571428571427,
20
+ "loss": 6.4461,
21
+ "step": 1000
22
+ },
23
+ {
24
+ "epoch": 0.07,
25
+ "eval_loss": 4.968512535095215,
26
+ "eval_ppl": 143.81281168511583,
27
+ "eval_runtime": 29.3664,
28
+ "eval_samples_per_second": 17.026,
29
+ "eval_steps_per_second": 0.136,
30
+ "step": 1000
31
+ },
32
+ {
33
+ "epoch": 0.14,
34
+ "learning_rate": 0.0002983246239337692,
35
+ "loss": 4.372,
36
+ "step": 2000
37
+ },
38
+ {
39
+ "epoch": 0.14,
40
+ "eval_loss": 4.0148515701293945,
41
+ "eval_ppl": 55.41506954042567,
42
+ "eval_runtime": 29.4326,
43
+ "eval_samples_per_second": 16.988,
44
+ "eval_steps_per_second": 0.136,
45
+ "step": 2000
46
+ },
47
+ {
48
+ "epoch": 0.21,
49
+ "learning_rate": 0.00028822143178056114,
50
+ "loss": 3.7967,
51
+ "step": 3000
52
+ },
53
+ {
54
+ "epoch": 0.21,
55
+ "eval_loss": 3.630861759185791,
56
+ "eval_ppl": 37.74532999066067,
57
+ "eval_runtime": 29.3762,
58
+ "eval_samples_per_second": 17.021,
59
+ "eval_steps_per_second": 0.136,
60
+ "step": 3000
61
+ },
62
+ {
63
+ "epoch": 0.29,
64
+ "learning_rate": 0.0002695698760834384,
65
+ "loss": 3.5768,
66
+ "step": 4000
67
+ },
68
+ {
69
+ "epoch": 0.29,
70
+ "eval_loss": 3.4959921836853027,
71
+ "eval_ppl": 32.982996915103584,
72
+ "eval_runtime": 29.6127,
73
+ "eval_samples_per_second": 16.885,
74
+ "eval_steps_per_second": 0.135,
75
+ "step": 4000
76
+ },
77
+ {
78
+ "epoch": 0.04,
79
+ "learning_rate": 0.00024352347027881003,
80
+ "loss": 3.431,
81
+ "step": 5000
82
+ },
83
+ {
84
+ "epoch": 0.04,
85
+ "eval_loss": 3.3921093940734863,
86
+ "eval_ppl": 29.72859550067386,
87
+ "eval_runtime": 30.2978,
88
+ "eval_samples_per_second": 16.503,
89
+ "eval_steps_per_second": 0.132,
90
+ "step": 5000
91
+ },
92
+ {
93
+ "epoch": 0.11,
94
+ "learning_rate": 0.00021169306546959174,
95
+ "loss": 3.3882,
96
+ "step": 6000
97
+ },
98
+ {
99
+ "epoch": 0.11,
100
+ "eval_loss": 3.3295722007751465,
101
+ "eval_ppl": 27.926392258476014,
102
+ "eval_runtime": 30.1857,
103
+ "eval_samples_per_second": 16.564,
104
+ "eval_steps_per_second": 0.133,
105
+ "step": 6000
106
+ },
107
+ {
108
+ "epoch": 0.18,
109
+ "learning_rate": 0.00017604722665003956,
110
+ "loss": 3.3295,
111
+ "step": 7000
112
+ },
113
+ {
114
+ "epoch": 0.18,
115
+ "eval_loss": 3.275782823562622,
116
+ "eval_ppl": 26.463933965027962,
117
+ "eval_runtime": 30.4221,
118
+ "eval_samples_per_second": 16.435,
119
+ "eval_steps_per_second": 0.131,
120
+ "step": 7000
121
+ },
122
+ {
123
+ "epoch": 0.25,
124
+ "learning_rate": 0.00013879048596203636,
125
+ "loss": 3.3156,
126
+ "step": 8000
127
+ },
128
+ {
129
+ "epoch": 0.25,
130
+ "eval_loss": 3.243619680404663,
131
+ "eval_ppl": 25.62631313413772,
132
+ "eval_runtime": 29.7883,
133
+ "eval_samples_per_second": 16.785,
134
+ "eval_steps_per_second": 0.134,
135
+ "step": 8000
136
+ },
137
+ {
138
+ "epoch": 0.32,
139
+ "learning_rate": 0.00010222700246224735,
140
+ "loss": 3.2716,
141
+ "step": 9000
142
+ },
143
+ {
144
+ "epoch": 0.32,
145
+ "eval_loss": 3.2149527072906494,
146
+ "eval_ppl": 24.90211419486803,
147
+ "eval_runtime": 29.5361,
148
+ "eval_samples_per_second": 16.928,
149
+ "eval_steps_per_second": 0.135,
150
+ "step": 9000
151
+ },
152
+ {
153
+ "epoch": 0.07,
154
+ "learning_rate": 6.86180604201361e-05,
155
+ "loss": 3.2465,
156
+ "step": 10000
157
+ },
158
+ {
159
+ "epoch": 0.07,
160
+ "eval_loss": 3.1856298446655273,
161
+ "eval_ppl": 24.182514838168,
162
+ "eval_runtime": 30.0092,
163
+ "eval_samples_per_second": 16.662,
164
+ "eval_steps_per_second": 0.133,
165
+ "step": 10000
166
+ },
167
+ {
168
+ "epoch": 0.14,
169
+ "learning_rate": 4.004221922552608e-05,
170
+ "loss": 3.2423,
171
+ "step": 11000
172
+ },
173
+ {
174
+ "epoch": 0.14,
175
+ "eval_loss": 3.1793622970581055,
176
+ "eval_ppl": 24.031423755029174,
177
+ "eval_runtime": 29.7001,
178
+ "eval_samples_per_second": 16.835,
179
+ "eval_steps_per_second": 0.135,
180
+ "step": 11000
181
+ },
182
+ {
183
+ "epoch": 0.21,
184
+ "learning_rate": 1.82667639944657e-05,
185
+ "loss": 3.2024,
186
+ "step": 12000
187
+ },
188
+ {
189
+ "epoch": 0.21,
190
+ "eval_loss": 3.1691527366638184,
191
+ "eval_ppl": 23.787321690556684,
192
+ "eval_runtime": 29.8148,
193
+ "eval_samples_per_second": 16.77,
194
+ "eval_steps_per_second": 0.134,
195
+ "step": 12000
196
+ },
197
+ {
198
+ "epoch": 0.29,
199
+ "learning_rate": 1e-05,
200
+ "loss": 3.2188,
201
+ "step": 13000
202
+ },
203
+ {
204
+ "epoch": 0.29,
205
+ "eval_loss": 3.1688954830169678,
206
+ "eval_ppl": 23.781203102351288,
207
+ "eval_runtime": 29.6003,
208
+ "eval_samples_per_second": 16.892,
209
+ "eval_steps_per_second": 0.135,
210
+ "step": 13000
211
+ },
212
+ {
213
+ "epoch": 0.04,
214
+ "learning_rate": 1e-05,
215
+ "loss": 3.2089,
216
+ "step": 14000
217
+ },
218
+ {
219
+ "epoch": 0.04,
220
+ "eval_loss": 3.168581008911133,
221
+ "eval_ppl": 23.773725705555453,
222
+ "eval_runtime": 30.6392,
223
+ "eval_samples_per_second": 16.319,
224
+ "eval_steps_per_second": 0.131,
225
+ "step": 14000
226
+ },
227
+ {
228
+ "epoch": 0.04,
229
+ "step": 14000,
230
+ "total_flos": 2.000248354517916e+19,
231
+ "train_loss": 0.12056473214285714,
232
+ "train_runtime": 1704.5129,
233
+ "train_samples_per_second": 2102.654,
234
+ "train_steps_per_second": 8.213
235
+ }
236
+ ],
237
+ "logging_steps": 1000,
238
+ "max_steps": 14000,
239
+ "num_input_tokens_seen": 0,
240
+ "num_train_epochs": 9223372036854775807,
241
+ "save_steps": 1000,
242
+ "total_flos": 2.000248354517916e+19,
243
+ "train_batch_size": 16,
244
+ "trial_name": null,
245
+ "trial_params": null
246
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4a0db9c87e95187c6d9c716978a1818a25844e18acb999d5f255059460cb0b0c
3
+ size 4856