peihaowang commited on
Commit
cacaa31
1 Parent(s): e8a52af

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": "diff_attn",
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": 16,
18
+ "num_hidden_layers": 24,
19
+ "num_key_value_heads": 16,
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:b4715f4cd0629ce585aa6244621255e813142ec92acd39373d6507c7717f29df
3
+ size 1011393224
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": 3.17564058303833,
3
+ "best_model_checkpoint": "./snap_diff_llama/diff_llama_410m_diff_attn/checkpoint-14000",
4
+ "epoch": 0.024642857142857143,
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": 11.0205,
15
+ "step": 1
16
+ },
17
+ {
18
+ "epoch": 0.07,
19
+ "learning_rate": 0.00021428571428571427,
20
+ "loss": 6.3862,
21
+ "step": 1000
22
+ },
23
+ {
24
+ "epoch": 0.07,
25
+ "eval_loss": 4.933394432067871,
26
+ "eval_ppl": 138.85003031304973,
27
+ "eval_runtime": 32.6853,
28
+ "eval_samples_per_second": 15.297,
29
+ "eval_steps_per_second": 0.122,
30
+ "step": 1000
31
+ },
32
+ {
33
+ "epoch": 0.14,
34
+ "learning_rate": 0.0002983246239337692,
35
+ "loss": 4.4203,
36
+ "step": 2000
37
+ },
38
+ {
39
+ "epoch": 0.14,
40
+ "eval_loss": 4.056069374084473,
41
+ "eval_ppl": 57.74688300953943,
42
+ "eval_runtime": 31.9488,
43
+ "eval_samples_per_second": 15.65,
44
+ "eval_steps_per_second": 0.125,
45
+ "step": 2000
46
+ },
47
+ {
48
+ "epoch": 0.21,
49
+ "learning_rate": 0.00028822143178056114,
50
+ "loss": 3.8205,
51
+ "step": 3000
52
+ },
53
+ {
54
+ "epoch": 0.21,
55
+ "eval_loss": 3.6541380882263184,
56
+ "eval_ppl": 38.63420748222174,
57
+ "eval_runtime": 31.7672,
58
+ "eval_samples_per_second": 15.74,
59
+ "eval_steps_per_second": 0.126,
60
+ "step": 3000
61
+ },
62
+ {
63
+ "epoch": 0.02,
64
+ "learning_rate": 0.0002695698760834384,
65
+ "loss": 3.5676,
66
+ "step": 4000
67
+ },
68
+ {
69
+ "epoch": 0.02,
70
+ "eval_loss": 3.523311138153076,
71
+ "eval_ppl": 33.896478778578945,
72
+ "eval_runtime": 33.1855,
73
+ "eval_samples_per_second": 15.067,
74
+ "eval_steps_per_second": 0.121,
75
+ "step": 4000
76
+ },
77
+ {
78
+ "epoch": 0.09,
79
+ "learning_rate": 0.00024352347027881003,
80
+ "loss": 3.4614,
81
+ "step": 5000
82
+ },
83
+ {
84
+ "epoch": 0.09,
85
+ "eval_loss": 3.4199113845825195,
86
+ "eval_ppl": 30.566706219598544,
87
+ "eval_runtime": 32.8838,
88
+ "eval_samples_per_second": 15.205,
89
+ "eval_steps_per_second": 0.122,
90
+ "step": 5000
91
+ },
92
+ {
93
+ "epoch": 0.17,
94
+ "learning_rate": 0.00021169306546959174,
95
+ "loss": 3.3952,
96
+ "step": 6000
97
+ },
98
+ {
99
+ "epoch": 0.17,
100
+ "eval_loss": 3.3484232425689697,
101
+ "eval_ppl": 28.457827159310067,
102
+ "eval_runtime": 32.4291,
103
+ "eval_samples_per_second": 15.418,
104
+ "eval_steps_per_second": 0.123,
105
+ "step": 6000
106
+ },
107
+ {
108
+ "epoch": 0.24,
109
+ "learning_rate": 0.00017604722665003956,
110
+ "loss": 3.347,
111
+ "step": 7000
112
+ },
113
+ {
114
+ "epoch": 0.24,
115
+ "eval_loss": 3.274552822113037,
116
+ "eval_ppl": 26.431403298374143,
117
+ "eval_runtime": 32.6886,
118
+ "eval_samples_per_second": 15.296,
119
+ "eval_steps_per_second": 0.122,
120
+ "step": 7000
121
+ },
122
+ {
123
+ "epoch": 0.05,
124
+ "learning_rate": 0.00013879048596203636,
125
+ "loss": 3.2857,
126
+ "step": 8000
127
+ },
128
+ {
129
+ "epoch": 0.05,
130
+ "eval_loss": 3.2431113719940186,
131
+ "eval_ppl": 25.613290373707557,
132
+ "eval_runtime": 32.5175,
133
+ "eval_samples_per_second": 15.376,
134
+ "eval_steps_per_second": 0.123,
135
+ "step": 8000
136
+ },
137
+ {
138
+ "epoch": 0.12,
139
+ "learning_rate": 0.00010222700246224735,
140
+ "loss": 3.2699,
141
+ "step": 9000
142
+ },
143
+ {
144
+ "epoch": 0.12,
145
+ "eval_loss": 3.204813003540039,
146
+ "eval_ppl": 24.6508899562805,
147
+ "eval_runtime": 32.063,
148
+ "eval_samples_per_second": 15.594,
149
+ "eval_steps_per_second": 0.125,
150
+ "step": 9000
151
+ },
152
+ {
153
+ "epoch": 0.19,
154
+ "learning_rate": 6.86180604201361e-05,
155
+ "loss": 3.2255,
156
+ "step": 10000
157
+ },
158
+ {
159
+ "epoch": 0.19,
160
+ "eval_loss": 3.1874945163726807,
161
+ "eval_ppl": 24.227649356846815,
162
+ "eval_runtime": 31.9699,
163
+ "eval_samples_per_second": 15.64,
164
+ "eval_steps_per_second": 0.125,
165
+ "step": 10000
166
+ },
167
+ {
168
+ "epoch": 0.07,
169
+ "learning_rate": 4.004221922552608e-05,
170
+ "loss": 3.2335,
171
+ "step": 11000
172
+ },
173
+ {
174
+ "epoch": 0.07,
175
+ "eval_loss": 3.1818697452545166,
176
+ "eval_ppl": 24.091756914706085,
177
+ "eval_runtime": 32.8207,
178
+ "eval_samples_per_second": 15.234,
179
+ "eval_steps_per_second": 0.122,
180
+ "step": 11000
181
+ },
182
+ {
183
+ "epoch": 0.14,
184
+ "learning_rate": 1.82667639944657e-05,
185
+ "loss": 3.2553,
186
+ "step": 12000
187
+ },
188
+ {
189
+ "epoch": 0.14,
190
+ "eval_loss": 3.178798198699951,
191
+ "eval_ppl": 24.017871491109133,
192
+ "eval_runtime": 32.5604,
193
+ "eval_samples_per_second": 15.356,
194
+ "eval_steps_per_second": 0.123,
195
+ "step": 12000
196
+ },
197
+ {
198
+ "epoch": 0.21,
199
+ "learning_rate": 1e-05,
200
+ "loss": 3.237,
201
+ "step": 13000
202
+ },
203
+ {
204
+ "epoch": 0.21,
205
+ "eval_loss": 3.1790049076080322,
206
+ "eval_ppl": 24.022836712259533,
207
+ "eval_runtime": 32.1732,
208
+ "eval_samples_per_second": 15.541,
209
+ "eval_steps_per_second": 0.124,
210
+ "step": 13000
211
+ },
212
+ {
213
+ "epoch": 0.02,
214
+ "learning_rate": 1e-05,
215
+ "loss": 3.227,
216
+ "step": 14000
217
+ },
218
+ {
219
+ "epoch": 0.02,
220
+ "eval_loss": 3.17564058303833,
221
+ "eval_ppl": 23.94215189353734,
222
+ "eval_runtime": 32.4234,
223
+ "eval_samples_per_second": 15.421,
224
+ "eval_steps_per_second": 0.123,
225
+ "step": 14000
226
+ },
227
+ {
228
+ "epoch": 0.02,
229
+ "step": 14000,
230
+ "total_flos": 2.0002685775324905e+19,
231
+ "train_loss": 0.07952269635881697,
232
+ "train_runtime": 1357.4941,
233
+ "train_samples_per_second": 2640.159,
234
+ "train_steps_per_second": 10.313
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": 2.0002685775324905e+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:ea971fc7657e499be15fa3437bf7d82b397571912eaef32c9e7d94a08c045fc4
3
+ size 4856