EXCO123 commited on
Commit
2dc3206
·
verified ·
1 Parent(s): a05113b

Upload folder using huggingface_hub

Browse files
config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "HuggingFaceTB/SmolLM2-360M-Instruct",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 1,
9
+ "eos_token_id": 2,
10
+ "head_dim": 64,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 960,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 2560,
15
+ "is_llama_config": true,
16
+ "max_position_embeddings": 8192,
17
+ "mlp_bias": false,
18
+ "model_type": "llama",
19
+ "num_attention_heads": 15,
20
+ "num_hidden_layers": 32,
21
+ "num_key_value_heads": 5,
22
+ "pad_token_id": 2,
23
+ "pretraining_tp": 1,
24
+ "rms_norm_eps": 1e-05,
25
+ "rope_interleaved": false,
26
+ "rope_scaling": null,
27
+ "rope_theta": 100000,
28
+ "tie_word_embeddings": true,
29
+ "torch_dtype": "float32",
30
+ "transformers.js_config": {
31
+ "kv_cache_dtype": {
32
+ "fp16": "float16",
33
+ "q4f16": "float16"
34
+ }
35
+ },
36
+ "transformers_version": "4.47.0",
37
+ "use_cache": true,
38
+ "vocab_size": 49152
39
+ }
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
+ "pad_token_id": 2,
6
+ "transformers_version": "4.47.0"
7
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f87583831cff62dc610e22c587a8cb6f7e0b78e2444892b5cd7531502a844fd
3
+ size 1447317080
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df7d9198de1f294ea56cd015c2e3937491185d21a93c9960168fa6dc5042a8f6
3
+ size 735625306
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d4c917636c7a58af68a29056522a757e9f9b99005b776641aa157c536967817d
3
+ size 14244
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fcd60da393ff67ad2f08779377eeaa08189a6bf520f752442788825d9bce1449
3
+ size 1064
special_tokens_map.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ {
4
+ "content": "<|im_start|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ {
11
+ "content": "<|im_end|>",
12
+ "lstrip": false,
13
+ "normalized": false,
14
+ "rstrip": false,
15
+ "single_word": false
16
+ }
17
+ ],
18
+ "bos_token": "<|im_start|>",
19
+ "eos_token": "<|im_end|>",
20
+ "pad_token": "<|im_end|>",
21
+ "unk_token": {
22
+ "content": "<|endoftext|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false
27
+ }
28
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,155 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "<|im_start|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "<|im_end|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "<repo_name>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "4": {
37
+ "content": "<reponame>",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "5": {
45
+ "content": "<file_sep>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "6": {
53
+ "content": "<filename>",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": true
59
+ },
60
+ "7": {
61
+ "content": "<gh_stars>",
62
+ "lstrip": false,
63
+ "normalized": false,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": true
67
+ },
68
+ "8": {
69
+ "content": "<issue_start>",
70
+ "lstrip": false,
71
+ "normalized": false,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": true
75
+ },
76
+ "9": {
77
+ "content": "<issue_comment>",
78
+ "lstrip": false,
79
+ "normalized": false,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": true
83
+ },
84
+ "10": {
85
+ "content": "<issue_closed>",
86
+ "lstrip": false,
87
+ "normalized": false,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": true
91
+ },
92
+ "11": {
93
+ "content": "<jupyter_start>",
94
+ "lstrip": false,
95
+ "normalized": false,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": true
99
+ },
100
+ "12": {
101
+ "content": "<jupyter_text>",
102
+ "lstrip": false,
103
+ "normalized": false,
104
+ "rstrip": false,
105
+ "single_word": false,
106
+ "special": true
107
+ },
108
+ "13": {
109
+ "content": "<jupyter_code>",
110
+ "lstrip": false,
111
+ "normalized": false,
112
+ "rstrip": false,
113
+ "single_word": false,
114
+ "special": true
115
+ },
116
+ "14": {
117
+ "content": "<jupyter_output>",
118
+ "lstrip": false,
119
+ "normalized": false,
120
+ "rstrip": false,
121
+ "single_word": false,
122
+ "special": true
123
+ },
124
+ "15": {
125
+ "content": "<jupyter_script>",
126
+ "lstrip": false,
127
+ "normalized": false,
128
+ "rstrip": false,
129
+ "single_word": false,
130
+ "special": true
131
+ },
132
+ "16": {
133
+ "content": "<empty_output>",
134
+ "lstrip": false,
135
+ "normalized": false,
136
+ "rstrip": false,
137
+ "single_word": false,
138
+ "special": true
139
+ }
140
+ },
141
+ "additional_special_tokens": [
142
+ "<|im_start|>",
143
+ "<|im_end|>"
144
+ ],
145
+ "bos_token": "<|im_start|>",
146
+ "chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
147
+ "clean_up_tokenization_spaces": false,
148
+ "eos_token": "<|im_end|>",
149
+ "extra_special_tokens": {},
150
+ "model_max_length": 8192,
151
+ "pad_token": "<|im_end|>",
152
+ "tokenizer_class": "GPT2Tokenizer",
153
+ "unk_token": "<|endoftext|>",
154
+ "vocab_size": 49152
155
+ }
trainer_state.json ADDED
@@ -0,0 +1,833 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.8,
5
+ "eval_steps": 500,
6
+ "global_step": 100,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.008,
13
+ "grad_norm": 34.44804382324219,
14
+ "learning_rate": 1e-05,
15
+ "loss": 13.0101,
16
+ "mean_token_accuracy": 0.4696590006351471,
17
+ "step": 1
18
+ },
19
+ {
20
+ "epoch": 0.016,
21
+ "grad_norm": 30.779788970947266,
22
+ "learning_rate": 2e-05,
23
+ "loss": 12.3851,
24
+ "mean_token_accuracy": 0.47303473204374313,
25
+ "step": 2
26
+ },
27
+ {
28
+ "epoch": 0.024,
29
+ "grad_norm": 29.67559242248535,
30
+ "learning_rate": 3e-05,
31
+ "loss": 12.3488,
32
+ "mean_token_accuracy": 0.49709559231996536,
33
+ "step": 3
34
+ },
35
+ {
36
+ "epoch": 0.032,
37
+ "grad_norm": 26.862010955810547,
38
+ "learning_rate": 4e-05,
39
+ "loss": 11.6596,
40
+ "mean_token_accuracy": 0.5584611147642136,
41
+ "step": 4
42
+ },
43
+ {
44
+ "epoch": 0.04,
45
+ "grad_norm": 22.10072135925293,
46
+ "learning_rate": 5e-05,
47
+ "loss": 10.1384,
48
+ "mean_token_accuracy": 0.5924926251173019,
49
+ "step": 5
50
+ },
51
+ {
52
+ "epoch": 0.048,
53
+ "grad_norm": 20.171361923217773,
54
+ "learning_rate": 4.9473684210526315e-05,
55
+ "loss": 9.5421,
56
+ "mean_token_accuracy": 0.5888276249170303,
57
+ "step": 6
58
+ },
59
+ {
60
+ "epoch": 0.056,
61
+ "grad_norm": 16.452842712402344,
62
+ "learning_rate": 4.8947368421052635e-05,
63
+ "loss": 8.4344,
64
+ "mean_token_accuracy": 0.632336363196373,
65
+ "step": 7
66
+ },
67
+ {
68
+ "epoch": 0.064,
69
+ "grad_norm": 12.61925983428955,
70
+ "learning_rate": 4.842105263157895e-05,
71
+ "loss": 7.7786,
72
+ "mean_token_accuracy": 0.6633019298315048,
73
+ "step": 8
74
+ },
75
+ {
76
+ "epoch": 0.072,
77
+ "grad_norm": 11.540078163146973,
78
+ "learning_rate": 4.789473684210526e-05,
79
+ "loss": 7.5607,
80
+ "mean_token_accuracy": 0.6721473336219788,
81
+ "step": 9
82
+ },
83
+ {
84
+ "epoch": 0.08,
85
+ "grad_norm": 9.264492988586426,
86
+ "learning_rate": 4.736842105263158e-05,
87
+ "loss": 7.5589,
88
+ "mean_token_accuracy": 0.6924590468406677,
89
+ "step": 10
90
+ },
91
+ {
92
+ "epoch": 0.088,
93
+ "grad_norm": 9.118257522583008,
94
+ "learning_rate": 4.68421052631579e-05,
95
+ "loss": 7.2038,
96
+ "mean_token_accuracy": 0.6936477273702621,
97
+ "step": 11
98
+ },
99
+ {
100
+ "epoch": 0.096,
101
+ "grad_norm": 9.140292167663574,
102
+ "learning_rate": 4.6315789473684214e-05,
103
+ "loss": 6.7882,
104
+ "mean_token_accuracy": 0.7149988412857056,
105
+ "step": 12
106
+ },
107
+ {
108
+ "epoch": 0.104,
109
+ "grad_norm": 8.944159507751465,
110
+ "learning_rate": 4.5789473684210527e-05,
111
+ "loss": 6.7822,
112
+ "mean_token_accuracy": 0.7038442492485046,
113
+ "step": 13
114
+ },
115
+ {
116
+ "epoch": 0.112,
117
+ "grad_norm": 8.406500816345215,
118
+ "learning_rate": 4.5263157894736846e-05,
119
+ "loss": 6.6675,
120
+ "mean_token_accuracy": 0.6912005394697189,
121
+ "step": 14
122
+ },
123
+ {
124
+ "epoch": 0.12,
125
+ "grad_norm": 7.81226921081543,
126
+ "learning_rate": 4.473684210526316e-05,
127
+ "loss": 6.156,
128
+ "mean_token_accuracy": 0.7322177290916443,
129
+ "step": 15
130
+ },
131
+ {
132
+ "epoch": 0.128,
133
+ "grad_norm": 10.26094913482666,
134
+ "learning_rate": 4.421052631578947e-05,
135
+ "loss": 6.3945,
136
+ "mean_token_accuracy": 0.7067171931266785,
137
+ "step": 16
138
+ },
139
+ {
140
+ "epoch": 0.136,
141
+ "grad_norm": 9.275789260864258,
142
+ "learning_rate": 4.368421052631579e-05,
143
+ "loss": 6.0611,
144
+ "mean_token_accuracy": 0.7207391560077667,
145
+ "step": 17
146
+ },
147
+ {
148
+ "epoch": 0.144,
149
+ "grad_norm": 9.354033470153809,
150
+ "learning_rate": 4.3157894736842105e-05,
151
+ "loss": 6.1713,
152
+ "mean_token_accuracy": 0.7210505157709122,
153
+ "step": 18
154
+ },
155
+ {
156
+ "epoch": 0.152,
157
+ "grad_norm": 7.362099647521973,
158
+ "learning_rate": 4.2631578947368425e-05,
159
+ "loss": 6.4072,
160
+ "mean_token_accuracy": 0.7182824611663818,
161
+ "step": 19
162
+ },
163
+ {
164
+ "epoch": 0.16,
165
+ "grad_norm": 7.947159290313721,
166
+ "learning_rate": 4.210526315789474e-05,
167
+ "loss": 6.2321,
168
+ "mean_token_accuracy": 0.7235151827335358,
169
+ "step": 20
170
+ },
171
+ {
172
+ "epoch": 0.168,
173
+ "grad_norm": 9.023740768432617,
174
+ "learning_rate": 4.157894736842106e-05,
175
+ "loss": 6.0462,
176
+ "mean_token_accuracy": 0.7328377515077591,
177
+ "step": 21
178
+ },
179
+ {
180
+ "epoch": 0.176,
181
+ "grad_norm": 7.097681999206543,
182
+ "learning_rate": 4.105263157894737e-05,
183
+ "loss": 5.1996,
184
+ "mean_token_accuracy": 0.7640947103500366,
185
+ "step": 22
186
+ },
187
+ {
188
+ "epoch": 0.184,
189
+ "grad_norm": 7.417032718658447,
190
+ "learning_rate": 4.0526315789473684e-05,
191
+ "loss": 6.2611,
192
+ "mean_token_accuracy": 0.7178521305322647,
193
+ "step": 23
194
+ },
195
+ {
196
+ "epoch": 0.192,
197
+ "grad_norm": 6.950761318206787,
198
+ "learning_rate": 4e-05,
199
+ "loss": 5.5961,
200
+ "mean_token_accuracy": 0.7444904744625092,
201
+ "step": 24
202
+ },
203
+ {
204
+ "epoch": 0.2,
205
+ "grad_norm": 11.129012107849121,
206
+ "learning_rate": 3.9473684210526316e-05,
207
+ "loss": 5.3222,
208
+ "mean_token_accuracy": 0.75727978348732,
209
+ "step": 25
210
+ },
211
+ {
212
+ "epoch": 0.208,
213
+ "grad_norm": 7.0950469970703125,
214
+ "learning_rate": 3.894736842105263e-05,
215
+ "loss": 5.4028,
216
+ "mean_token_accuracy": 0.7472832798957825,
217
+ "step": 26
218
+ },
219
+ {
220
+ "epoch": 0.216,
221
+ "grad_norm": 9.279951095581055,
222
+ "learning_rate": 3.842105263157895e-05,
223
+ "loss": 5.6822,
224
+ "mean_token_accuracy": 0.7470583468675613,
225
+ "step": 27
226
+ },
227
+ {
228
+ "epoch": 0.224,
229
+ "grad_norm": 7.986962795257568,
230
+ "learning_rate": 3.789473684210527e-05,
231
+ "loss": 5.5314,
232
+ "mean_token_accuracy": 0.7577493786811829,
233
+ "step": 28
234
+ },
235
+ {
236
+ "epoch": 0.232,
237
+ "grad_norm": 7.804550647735596,
238
+ "learning_rate": 3.736842105263158e-05,
239
+ "loss": 5.6165,
240
+ "mean_token_accuracy": 0.7538002282381058,
241
+ "step": 29
242
+ },
243
+ {
244
+ "epoch": 0.24,
245
+ "grad_norm": 7.608943939208984,
246
+ "learning_rate": 3.6842105263157895e-05,
247
+ "loss": 5.8104,
248
+ "mean_token_accuracy": 0.7309564054012299,
249
+ "step": 30
250
+ },
251
+ {
252
+ "epoch": 0.248,
253
+ "grad_norm": 7.622748374938965,
254
+ "learning_rate": 3.6315789473684214e-05,
255
+ "loss": 6.0722,
256
+ "mean_token_accuracy": 0.740648090839386,
257
+ "step": 31
258
+ },
259
+ {
260
+ "epoch": 0.256,
261
+ "grad_norm": 7.36374044418335,
262
+ "learning_rate": 3.578947368421053e-05,
263
+ "loss": 5.1848,
264
+ "mean_token_accuracy": 0.7709122896194458,
265
+ "step": 32
266
+ },
267
+ {
268
+ "epoch": 0.264,
269
+ "grad_norm": 6.820411682128906,
270
+ "learning_rate": 3.526315789473684e-05,
271
+ "loss": 5.0621,
272
+ "mean_token_accuracy": 0.7692567408084869,
273
+ "step": 33
274
+ },
275
+ {
276
+ "epoch": 0.272,
277
+ "grad_norm": 6.473299980163574,
278
+ "learning_rate": 3.473684210526316e-05,
279
+ "loss": 5.3879,
280
+ "mean_token_accuracy": 0.7631748914718628,
281
+ "step": 34
282
+ },
283
+ {
284
+ "epoch": 0.28,
285
+ "grad_norm": 7.249595642089844,
286
+ "learning_rate": 3.421052631578947e-05,
287
+ "loss": 5.7251,
288
+ "mean_token_accuracy": 0.7535725235939026,
289
+ "step": 35
290
+ },
291
+ {
292
+ "epoch": 0.288,
293
+ "grad_norm": 6.396822929382324,
294
+ "learning_rate": 3.368421052631579e-05,
295
+ "loss": 5.5203,
296
+ "mean_token_accuracy": 0.7570009678602219,
297
+ "step": 36
298
+ },
299
+ {
300
+ "epoch": 0.296,
301
+ "grad_norm": 5.999199390411377,
302
+ "learning_rate": 3.3157894736842106e-05,
303
+ "loss": 4.8803,
304
+ "mean_token_accuracy": 0.7936893254518509,
305
+ "step": 37
306
+ },
307
+ {
308
+ "epoch": 0.304,
309
+ "grad_norm": 6.992559909820557,
310
+ "learning_rate": 3.2631578947368426e-05,
311
+ "loss": 5.3993,
312
+ "mean_token_accuracy": 0.7533106952905655,
313
+ "step": 38
314
+ },
315
+ {
316
+ "epoch": 0.312,
317
+ "grad_norm": 7.724341869354248,
318
+ "learning_rate": 3.210526315789474e-05,
319
+ "loss": 5.6051,
320
+ "mean_token_accuracy": 0.7366128116846085,
321
+ "step": 39
322
+ },
323
+ {
324
+ "epoch": 0.32,
325
+ "grad_norm": 6.947137832641602,
326
+ "learning_rate": 3.157894736842105e-05,
327
+ "loss": 5.5221,
328
+ "mean_token_accuracy": 0.7558678537607193,
329
+ "step": 40
330
+ },
331
+ {
332
+ "epoch": 0.328,
333
+ "grad_norm": 7.61790657043457,
334
+ "learning_rate": 3.105263157894737e-05,
335
+ "loss": 5.0442,
336
+ "mean_token_accuracy": 0.7664971798658371,
337
+ "step": 41
338
+ },
339
+ {
340
+ "epoch": 0.336,
341
+ "grad_norm": 6.234894275665283,
342
+ "learning_rate": 3.0526315789473684e-05,
343
+ "loss": 5.1083,
344
+ "mean_token_accuracy": 0.7650484591722488,
345
+ "step": 42
346
+ },
347
+ {
348
+ "epoch": 0.344,
349
+ "grad_norm": 6.606740951538086,
350
+ "learning_rate": 3e-05,
351
+ "loss": 4.7578,
352
+ "mean_token_accuracy": 0.7714228928089142,
353
+ "step": 43
354
+ },
355
+ {
356
+ "epoch": 0.352,
357
+ "grad_norm": 7.6674957275390625,
358
+ "learning_rate": 2.9473684210526314e-05,
359
+ "loss": 4.8684,
360
+ "mean_token_accuracy": 0.7777758836746216,
361
+ "step": 44
362
+ },
363
+ {
364
+ "epoch": 0.36,
365
+ "grad_norm": 6.467043399810791,
366
+ "learning_rate": 2.8947368421052634e-05,
367
+ "loss": 4.8455,
368
+ "mean_token_accuracy": 0.7818402796983719,
369
+ "step": 45
370
+ },
371
+ {
372
+ "epoch": 0.368,
373
+ "grad_norm": 8.154311180114746,
374
+ "learning_rate": 2.842105263157895e-05,
375
+ "loss": 4.2716,
376
+ "mean_token_accuracy": 0.7975698858499527,
377
+ "step": 46
378
+ },
379
+ {
380
+ "epoch": 0.376,
381
+ "grad_norm": 6.493333339691162,
382
+ "learning_rate": 2.7894736842105263e-05,
383
+ "loss": 4.8411,
384
+ "mean_token_accuracy": 0.7828859686851501,
385
+ "step": 47
386
+ },
387
+ {
388
+ "epoch": 0.384,
389
+ "grad_norm": 6.82868766784668,
390
+ "learning_rate": 2.7368421052631583e-05,
391
+ "loss": 5.1772,
392
+ "mean_token_accuracy": 0.7642232775688171,
393
+ "step": 48
394
+ },
395
+ {
396
+ "epoch": 0.392,
397
+ "grad_norm": 7.6515793800354,
398
+ "learning_rate": 2.6842105263157896e-05,
399
+ "loss": 5.3152,
400
+ "mean_token_accuracy": 0.7572789639234543,
401
+ "step": 49
402
+ },
403
+ {
404
+ "epoch": 0.4,
405
+ "grad_norm": 7.436869144439697,
406
+ "learning_rate": 2.6315789473684212e-05,
407
+ "loss": 5.6628,
408
+ "mean_token_accuracy": 0.7437437325716019,
409
+ "step": 50
410
+ },
411
+ {
412
+ "epoch": 0.408,
413
+ "grad_norm": 7.494150161743164,
414
+ "learning_rate": 2.578947368421053e-05,
415
+ "loss": 4.7967,
416
+ "mean_token_accuracy": 0.7860404402017593,
417
+ "step": 51
418
+ },
419
+ {
420
+ "epoch": 0.416,
421
+ "grad_norm": 7.129732131958008,
422
+ "learning_rate": 2.5263157894736845e-05,
423
+ "loss": 4.1962,
424
+ "mean_token_accuracy": 0.8091482371091843,
425
+ "step": 52
426
+ },
427
+ {
428
+ "epoch": 0.424,
429
+ "grad_norm": 6.54312801361084,
430
+ "learning_rate": 2.4736842105263158e-05,
431
+ "loss": 5.1673,
432
+ "mean_token_accuracy": 0.7621930986642838,
433
+ "step": 53
434
+ },
435
+ {
436
+ "epoch": 0.432,
437
+ "grad_norm": 7.091205596923828,
438
+ "learning_rate": 2.4210526315789474e-05,
439
+ "loss": 4.9484,
440
+ "mean_token_accuracy": 0.7637773156166077,
441
+ "step": 54
442
+ },
443
+ {
444
+ "epoch": 0.44,
445
+ "grad_norm": 6.452225685119629,
446
+ "learning_rate": 2.368421052631579e-05,
447
+ "loss": 5.2121,
448
+ "mean_token_accuracy": 0.7751423120498657,
449
+ "step": 55
450
+ },
451
+ {
452
+ "epoch": 0.448,
453
+ "grad_norm": 7.079778671264648,
454
+ "learning_rate": 2.3157894736842107e-05,
455
+ "loss": 4.4913,
456
+ "mean_token_accuracy": 0.7925348579883575,
457
+ "step": 56
458
+ },
459
+ {
460
+ "epoch": 0.456,
461
+ "grad_norm": 6.021428108215332,
462
+ "learning_rate": 2.2631578947368423e-05,
463
+ "loss": 5.1743,
464
+ "mean_token_accuracy": 0.7735058069229126,
465
+ "step": 57
466
+ },
467
+ {
468
+ "epoch": 0.464,
469
+ "grad_norm": 6.639064788818359,
470
+ "learning_rate": 2.2105263157894736e-05,
471
+ "loss": 4.2683,
472
+ "mean_token_accuracy": 0.7983661592006683,
473
+ "step": 58
474
+ },
475
+ {
476
+ "epoch": 0.472,
477
+ "grad_norm": 7.0270256996154785,
478
+ "learning_rate": 2.1578947368421053e-05,
479
+ "loss": 4.7973,
480
+ "mean_token_accuracy": 0.7833641171455383,
481
+ "step": 59
482
+ },
483
+ {
484
+ "epoch": 0.48,
485
+ "grad_norm": 6.48342752456665,
486
+ "learning_rate": 2.105263157894737e-05,
487
+ "loss": 4.7573,
488
+ "mean_token_accuracy": 0.7896635830402374,
489
+ "step": 60
490
+ },
491
+ {
492
+ "epoch": 0.488,
493
+ "grad_norm": 7.281738758087158,
494
+ "learning_rate": 2.0526315789473685e-05,
495
+ "loss": 5.3465,
496
+ "mean_token_accuracy": 0.7754404097795486,
497
+ "step": 61
498
+ },
499
+ {
500
+ "epoch": 0.496,
501
+ "grad_norm": 7.372372627258301,
502
+ "learning_rate": 2e-05,
503
+ "loss": 4.3753,
504
+ "mean_token_accuracy": 0.7940351366996765,
505
+ "step": 62
506
+ },
507
+ {
508
+ "epoch": 0.504,
509
+ "grad_norm": 7.551279544830322,
510
+ "learning_rate": 1.9473684210526315e-05,
511
+ "loss": 4.7479,
512
+ "mean_token_accuracy": 0.7812730073928833,
513
+ "step": 63
514
+ },
515
+ {
516
+ "epoch": 0.512,
517
+ "grad_norm": 6.71967077255249,
518
+ "learning_rate": 1.8947368421052634e-05,
519
+ "loss": 4.7599,
520
+ "mean_token_accuracy": 0.7793499678373337,
521
+ "step": 64
522
+ },
523
+ {
524
+ "epoch": 0.52,
525
+ "grad_norm": 7.2533063888549805,
526
+ "learning_rate": 1.8421052631578947e-05,
527
+ "loss": 4.8565,
528
+ "mean_token_accuracy": 0.7772107869386673,
529
+ "step": 65
530
+ },
531
+ {
532
+ "epoch": 0.528,
533
+ "grad_norm": 6.089155197143555,
534
+ "learning_rate": 1.7894736842105264e-05,
535
+ "loss": 4.4817,
536
+ "mean_token_accuracy": 0.7843845635652542,
537
+ "step": 66
538
+ },
539
+ {
540
+ "epoch": 0.536,
541
+ "grad_norm": 7.141996383666992,
542
+ "learning_rate": 1.736842105263158e-05,
543
+ "loss": 4.8889,
544
+ "mean_token_accuracy": 0.7912164181470871,
545
+ "step": 67
546
+ },
547
+ {
548
+ "epoch": 0.544,
549
+ "grad_norm": 6.36722993850708,
550
+ "learning_rate": 1.6842105263157896e-05,
551
+ "loss": 5.663,
552
+ "mean_token_accuracy": 0.7410993576049805,
553
+ "step": 68
554
+ },
555
+ {
556
+ "epoch": 0.552,
557
+ "grad_norm": 6.695736885070801,
558
+ "learning_rate": 1.6315789473684213e-05,
559
+ "loss": 5.4292,
560
+ "mean_token_accuracy": 0.7530855089426041,
561
+ "step": 69
562
+ },
563
+ {
564
+ "epoch": 0.56,
565
+ "grad_norm": 6.8679518699646,
566
+ "learning_rate": 1.5789473684210526e-05,
567
+ "loss": 4.6897,
568
+ "mean_token_accuracy": 0.7747458964586258,
569
+ "step": 70
570
+ },
571
+ {
572
+ "epoch": 0.568,
573
+ "grad_norm": 7.445884704589844,
574
+ "learning_rate": 1.5263157894736842e-05,
575
+ "loss": 4.9695,
576
+ "mean_token_accuracy": 0.782129317522049,
577
+ "step": 71
578
+ },
579
+ {
580
+ "epoch": 0.576,
581
+ "grad_norm": 6.467252254486084,
582
+ "learning_rate": 1.4736842105263157e-05,
583
+ "loss": 4.2316,
584
+ "mean_token_accuracy": 0.8010141849517822,
585
+ "step": 72
586
+ },
587
+ {
588
+ "epoch": 0.584,
589
+ "grad_norm": 6.673328876495361,
590
+ "learning_rate": 1.4210526315789475e-05,
591
+ "loss": 5.5348,
592
+ "mean_token_accuracy": 0.7492043673992157,
593
+ "step": 73
594
+ },
595
+ {
596
+ "epoch": 0.592,
597
+ "grad_norm": 6.37332820892334,
598
+ "learning_rate": 1.3684210526315791e-05,
599
+ "loss": 4.1118,
600
+ "mean_token_accuracy": 0.8063640743494034,
601
+ "step": 74
602
+ },
603
+ {
604
+ "epoch": 0.6,
605
+ "grad_norm": 6.5554327964782715,
606
+ "learning_rate": 1.3157894736842106e-05,
607
+ "loss": 4.3587,
608
+ "mean_token_accuracy": 0.7785357385873795,
609
+ "step": 75
610
+ },
611
+ {
612
+ "epoch": 0.608,
613
+ "grad_norm": 7.242586135864258,
614
+ "learning_rate": 1.2631578947368422e-05,
615
+ "loss": 4.7259,
616
+ "mean_token_accuracy": 0.7722227722406387,
617
+ "step": 76
618
+ },
619
+ {
620
+ "epoch": 0.616,
621
+ "grad_norm": 6.499831676483154,
622
+ "learning_rate": 1.2105263157894737e-05,
623
+ "loss": 4.582,
624
+ "mean_token_accuracy": 0.8019344508647919,
625
+ "step": 77
626
+ },
627
+ {
628
+ "epoch": 0.624,
629
+ "grad_norm": 6.212286949157715,
630
+ "learning_rate": 1.1578947368421053e-05,
631
+ "loss": 4.3784,
632
+ "mean_token_accuracy": 0.7915610671043396,
633
+ "step": 78
634
+ },
635
+ {
636
+ "epoch": 0.632,
637
+ "grad_norm": 6.525815963745117,
638
+ "learning_rate": 1.1052631578947368e-05,
639
+ "loss": 4.6062,
640
+ "mean_token_accuracy": 0.7760037034749985,
641
+ "step": 79
642
+ },
643
+ {
644
+ "epoch": 0.64,
645
+ "grad_norm": 6.437106609344482,
646
+ "learning_rate": 1.0526315789473684e-05,
647
+ "loss": 4.3811,
648
+ "mean_token_accuracy": 0.7914712876081467,
649
+ "step": 80
650
+ },
651
+ {
652
+ "epoch": 0.648,
653
+ "grad_norm": 6.544358730316162,
654
+ "learning_rate": 1e-05,
655
+ "loss": 4.1778,
656
+ "mean_token_accuracy": 0.813565582036972,
657
+ "step": 81
658
+ },
659
+ {
660
+ "epoch": 0.656,
661
+ "grad_norm": 5.799524307250977,
662
+ "learning_rate": 9.473684210526317e-06,
663
+ "loss": 4.5642,
664
+ "mean_token_accuracy": 0.7896921932697296,
665
+ "step": 82
666
+ },
667
+ {
668
+ "epoch": 0.664,
669
+ "grad_norm": 6.26992130279541,
670
+ "learning_rate": 8.947368421052632e-06,
671
+ "loss": 4.4728,
672
+ "mean_token_accuracy": 0.7932559102773666,
673
+ "step": 83
674
+ },
675
+ {
676
+ "epoch": 0.672,
677
+ "grad_norm": 7.898167133331299,
678
+ "learning_rate": 8.421052631578948e-06,
679
+ "loss": 4.7496,
680
+ "mean_token_accuracy": 0.7824009358882904,
681
+ "step": 84
682
+ },
683
+ {
684
+ "epoch": 0.68,
685
+ "grad_norm": 5.840052127838135,
686
+ "learning_rate": 7.894736842105263e-06,
687
+ "loss": 4.4144,
688
+ "mean_token_accuracy": 0.8065742999315262,
689
+ "step": 85
690
+ },
691
+ {
692
+ "epoch": 0.688,
693
+ "grad_norm": 5.884693145751953,
694
+ "learning_rate": 7.3684210526315784e-06,
695
+ "loss": 4.0572,
696
+ "mean_token_accuracy": 0.8163146525621414,
697
+ "step": 86
698
+ },
699
+ {
700
+ "epoch": 0.696,
701
+ "grad_norm": 6.5094380378723145,
702
+ "learning_rate": 6.842105263157896e-06,
703
+ "loss": 4.692,
704
+ "mean_token_accuracy": 0.7821700870990753,
705
+ "step": 87
706
+ },
707
+ {
708
+ "epoch": 0.704,
709
+ "grad_norm": 6.171222686767578,
710
+ "learning_rate": 6.315789473684211e-06,
711
+ "loss": 4.7373,
712
+ "mean_token_accuracy": 0.7865629494190216,
713
+ "step": 88
714
+ },
715
+ {
716
+ "epoch": 0.712,
717
+ "grad_norm": 6.430420875549316,
718
+ "learning_rate": 5.789473684210527e-06,
719
+ "loss": 5.1443,
720
+ "mean_token_accuracy": 0.7733548134565353,
721
+ "step": 89
722
+ },
723
+ {
724
+ "epoch": 0.72,
725
+ "grad_norm": 6.6331987380981445,
726
+ "learning_rate": 5.263157894736842e-06,
727
+ "loss": 4.8172,
728
+ "mean_token_accuracy": 0.7886734008789062,
729
+ "step": 90
730
+ },
731
+ {
732
+ "epoch": 0.728,
733
+ "grad_norm": 6.18582820892334,
734
+ "learning_rate": 4.736842105263159e-06,
735
+ "loss": 4.0192,
736
+ "mean_token_accuracy": 0.8108067065477371,
737
+ "step": 91
738
+ },
739
+ {
740
+ "epoch": 0.736,
741
+ "grad_norm": 6.787937641143799,
742
+ "learning_rate": 4.210526315789474e-06,
743
+ "loss": 4.3634,
744
+ "mean_token_accuracy": 0.7937927544116974,
745
+ "step": 92
746
+ },
747
+ {
748
+ "epoch": 0.744,
749
+ "grad_norm": 6.101965427398682,
750
+ "learning_rate": 3.6842105263157892e-06,
751
+ "loss": 4.7228,
752
+ "mean_token_accuracy": 0.7906162887811661,
753
+ "step": 93
754
+ },
755
+ {
756
+ "epoch": 0.752,
757
+ "grad_norm": 6.77475118637085,
758
+ "learning_rate": 3.1578947368421056e-06,
759
+ "loss": 4.4398,
760
+ "mean_token_accuracy": 0.7847026586532593,
761
+ "step": 94
762
+ },
763
+ {
764
+ "epoch": 0.76,
765
+ "grad_norm": 6.1204023361206055,
766
+ "learning_rate": 2.631578947368421e-06,
767
+ "loss": 4.3872,
768
+ "mean_token_accuracy": 0.7921232283115387,
769
+ "step": 95
770
+ },
771
+ {
772
+ "epoch": 0.768,
773
+ "grad_norm": 6.262160301208496,
774
+ "learning_rate": 2.105263157894737e-06,
775
+ "loss": 4.2201,
776
+ "mean_token_accuracy": 0.7995105534791946,
777
+ "step": 96
778
+ },
779
+ {
780
+ "epoch": 0.776,
781
+ "grad_norm": 6.433416843414307,
782
+ "learning_rate": 1.5789473684210528e-06,
783
+ "loss": 4.2633,
784
+ "mean_token_accuracy": 0.782690092921257,
785
+ "step": 97
786
+ },
787
+ {
788
+ "epoch": 0.784,
789
+ "grad_norm": 6.012047290802002,
790
+ "learning_rate": 1.0526315789473685e-06,
791
+ "loss": 4.2714,
792
+ "mean_token_accuracy": 0.791715532541275,
793
+ "step": 98
794
+ },
795
+ {
796
+ "epoch": 0.792,
797
+ "grad_norm": 6.2551445960998535,
798
+ "learning_rate": 5.263157894736843e-07,
799
+ "loss": 4.4735,
800
+ "mean_token_accuracy": 0.7887705862522125,
801
+ "step": 99
802
+ },
803
+ {
804
+ "epoch": 0.8,
805
+ "grad_norm": 6.641271591186523,
806
+ "learning_rate": 0.0,
807
+ "loss": 4.7771,
808
+ "mean_token_accuracy": 0.7853755056858063,
809
+ "step": 100
810
+ }
811
+ ],
812
+ "logging_steps": 1,
813
+ "max_steps": 100,
814
+ "num_input_tokens_seen": 0,
815
+ "num_train_epochs": 1,
816
+ "save_steps": 500,
817
+ "stateful_callbacks": {
818
+ "TrainerControl": {
819
+ "args": {
820
+ "should_epoch_stop": false,
821
+ "should_evaluate": false,
822
+ "should_log": false,
823
+ "should_save": true,
824
+ "should_training_stop": true
825
+ },
826
+ "attributes": {}
827
+ }
828
+ },
829
+ "total_flos": 1546494935040000.0,
830
+ "train_batch_size": 4,
831
+ "trial_name": null,
832
+ "trial_params": null
833
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0efd804ff22ebcd85ead312b9e1e14442e70fa9dd60bd83b2f0f7ea79fef24f5
3
+ size 5496
vocab.json ADDED
The diff for this file is too large to render. See raw diff