EXCO123 commited on
Commit
684a663
·
verified ·
1 Parent(s): 9cf7225

Upload folder using huggingface_hub

Browse files
config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "HuggingFaceTB/SmolLM2-135M-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": 576,
13
+ "initializer_range": 0.041666666666666664,
14
+ "intermediate_size": 1536,
15
+ "is_llama_config": true,
16
+ "max_position_embeddings": 8192,
17
+ "mlp_bias": false,
18
+ "model_type": "llama",
19
+ "num_attention_heads": 9,
20
+ "num_hidden_layers": 30,
21
+ "num_key_value_heads": 3,
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:db79ed00b1f288135aa6fedfb6e2ec490ed212c5e10da993e685e5bc99cf7333
3
+ size 538090408
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9fbd666ee2b23b101dd6fed232c073ddfc43ea8e19a3b33406f5f3af066769e0
3
+ size 273728186
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 sha256:974fb60062a9e094d57046984954545b807c1053a95415c6cb8cd6fd59c288ae
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 +1,513 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.48,
5
+ "eval_steps": 500,
6
+ "global_step": 60,
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": 29.132591247558594,
14
+ "learning_rate": 1e-05,
15
+ "loss": 14.6502,
16
+ "mean_token_accuracy": 0.44139818847179413,
17
+ "step": 1
18
+ },
19
+ {
20
+ "epoch": 0.016,
21
+ "grad_norm": 26.889101028442383,
22
+ "learning_rate": 2e-05,
23
+ "loss": 14.1037,
24
+ "mean_token_accuracy": 0.46050838381052017,
25
+ "step": 2
26
+ },
27
+ {
28
+ "epoch": 0.024,
29
+ "grad_norm": 25.33008575439453,
30
+ "learning_rate": 3e-05,
31
+ "loss": 13.9492,
32
+ "mean_token_accuracy": 0.45162031054496765,
33
+ "step": 3
34
+ },
35
+ {
36
+ "epoch": 0.032,
37
+ "grad_norm": 21.760456085205078,
38
+ "learning_rate": 4e-05,
39
+ "loss": 13.5332,
40
+ "mean_token_accuracy": 0.47065450996160507,
41
+ "step": 4
42
+ },
43
+ {
44
+ "epoch": 0.04,
45
+ "grad_norm": 19.281452178955078,
46
+ "learning_rate": 5e-05,
47
+ "loss": 11.718,
48
+ "mean_token_accuracy": 0.5306272506713867,
49
+ "step": 5
50
+ },
51
+ {
52
+ "epoch": 0.048,
53
+ "grad_norm": 17.71002197265625,
54
+ "learning_rate": 4.909090909090909e-05,
55
+ "loss": 11.6275,
56
+ "mean_token_accuracy": 0.5233139544725418,
57
+ "step": 6
58
+ },
59
+ {
60
+ "epoch": 0.056,
61
+ "grad_norm": 18.48400115966797,
62
+ "learning_rate": 4.8181818181818186e-05,
63
+ "loss": 10.769,
64
+ "mean_token_accuracy": 0.538578063249588,
65
+ "step": 7
66
+ },
67
+ {
68
+ "epoch": 0.064,
69
+ "grad_norm": 17.125812530517578,
70
+ "learning_rate": 4.7272727272727275e-05,
71
+ "loss": 10.1511,
72
+ "mean_token_accuracy": 0.57903091609478,
73
+ "step": 8
74
+ },
75
+ {
76
+ "epoch": 0.072,
77
+ "grad_norm": 16.800792694091797,
78
+ "learning_rate": 4.636363636363636e-05,
79
+ "loss": 9.5746,
80
+ "mean_token_accuracy": 0.5945043712854385,
81
+ "step": 9
82
+ },
83
+ {
84
+ "epoch": 0.08,
85
+ "grad_norm": 13.959136009216309,
86
+ "learning_rate": 4.545454545454546e-05,
87
+ "loss": 9.5138,
88
+ "mean_token_accuracy": 0.6166220307350159,
89
+ "step": 10
90
+ },
91
+ {
92
+ "epoch": 0.088,
93
+ "grad_norm": 13.918156623840332,
94
+ "learning_rate": 4.454545454545455e-05,
95
+ "loss": 9.3013,
96
+ "mean_token_accuracy": 0.6187369078397751,
97
+ "step": 11
98
+ },
99
+ {
100
+ "epoch": 0.096,
101
+ "grad_norm": 13.260101318359375,
102
+ "learning_rate": 4.3636363636363636e-05,
103
+ "loss": 8.5085,
104
+ "mean_token_accuracy": 0.6477507650852203,
105
+ "step": 12
106
+ },
107
+ {
108
+ "epoch": 0.104,
109
+ "grad_norm": 11.593629837036133,
110
+ "learning_rate": 4.2727272727272724e-05,
111
+ "loss": 8.5987,
112
+ "mean_token_accuracy": 0.6391231864690781,
113
+ "step": 13
114
+ },
115
+ {
116
+ "epoch": 0.112,
117
+ "grad_norm": 10.642716407775879,
118
+ "learning_rate": 4.181818181818182e-05,
119
+ "loss": 8.0015,
120
+ "mean_token_accuracy": 0.6515648812055588,
121
+ "step": 14
122
+ },
123
+ {
124
+ "epoch": 0.12,
125
+ "grad_norm": 10.687582015991211,
126
+ "learning_rate": 4.0909090909090915e-05,
127
+ "loss": 7.8515,
128
+ "mean_token_accuracy": 0.659519150853157,
129
+ "step": 15
130
+ },
131
+ {
132
+ "epoch": 0.128,
133
+ "grad_norm": 11.342368125915527,
134
+ "learning_rate": 4e-05,
135
+ "loss": 8.1734,
136
+ "mean_token_accuracy": 0.6454901546239853,
137
+ "step": 16
138
+ },
139
+ {
140
+ "epoch": 0.136,
141
+ "grad_norm": 10.889402389526367,
142
+ "learning_rate": 3.909090909090909e-05,
143
+ "loss": 7.7197,
144
+ "mean_token_accuracy": 0.6463980078697205,
145
+ "step": 17
146
+ },
147
+ {
148
+ "epoch": 0.144,
149
+ "grad_norm": 11.274605751037598,
150
+ "learning_rate": 3.818181818181819e-05,
151
+ "loss": 7.7246,
152
+ "mean_token_accuracy": 0.6666717827320099,
153
+ "step": 18
154
+ },
155
+ {
156
+ "epoch": 0.152,
157
+ "grad_norm": 9.856607437133789,
158
+ "learning_rate": 3.7272727272727276e-05,
159
+ "loss": 7.9621,
160
+ "mean_token_accuracy": 0.6616508513689041,
161
+ "step": 19
162
+ },
163
+ {
164
+ "epoch": 0.16,
165
+ "grad_norm": 11.277185440063477,
166
+ "learning_rate": 3.6363636363636364e-05,
167
+ "loss": 7.6901,
168
+ "mean_token_accuracy": 0.6638920903205872,
169
+ "step": 20
170
+ },
171
+ {
172
+ "epoch": 0.168,
173
+ "grad_norm": 11.014278411865234,
174
+ "learning_rate": 3.545454545454546e-05,
175
+ "loss": 7.4989,
176
+ "mean_token_accuracy": 0.6643838137388229,
177
+ "step": 21
178
+ },
179
+ {
180
+ "epoch": 0.176,
181
+ "grad_norm": 10.972683906555176,
182
+ "learning_rate": 3.454545454545455e-05,
183
+ "loss": 6.8229,
184
+ "mean_token_accuracy": 0.7015579491853714,
185
+ "step": 22
186
+ },
187
+ {
188
+ "epoch": 0.184,
189
+ "grad_norm": 9.975464820861816,
190
+ "learning_rate": 3.3636363636363636e-05,
191
+ "loss": 7.3764,
192
+ "mean_token_accuracy": 0.6741979718208313,
193
+ "step": 23
194
+ },
195
+ {
196
+ "epoch": 0.192,
197
+ "grad_norm": 9.958491325378418,
198
+ "learning_rate": 3.272727272727273e-05,
199
+ "loss": 7.0166,
200
+ "mean_token_accuracy": 0.698300376534462,
201
+ "step": 24
202
+ },
203
+ {
204
+ "epoch": 0.2,
205
+ "grad_norm": 10.115056037902832,
206
+ "learning_rate": 3.181818181818182e-05,
207
+ "loss": 6.4697,
208
+ "mean_token_accuracy": 0.7078270465135574,
209
+ "step": 25
210
+ },
211
+ {
212
+ "epoch": 0.208,
213
+ "grad_norm": 10.057324409484863,
214
+ "learning_rate": 3.090909090909091e-05,
215
+ "loss": 6.6724,
216
+ "mean_token_accuracy": 0.7051044702529907,
217
+ "step": 26
218
+ },
219
+ {
220
+ "epoch": 0.216,
221
+ "grad_norm": 9.80183219909668,
222
+ "learning_rate": 3e-05,
223
+ "loss": 7.0968,
224
+ "mean_token_accuracy": 0.6842809170484543,
225
+ "step": 27
226
+ },
227
+ {
228
+ "epoch": 0.224,
229
+ "grad_norm": 10.466309547424316,
230
+ "learning_rate": 2.909090909090909e-05,
231
+ "loss": 6.8699,
232
+ "mean_token_accuracy": 0.7123119533061981,
233
+ "step": 28
234
+ },
235
+ {
236
+ "epoch": 0.232,
237
+ "grad_norm": 10.540712356567383,
238
+ "learning_rate": 2.818181818181818e-05,
239
+ "loss": 6.8986,
240
+ "mean_token_accuracy": 0.6990974545478821,
241
+ "step": 29
242
+ },
243
+ {
244
+ "epoch": 0.24,
245
+ "grad_norm": 10.496529579162598,
246
+ "learning_rate": 2.7272727272727273e-05,
247
+ "loss": 7.1639,
248
+ "mean_token_accuracy": 0.6841171979904175,
249
+ "step": 30
250
+ },
251
+ {
252
+ "epoch": 0.248,
253
+ "grad_norm": 10.347450256347656,
254
+ "learning_rate": 2.636363636363636e-05,
255
+ "loss": 7.1243,
256
+ "mean_token_accuracy": 0.7038989663124084,
257
+ "step": 31
258
+ },
259
+ {
260
+ "epoch": 0.256,
261
+ "grad_norm": 10.918871879577637,
262
+ "learning_rate": 2.5454545454545454e-05,
263
+ "loss": 6.5305,
264
+ "mean_token_accuracy": 0.7208158075809479,
265
+ "step": 32
266
+ },
267
+ {
268
+ "epoch": 0.264,
269
+ "grad_norm": 9.658543586730957,
270
+ "learning_rate": 2.4545454545454545e-05,
271
+ "loss": 6.4891,
272
+ "mean_token_accuracy": 0.7414443045854568,
273
+ "step": 33
274
+ },
275
+ {
276
+ "epoch": 0.272,
277
+ "grad_norm": 9.635473251342773,
278
+ "learning_rate": 2.3636363636363637e-05,
279
+ "loss": 6.6357,
280
+ "mean_token_accuracy": 0.73957559466362,
281
+ "step": 34
282
+ },
283
+ {
284
+ "epoch": 0.28,
285
+ "grad_norm": 9.881387710571289,
286
+ "learning_rate": 2.272727272727273e-05,
287
+ "loss": 6.8124,
288
+ "mean_token_accuracy": 0.7286674231290817,
289
+ "step": 35
290
+ },
291
+ {
292
+ "epoch": 0.288,
293
+ "grad_norm": 9.951563835144043,
294
+ "learning_rate": 2.1818181818181818e-05,
295
+ "loss": 6.8861,
296
+ "mean_token_accuracy": 0.7150181531906128,
297
+ "step": 36
298
+ },
299
+ {
300
+ "epoch": 0.296,
301
+ "grad_norm": 8.651752471923828,
302
+ "learning_rate": 2.090909090909091e-05,
303
+ "loss": 6.1332,
304
+ "mean_token_accuracy": 0.7416634857654572,
305
+ "step": 37
306
+ },
307
+ {
308
+ "epoch": 0.304,
309
+ "grad_norm": 9.848931312561035,
310
+ "learning_rate": 2e-05,
311
+ "loss": 6.2172,
312
+ "mean_token_accuracy": 0.737366572022438,
313
+ "step": 38
314
+ },
315
+ {
316
+ "epoch": 0.312,
317
+ "grad_norm": 9.531893730163574,
318
+ "learning_rate": 1.9090909090909094e-05,
319
+ "loss": 6.8838,
320
+ "mean_token_accuracy": 0.6978575885295868,
321
+ "step": 39
322
+ },
323
+ {
324
+ "epoch": 0.32,
325
+ "grad_norm": 9.349637031555176,
326
+ "learning_rate": 1.8181818181818182e-05,
327
+ "loss": 6.739,
328
+ "mean_token_accuracy": 0.7097857445478439,
329
+ "step": 40
330
+ },
331
+ {
332
+ "epoch": 0.328,
333
+ "grad_norm": 9.532185554504395,
334
+ "learning_rate": 1.7272727272727274e-05,
335
+ "loss": 6.0505,
336
+ "mean_token_accuracy": 0.7424566149711609,
337
+ "step": 41
338
+ },
339
+ {
340
+ "epoch": 0.336,
341
+ "grad_norm": 8.855209350585938,
342
+ "learning_rate": 1.6363636363636366e-05,
343
+ "loss": 6.4006,
344
+ "mean_token_accuracy": 0.7251224219799042,
345
+ "step": 42
346
+ },
347
+ {
348
+ "epoch": 0.344,
349
+ "grad_norm": 8.668252944946289,
350
+ "learning_rate": 1.5454545454545454e-05,
351
+ "loss": 6.0441,
352
+ "mean_token_accuracy": 0.7409052848815918,
353
+ "step": 43
354
+ },
355
+ {
356
+ "epoch": 0.352,
357
+ "grad_norm": 10.111790657043457,
358
+ "learning_rate": 1.4545454545454545e-05,
359
+ "loss": 6.173,
360
+ "mean_token_accuracy": 0.7369689494371414,
361
+ "step": 44
362
+ },
363
+ {
364
+ "epoch": 0.36,
365
+ "grad_norm": 8.958393096923828,
366
+ "learning_rate": 1.3636363636363637e-05,
367
+ "loss": 6.2257,
368
+ "mean_token_accuracy": 0.7140295207500458,
369
+ "step": 45
370
+ },
371
+ {
372
+ "epoch": 0.368,
373
+ "grad_norm": 10.362472534179688,
374
+ "learning_rate": 1.2727272727272727e-05,
375
+ "loss": 5.2547,
376
+ "mean_token_accuracy": 0.7552689164876938,
377
+ "step": 46
378
+ },
379
+ {
380
+ "epoch": 0.376,
381
+ "grad_norm": 9.94664478302002,
382
+ "learning_rate": 1.1818181818181819e-05,
383
+ "loss": 5.992,
384
+ "mean_token_accuracy": 0.7395860105752945,
385
+ "step": 47
386
+ },
387
+ {
388
+ "epoch": 0.384,
389
+ "grad_norm": 8.77272891998291,
390
+ "learning_rate": 1.0909090909090909e-05,
391
+ "loss": 6.4631,
392
+ "mean_token_accuracy": 0.7185734361410141,
393
+ "step": 48
394
+ },
395
+ {
396
+ "epoch": 0.392,
397
+ "grad_norm": 8.110837936401367,
398
+ "learning_rate": 1e-05,
399
+ "loss": 6.3143,
400
+ "mean_token_accuracy": 0.7158133089542389,
401
+ "step": 49
402
+ },
403
+ {
404
+ "epoch": 0.4,
405
+ "grad_norm": 8.038437843322754,
406
+ "learning_rate": 9.090909090909091e-06,
407
+ "loss": 6.8103,
408
+ "mean_token_accuracy": 0.7134602963924408,
409
+ "step": 50
410
+ },
411
+ {
412
+ "epoch": 0.408,
413
+ "grad_norm": 8.795354843139648,
414
+ "learning_rate": 8.181818181818183e-06,
415
+ "loss": 6.0269,
416
+ "mean_token_accuracy": 0.7261971086263657,
417
+ "step": 51
418
+ },
419
+ {
420
+ "epoch": 0.416,
421
+ "grad_norm": 8.536953926086426,
422
+ "learning_rate": 7.272727272727272e-06,
423
+ "loss": 5.355,
424
+ "mean_token_accuracy": 0.7585936486721039,
425
+ "step": 52
426
+ },
427
+ {
428
+ "epoch": 0.424,
429
+ "grad_norm": 8.2533540725708,
430
+ "learning_rate": 6.363636363636363e-06,
431
+ "loss": 6.5612,
432
+ "mean_token_accuracy": 0.7138941884040833,
433
+ "step": 53
434
+ },
435
+ {
436
+ "epoch": 0.432,
437
+ "grad_norm": 9.274043083190918,
438
+ "learning_rate": 5.4545454545454545e-06,
439
+ "loss": 6.4098,
440
+ "mean_token_accuracy": 0.7215629369020462,
441
+ "step": 54
442
+ },
443
+ {
444
+ "epoch": 0.44,
445
+ "grad_norm": 9.127202987670898,
446
+ "learning_rate": 4.5454545454545455e-06,
447
+ "loss": 6.5323,
448
+ "mean_token_accuracy": 0.7295349985361099,
449
+ "step": 55
450
+ },
451
+ {
452
+ "epoch": 0.448,
453
+ "grad_norm": 8.477712631225586,
454
+ "learning_rate": 3.636363636363636e-06,
455
+ "loss": 5.4184,
456
+ "mean_token_accuracy": 0.7586539834737778,
457
+ "step": 56
458
+ },
459
+ {
460
+ "epoch": 0.456,
461
+ "grad_norm": 7.758520126342773,
462
+ "learning_rate": 2.7272727272727272e-06,
463
+ "loss": 6.2795,
464
+ "mean_token_accuracy": 0.7345724701881409,
465
+ "step": 57
466
+ },
467
+ {
468
+ "epoch": 0.464,
469
+ "grad_norm": 8.064261436462402,
470
+ "learning_rate": 1.818181818181818e-06,
471
+ "loss": 5.3877,
472
+ "mean_token_accuracy": 0.7539169639348984,
473
+ "step": 58
474
+ },
475
+ {
476
+ "epoch": 0.472,
477
+ "grad_norm": 8.512259483337402,
478
+ "learning_rate": 9.09090909090909e-07,
479
+ "loss": 5.8114,
480
+ "mean_token_accuracy": 0.7418429106473923,
481
+ "step": 59
482
+ },
483
+ {
484
+ "epoch": 0.48,
485
+ "grad_norm": 8.13984203338623,
486
+ "learning_rate": 0.0,
487
+ "loss": 5.8393,
488
+ "mean_token_accuracy": 0.7534664273262024,
489
+ "step": 60
490
+ }
491
+ ],
492
+ "logging_steps": 1,
493
+ "max_steps": 60,
494
+ "num_input_tokens_seen": 0,
495
+ "num_train_epochs": 1,
496
+ "save_steps": 500,
497
+ "stateful_callbacks": {
498
+ "TrainerControl": {
499
+ "args": {
500
+ "should_epoch_stop": false,
501
+ "should_evaluate": false,
502
+ "should_log": false,
503
+ "should_save": true,
504
+ "should_training_stop": true
505
+ },
506
+ "attributes": {}
507
+ }
508
+ },
509
+ "total_flos": 313206736158720.0,
510
+ "train_batch_size": 4,
511
+ "trial_name": null,
512
+ "trial_params": null
513
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da715b3c3e2461e889958f7693ca7f329c6d06895029ad9ecb508df681d870e8
3
+ size 5496
vocab.json ADDED
The diff for this file is too large to render. See raw diff