Hugging Face's logo

EXCO123
/
admdk10

Text Generation
Transformers
Safetensors
llama
trl
sft
conversational
text-generation-inference
Model card Files
xet
Community
EXCO123 commited on
Commit
64a4898
·
verified ·
1 Parent(s): 69b1e9f

Upload folder using huggingface_hub

Browse files
Files changed (13) hide show
  1. config.json +39 -0
  2. generation_config.json +7 -0
  3. merges.txt +0 -0
  4. model.safetensors +3 -0
  5. optimizer.pt +3 -0
  6. rng_state.pth +3 -0
  7. scheduler.pt +3 -0
  8. special_tokens_map.json +28 -0
  9. tokenizer.json +0 -0
  10. tokenizer_config.json +155 -0
  11. trainer_state.json +433 -0
  12. training_args.bin +3 -0
  13. vocab.json +0 -0
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 sha256:162f0b24e157ae1fab5f45d3f4b3daba9f452e1bdddff1946486b02f9d8c2bd3
3
+ size 538090408
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:70424b39c4a86379824a8e728e6d1a98a97fbff917b8ceb75e2785587da27460
3
+ size 273728186
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f078a27a793c86328ba28a6dfba5a1eb5bbedcd6e09d2fec0ba4b6f518c41808
3
+ size 14244
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:439e51f57871ee9c2bc8b35458a0c03f9b948af7a0d15ffe5e1cf9789955c6c8
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 +1,433 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.3902439024390243,
5
+ "eval_steps": 500,
6
+ "global_step": 50,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.04878048780487805,
13
+ "grad_norm": 5.292644023895264,
14
+ "learning_rate": 1e-05,
15
+ "loss": 4.2989,
16
+ "mean_token_accuracy": 0.7670535296201706,
17
+ "step": 1
18
+ },
19
+ {
20
+ "epoch": 0.0975609756097561,
21
+ "grad_norm": 5.072988033294678,
22
+ "learning_rate": 2e-05,
23
+ "loss": 4.9172,
24
+ "mean_token_accuracy": 0.7377254962921143,
25
+ "step": 2
26
+ },
27
+ {
28
+ "epoch": 0.14634146341463414,
29
+ "grad_norm": 5.262055397033691,
30
+ "learning_rate": 3e-05,
31
+ "loss": 4.3559,
32
+ "mean_token_accuracy": 0.7575394362211227,
33
+ "step": 3
34
+ },
35
+ {
36
+ "epoch": 0.1951219512195122,
37
+ "grad_norm": 4.690796375274658,
38
+ "learning_rate": 4e-05,
39
+ "loss": 4.0699,
40
+ "mean_token_accuracy": 0.775342732667923,
41
+ "step": 4
42
+ },
43
+ {
44
+ "epoch": 0.24390243902439024,
45
+ "grad_norm": 5.084864616394043,
46
+ "learning_rate": 5e-05,
47
+ "loss": 4.0367,
48
+ "mean_token_accuracy": 0.7870949655771255,
49
+ "step": 5
50
+ },
51
+ {
52
+ "epoch": 0.2926829268292683,
53
+ "grad_norm": 5.311507701873779,
54
+ "learning_rate": 4.888888888888889e-05,
55
+ "loss": 4.6084,
56
+ "mean_token_accuracy": 0.7504871934652328,
57
+ "step": 6
58
+ },
59
+ {
60
+ "epoch": 0.34146341463414637,
61
+ "grad_norm": 6.440568447113037,
62
+ "learning_rate": 4.7777777777777784e-05,
63
+ "loss": 4.7291,
64
+ "mean_token_accuracy": 0.7459312677383423,
65
+ "step": 7
66
+ },
67
+ {
68
+ "epoch": 0.3902439024390244,
69
+ "grad_norm": 6.664432048797607,
70
+ "learning_rate": 4.666666666666667e-05,
71
+ "loss": 4.5902,
72
+ "mean_token_accuracy": 0.7366409450769424,
73
+ "step": 8
74
+ },
75
+ {
76
+ "epoch": 0.43902439024390244,
77
+ "grad_norm": 6.393540382385254,
78
+ "learning_rate": 4.555555555555556e-05,
79
+ "loss": 3.9964,
80
+ "mean_token_accuracy": 0.7768445461988449,
81
+ "step": 9
82
+ },
83
+ {
84
+ "epoch": 0.4878048780487805,
85
+ "grad_norm": 7.187014579772949,
86
+ "learning_rate": 4.4444444444444447e-05,
87
+ "loss": 4.8158,
88
+ "mean_token_accuracy": 0.7345478385686874,
89
+ "step": 10
90
+ },
91
+ {
92
+ "epoch": 0.5365853658536586,
93
+ "grad_norm": 6.634271621704102,
94
+ "learning_rate": 4.3333333333333334e-05,
95
+ "loss": 4.3145,
96
+ "mean_token_accuracy": 0.7628218829631805,
97
+ "step": 11
98
+ },
99
+ {
100
+ "epoch": 0.5853658536585366,
101
+ "grad_norm": 6.83073091506958,
102
+ "learning_rate": 4.222222222222222e-05,
103
+ "loss": 4.4571,
104
+ "mean_token_accuracy": 0.7455749660730362,
105
+ "step": 12
106
+ },
107
+ {
108
+ "epoch": 0.6341463414634146,
109
+ "grad_norm": 6.895959854125977,
110
+ "learning_rate": 4.111111111111111e-05,
111
+ "loss": 4.0771,
112
+ "mean_token_accuracy": 0.7768183499574661,
113
+ "step": 13
114
+ },
115
+ {
116
+ "epoch": 0.6829268292682927,
117
+ "grad_norm": 6.867372035980225,
118
+ "learning_rate": 4e-05,
119
+ "loss": 4.4007,
120
+ "mean_token_accuracy": 0.7588072121143341,
121
+ "step": 14
122
+ },
123
+ {
124
+ "epoch": 0.7317073170731707,
125
+ "grad_norm": 6.1517791748046875,
126
+ "learning_rate": 3.888888888888889e-05,
127
+ "loss": 4.1443,
128
+ "mean_token_accuracy": 0.7709105908870697,
129
+ "step": 15
130
+ },
131
+ {
132
+ "epoch": 0.7804878048780488,
133
+ "grad_norm": 6.296253681182861,
134
+ "learning_rate": 3.777777777777778e-05,
135
+ "loss": 4.5376,
136
+ "mean_token_accuracy": 0.7590610980987549,
137
+ "step": 16
138
+ },
139
+ {
140
+ "epoch": 0.8292682926829268,
141
+ "grad_norm": 6.150022983551025,
142
+ "learning_rate": 3.6666666666666666e-05,
143
+ "loss": 4.1576,
144
+ "mean_token_accuracy": 0.7677088677883148,
145
+ "step": 17
146
+ },
147
+ {
148
+ "epoch": 0.8780487804878049,
149
+ "grad_norm": 6.601177215576172,
150
+ "learning_rate": 3.555555555555556e-05,
151
+ "loss": 4.8123,
152
+ "mean_token_accuracy": 0.7380577623844147,
153
+ "step": 18
154
+ },
155
+ {
156
+ "epoch": 0.926829268292683,
157
+ "grad_norm": 6.141186714172363,
158
+ "learning_rate": 3.444444444444445e-05,
159
+ "loss": 4.4355,
160
+ "mean_token_accuracy": 0.7588777989149094,
161
+ "step": 19
162
+ },
163
+ {
164
+ "epoch": 0.975609756097561,
165
+ "grad_norm": 7.759636402130127,
166
+ "learning_rate": 3.3333333333333335e-05,
167
+ "loss": 4.196,
168
+ "mean_token_accuracy": 0.7583473473787308,
169
+ "step": 20
170
+ },
171
+ {
172
+ "epoch": 1.0,
173
+ "grad_norm": 4.481691837310791,
174
+ "learning_rate": 3.222222222222223e-05,
175
+ "loss": 2.7981,
176
+ "mean_token_accuracy": 0.712793231010437,
177
+ "step": 21
178
+ },
179
+ {
180
+ "epoch": 1.048780487804878,
181
+ "grad_norm": 6.39988899230957,
182
+ "learning_rate": 3.111111111111111e-05,
183
+ "loss": 4.1204,
184
+ "mean_token_accuracy": 0.778206542134285,
185
+ "step": 22
186
+ },
187
+ {
188
+ "epoch": 1.0975609756097562,
189
+ "grad_norm": 5.795325756072998,
190
+ "learning_rate": 3e-05,
191
+ "loss": 3.2981,
192
+ "mean_token_accuracy": 0.8128762543201447,
193
+ "step": 23
194
+ },
195
+ {
196
+ "epoch": 1.146341463414634,
197
+ "grad_norm": 5.800813674926758,
198
+ "learning_rate": 2.8888888888888888e-05,
199
+ "loss": 3.6657,
200
+ "mean_token_accuracy": 0.7923942655324936,
201
+ "step": 24
202
+ },
203
+ {
204
+ "epoch": 1.1951219512195121,
205
+ "grad_norm": 6.182375431060791,
206
+ "learning_rate": 2.777777777777778e-05,
207
+ "loss": 4.0254,
208
+ "mean_token_accuracy": 0.773567721247673,
209
+ "step": 25
210
+ },
211
+ {
212
+ "epoch": 1.2439024390243902,
213
+ "grad_norm": 6.226065158843994,
214
+ "learning_rate": 2.6666666666666667e-05,
215
+ "loss": 3.6803,
216
+ "mean_token_accuracy": 0.7928623855113983,
217
+ "step": 26
218
+ },
219
+ {
220
+ "epoch": 1.2926829268292683,
221
+ "grad_norm": 5.555008411407471,
222
+ "learning_rate": 2.5555555555555554e-05,
223
+ "loss": 3.8551,
224
+ "mean_token_accuracy": 0.7828929722309113,
225
+ "step": 27
226
+ },
227
+ {
228
+ "epoch": 1.3414634146341464,
229
+ "grad_norm": 5.869503498077393,
230
+ "learning_rate": 2.4444444444444445e-05,
231
+ "loss": 3.9832,
232
+ "mean_token_accuracy": 0.7784373760223389,
233
+ "step": 28
234
+ },
235
+ {
236
+ "epoch": 1.3902439024390243,
237
+ "grad_norm": 5.494263172149658,
238
+ "learning_rate": 2.3333333333333336e-05,
239
+ "loss": 3.5122,
240
+ "mean_token_accuracy": 0.8014999330043793,
241
+ "step": 29
242
+ },
243
+ {
244
+ "epoch": 1.4390243902439024,
245
+ "grad_norm": 5.7608466148376465,
246
+ "learning_rate": 2.2222222222222223e-05,
247
+ "loss": 3.6381,
248
+ "mean_token_accuracy": 0.7957581877708435,
249
+ "step": 30
250
+ },
251
+ {
252
+ "epoch": 1.4878048780487805,
253
+ "grad_norm": 6.845158576965332,
254
+ "learning_rate": 2.111111111111111e-05,
255
+ "loss": 4.183,
256
+ "mean_token_accuracy": 0.7679397910833359,
257
+ "step": 31
258
+ },
259
+ {
260
+ "epoch": 1.5365853658536586,
261
+ "grad_norm": 6.817462921142578,
262
+ "learning_rate": 2e-05,
263
+ "loss": 4.2954,
264
+ "mean_token_accuracy": 0.7643744349479675,
265
+ "step": 32
266
+ },
267
+ {
268
+ "epoch": 1.5853658536585367,
269
+ "grad_norm": 5.7466349601745605,
270
+ "learning_rate": 1.888888888888889e-05,
271
+ "loss": 3.6042,
272
+ "mean_token_accuracy": 0.7952823042869568,
273
+ "step": 33
274
+ },
275
+ {
276
+ "epoch": 1.6341463414634148,
277
+ "grad_norm": 6.517263412475586,
278
+ "learning_rate": 1.777777777777778e-05,
279
+ "loss": 3.8403,
280
+ "mean_token_accuracy": 0.7832227051258087,
281
+ "step": 34
282
+ },
283
+ {
284
+ "epoch": 1.6829268292682928,
285
+ "grad_norm": 6.389585018157959,
286
+ "learning_rate": 1.6666666666666667e-05,
287
+ "loss": 4.1519,
288
+ "mean_token_accuracy": 0.7758816480636597,
289
+ "step": 35
290
+ },
291
+ {
292
+ "epoch": 1.7317073170731707,
293
+ "grad_norm": 6.375441551208496,
294
+ "learning_rate": 1.5555555555555555e-05,
295
+ "loss": 4.202,
296
+ "mean_token_accuracy": 0.7712285220623016,
297
+ "step": 36
298
+ },
299
+ {
300
+ "epoch": 1.7804878048780488,
301
+ "grad_norm": 6.385025501251221,
302
+ "learning_rate": 1.4444444444444444e-05,
303
+ "loss": 3.7112,
304
+ "mean_token_accuracy": 0.7900592088699341,
305
+ "step": 37
306
+ },
307
+ {
308
+ "epoch": 1.8292682926829267,
309
+ "grad_norm": 6.213353633880615,
310
+ "learning_rate": 1.3333333333333333e-05,
311
+ "loss": 3.9617,
312
+ "mean_token_accuracy": 0.7816430032253265,
313
+ "step": 38
314
+ },
315
+ {
316
+ "epoch": 1.8780487804878048,
317
+ "grad_norm": 6.150025367736816,
318
+ "learning_rate": 1.2222222222222222e-05,
319
+ "loss": 4.0205,
320
+ "mean_token_accuracy": 0.7726276069879532,
321
+ "step": 39
322
+ },
323
+ {
324
+ "epoch": 1.9268292682926829,
325
+ "grad_norm": 6.346643924713135,
326
+ "learning_rate": 1.1111111111111112e-05,
327
+ "loss": 4.3219,
328
+ "mean_token_accuracy": 0.7638045698404312,
329
+ "step": 40
330
+ },
331
+ {
332
+ "epoch": 1.975609756097561,
333
+ "grad_norm": 6.996342182159424,
334
+ "learning_rate": 1e-05,
335
+ "loss": 4.0849,
336
+ "mean_token_accuracy": 0.7685424983501434,
337
+ "step": 41
338
+ },
339
+ {
340
+ "epoch": 2.0,
341
+ "grad_norm": 4.610576629638672,
342
+ "learning_rate": 8.88888888888889e-06,
343
+ "loss": 2.252,
344
+ "mean_token_accuracy": 0.757177472114563,
345
+ "step": 42
346
+ },
347
+ {
348
+ "epoch": 2.048780487804878,
349
+ "grad_norm": 5.402480602264404,
350
+ "learning_rate": 7.777777777777777e-06,
351
+ "loss": 3.6178,
352
+ "mean_token_accuracy": 0.8000039011240005,
353
+ "step": 43
354
+ },
355
+ {
356
+ "epoch": 2.097560975609756,
357
+ "grad_norm": 5.952712535858154,
358
+ "learning_rate": 6.666666666666667e-06,
359
+ "loss": 3.1941,
360
+ "mean_token_accuracy": 0.8220265060663223,
361
+ "step": 44
362
+ },
363
+ {
364
+ "epoch": 2.1463414634146343,
365
+ "grad_norm": 5.641570568084717,
366
+ "learning_rate": 5.555555555555556e-06,
367
+ "loss": 3.7628,
368
+ "mean_token_accuracy": 0.7894951105117798,
369
+ "step": 45
370
+ },
371
+ {
372
+ "epoch": 2.1951219512195124,
373
+ "grad_norm": 5.362001895904541,
374
+ "learning_rate": 4.444444444444445e-06,
375
+ "loss": 3.128,
376
+ "mean_token_accuracy": 0.8270062953233719,
377
+ "step": 46
378
+ },
379
+ {
380
+ "epoch": 2.2439024390243905,
381
+ "grad_norm": 5.856266021728516,
382
+ "learning_rate": 3.3333333333333333e-06,
383
+ "loss": 3.7393,
384
+ "mean_token_accuracy": 0.7911360561847687,
385
+ "step": 47
386
+ },
387
+ {
388
+ "epoch": 2.292682926829268,
389
+ "grad_norm": 6.097686290740967,
390
+ "learning_rate": 2.2222222222222225e-06,
391
+ "loss": 3.452,
392
+ "mean_token_accuracy": 0.8116942197084427,
393
+ "step": 48
394
+ },
395
+ {
396
+ "epoch": 2.341463414634146,
397
+ "grad_norm": 5.644529342651367,
398
+ "learning_rate": 1.1111111111111112e-06,
399
+ "loss": 3.4835,
400
+ "mean_token_accuracy": 0.8041615337133408,
401
+ "step": 49
402
+ },
403
+ {
404
+ "epoch": 2.3902439024390243,
405
+ "grad_norm": 5.310006618499756,
406
+ "learning_rate": 0.0,
407
+ "loss": 3.3661,
408
+ "mean_token_accuracy": 0.8213394284248352,
409
+ "step": 50
410
+ }
411
+ ],
412
+ "logging_steps": 1,
413
+ "max_steps": 50,
414
+ "num_input_tokens_seen": 0,
415
+ "num_train_epochs": 3,
416
+ "save_steps": 500,
417
+ "stateful_callbacks": {
418
+ "TrainerControl": {
419
+ "args": {
420
+ "should_epoch_stop": false,
421
+ "should_evaluate": false,
422
+ "should_log": false,
423
+ "should_save": true,
424
+ "should_training_stop": true
425
+ },
426
+ "attributes": {}
427
+ }
428
+ },
429
+ "total_flos": 255785501196288.0,
430
+ "train_batch_size": 4,
431
+ "trial_name": null,
432
+ "trial_params": null
433
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aee6e8f758a8cf602475b7f4b0a32a5f5db8deb5200715d846930092191d1844
3
+ size 5496
vocab.json ADDED
The diff for this file is too large to render. See raw diff