ukung commited on
Commit
8801c88
·
verified ·
1 Parent(s): 9b19068

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 sha256:2b177525e053e662c8ce8c8a8513d1cae3071edc813953a7ca7bf84e27c19b91
3
+ size 538090408
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c11080d5e63ec40cd6eec78bdeb76fe84ffa0f0006be437c99e2916770dcfcb9
3
+ size 273728442
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:448594757d6de5d1e88c4f56dc0f856ce5b411ae6f4a9716f1743b750f7387d1
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": 2.0846560846560847,
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": 0.021164021164021163,
13
+ "grad_norm": 6.048354625701904,
14
+ "learning_rate": 1e-05,
15
+ "loss": 3.1366,
16
+ "mean_token_accuracy": 0.8490224033594131,
17
+ "step": 1
18
+ },
19
+ {
20
+ "epoch": 0.042328042328042326,
21
+ "grad_norm": 6.282668590545654,
22
+ "learning_rate": 2e-05,
23
+ "loss": 3.3445,
24
+ "mean_token_accuracy": 0.8413912802934647,
25
+ "step": 2
26
+ },
27
+ {
28
+ "epoch": 0.06349206349206349,
29
+ "grad_norm": 5.931667327880859,
30
+ "learning_rate": 3e-05,
31
+ "loss": 3.6371,
32
+ "mean_token_accuracy": 0.819273829460144,
33
+ "step": 3
34
+ },
35
+ {
36
+ "epoch": 0.08465608465608465,
37
+ "grad_norm": 5.271315097808838,
38
+ "learning_rate": 4e-05,
39
+ "loss": 2.8728,
40
+ "mean_token_accuracy": 0.864514172077179,
41
+ "step": 4
42
+ },
43
+ {
44
+ "epoch": 0.10582010582010581,
45
+ "grad_norm": 6.306461811065674,
46
+ "learning_rate": 5e-05,
47
+ "loss": 3.2277,
48
+ "mean_token_accuracy": 0.8422431498765945,
49
+ "step": 5
50
+ },
51
+ {
52
+ "epoch": 0.12698412698412698,
53
+ "grad_norm": 7.170639514923096,
54
+ "learning_rate": 4.9473684210526315e-05,
55
+ "loss": 3.1188,
56
+ "mean_token_accuracy": 0.8523378223180771,
57
+ "step": 6
58
+ },
59
+ {
60
+ "epoch": 0.14814814814814814,
61
+ "grad_norm": 6.320353984832764,
62
+ "learning_rate": 4.8947368421052635e-05,
63
+ "loss": 3.2011,
64
+ "mean_token_accuracy": 0.8276277035474777,
65
+ "step": 7
66
+ },
67
+ {
68
+ "epoch": 0.1693121693121693,
69
+ "grad_norm": 7.527361869812012,
70
+ "learning_rate": 4.842105263157895e-05,
71
+ "loss": 3.5806,
72
+ "mean_token_accuracy": 0.8307382017374039,
73
+ "step": 8
74
+ },
75
+ {
76
+ "epoch": 0.19047619047619047,
77
+ "grad_norm": 9.139302253723145,
78
+ "learning_rate": 4.789473684210526e-05,
79
+ "loss": 3.3045,
80
+ "mean_token_accuracy": 0.8234163820743561,
81
+ "step": 9
82
+ },
83
+ {
84
+ "epoch": 0.21164021164021163,
85
+ "grad_norm": 8.344583511352539,
86
+ "learning_rate": 4.736842105263158e-05,
87
+ "loss": 3.4053,
88
+ "mean_token_accuracy": 0.8328999727964401,
89
+ "step": 10
90
+ },
91
+ {
92
+ "epoch": 0.2328042328042328,
93
+ "grad_norm": 7.198660850524902,
94
+ "learning_rate": 4.68421052631579e-05,
95
+ "loss": 3.6999,
96
+ "mean_token_accuracy": 0.8166868537664413,
97
+ "step": 11
98
+ },
99
+ {
100
+ "epoch": 0.25396825396825395,
101
+ "grad_norm": 7.656338691711426,
102
+ "learning_rate": 4.6315789473684214e-05,
103
+ "loss": 3.5236,
104
+ "mean_token_accuracy": 0.8194563537836075,
105
+ "step": 12
106
+ },
107
+ {
108
+ "epoch": 0.2751322751322751,
109
+ "grad_norm": 6.596268653869629,
110
+ "learning_rate": 4.5789473684210527e-05,
111
+ "loss": 3.1002,
112
+ "mean_token_accuracy": 0.8456875830888748,
113
+ "step": 13
114
+ },
115
+ {
116
+ "epoch": 0.2962962962962963,
117
+ "grad_norm": 7.026238918304443,
118
+ "learning_rate": 4.5263157894736846e-05,
119
+ "loss": 3.5912,
120
+ "mean_token_accuracy": 0.8176615834236145,
121
+ "step": 14
122
+ },
123
+ {
124
+ "epoch": 0.31746031746031744,
125
+ "grad_norm": 6.6125640869140625,
126
+ "learning_rate": 4.473684210526316e-05,
127
+ "loss": 3.2967,
128
+ "mean_token_accuracy": 0.8385807871818542,
129
+ "step": 15
130
+ },
131
+ {
132
+ "epoch": 0.3386243386243386,
133
+ "grad_norm": 6.488234043121338,
134
+ "learning_rate": 4.421052631578947e-05,
135
+ "loss": 2.9518,
136
+ "mean_token_accuracy": 0.8566168546676636,
137
+ "step": 16
138
+ },
139
+ {
140
+ "epoch": 0.35978835978835977,
141
+ "grad_norm": 6.3693389892578125,
142
+ "learning_rate": 4.368421052631579e-05,
143
+ "loss": 3.4379,
144
+ "mean_token_accuracy": 0.8285104632377625,
145
+ "step": 17
146
+ },
147
+ {
148
+ "epoch": 0.38095238095238093,
149
+ "grad_norm": 6.490217208862305,
150
+ "learning_rate": 4.3157894736842105e-05,
151
+ "loss": 3.2799,
152
+ "mean_token_accuracy": 0.8258774131536484,
153
+ "step": 18
154
+ },
155
+ {
156
+ "epoch": 0.4021164021164021,
157
+ "grad_norm": 6.357998847961426,
158
+ "learning_rate": 4.2631578947368425e-05,
159
+ "loss": 3.556,
160
+ "mean_token_accuracy": 0.8310040086507797,
161
+ "step": 19
162
+ },
163
+ {
164
+ "epoch": 0.42328042328042326,
165
+ "grad_norm": 6.8284807205200195,
166
+ "learning_rate": 4.210526315789474e-05,
167
+ "loss": 3.225,
168
+ "mean_token_accuracy": 0.8262167721986771,
169
+ "step": 20
170
+ },
171
+ {
172
+ "epoch": 0.4444444444444444,
173
+ "grad_norm": 6.557299613952637,
174
+ "learning_rate": 4.157894736842106e-05,
175
+ "loss": 2.8915,
176
+ "mean_token_accuracy": 0.8450914323329926,
177
+ "step": 21
178
+ },
179
+ {
180
+ "epoch": 0.4656084656084656,
181
+ "grad_norm": 6.227797508239746,
182
+ "learning_rate": 4.105263157894737e-05,
183
+ "loss": 3.5964,
184
+ "mean_token_accuracy": 0.8293115049600601,
185
+ "step": 22
186
+ },
187
+ {
188
+ "epoch": 0.48677248677248675,
189
+ "grad_norm": 6.4811482429504395,
190
+ "learning_rate": 4.0526315789473684e-05,
191
+ "loss": 2.9146,
192
+ "mean_token_accuracy": 0.8511508405208588,
193
+ "step": 23
194
+ },
195
+ {
196
+ "epoch": 0.5079365079365079,
197
+ "grad_norm": 7.390919208526611,
198
+ "learning_rate": 4e-05,
199
+ "loss": 3.0839,
200
+ "mean_token_accuracy": 0.8521782755851746,
201
+ "step": 24
202
+ },
203
+ {
204
+ "epoch": 0.5291005291005291,
205
+ "grad_norm": 7.000582695007324,
206
+ "learning_rate": 3.9473684210526316e-05,
207
+ "loss": 3.419,
208
+ "mean_token_accuracy": 0.8302050828933716,
209
+ "step": 25
210
+ },
211
+ {
212
+ "epoch": 0.5502645502645502,
213
+ "grad_norm": 7.646208763122559,
214
+ "learning_rate": 3.894736842105263e-05,
215
+ "loss": 3.5312,
216
+ "mean_token_accuracy": 0.8222539722919464,
217
+ "step": 26
218
+ },
219
+ {
220
+ "epoch": 0.5714285714285714,
221
+ "grad_norm": 8.202258110046387,
222
+ "learning_rate": 3.842105263157895e-05,
223
+ "loss": 3.2736,
224
+ "mean_token_accuracy": 0.8385538011789322,
225
+ "step": 27
226
+ },
227
+ {
228
+ "epoch": 0.5925925925925926,
229
+ "grad_norm": 7.112030982971191,
230
+ "learning_rate": 3.789473684210527e-05,
231
+ "loss": 3.5607,
232
+ "mean_token_accuracy": 0.8270172476768494,
233
+ "step": 28
234
+ },
235
+ {
236
+ "epoch": 0.6137566137566137,
237
+ "grad_norm": 7.77510404586792,
238
+ "learning_rate": 3.736842105263158e-05,
239
+ "loss": 3.4509,
240
+ "mean_token_accuracy": 0.8338000029325485,
241
+ "step": 29
242
+ },
243
+ {
244
+ "epoch": 0.6349206349206349,
245
+ "grad_norm": 8.627528190612793,
246
+ "learning_rate": 3.6842105263157895e-05,
247
+ "loss": 3.4089,
248
+ "mean_token_accuracy": 0.8251242786645889,
249
+ "step": 30
250
+ },
251
+ {
252
+ "epoch": 0.656084656084656,
253
+ "grad_norm": 7.149316787719727,
254
+ "learning_rate": 3.6315789473684214e-05,
255
+ "loss": 3.0029,
256
+ "mean_token_accuracy": 0.8458760529756546,
257
+ "step": 31
258
+ },
259
+ {
260
+ "epoch": 0.6772486772486772,
261
+ "grad_norm": 8.06534194946289,
262
+ "learning_rate": 3.578947368421053e-05,
263
+ "loss": 3.2129,
264
+ "mean_token_accuracy": 0.8390202522277832,
265
+ "step": 32
266
+ },
267
+ {
268
+ "epoch": 0.6984126984126984,
269
+ "grad_norm": 6.458263397216797,
270
+ "learning_rate": 3.526315789473684e-05,
271
+ "loss": 3.7385,
272
+ "mean_token_accuracy": 0.8196459114551544,
273
+ "step": 33
274
+ },
275
+ {
276
+ "epoch": 0.7195767195767195,
277
+ "grad_norm": 6.388949394226074,
278
+ "learning_rate": 3.473684210526316e-05,
279
+ "loss": 3.0692,
280
+ "mean_token_accuracy": 0.8393152952194214,
281
+ "step": 34
282
+ },
283
+ {
284
+ "epoch": 0.7407407407407407,
285
+ "grad_norm": 7.467120170593262,
286
+ "learning_rate": 3.421052631578947e-05,
287
+ "loss": 3.4118,
288
+ "mean_token_accuracy": 0.8257147669792175,
289
+ "step": 35
290
+ },
291
+ {
292
+ "epoch": 0.7619047619047619,
293
+ "grad_norm": 7.274282932281494,
294
+ "learning_rate": 3.368421052631579e-05,
295
+ "loss": 3.2201,
296
+ "mean_token_accuracy": 0.8417303115129471,
297
+ "step": 36
298
+ },
299
+ {
300
+ "epoch": 0.783068783068783,
301
+ "grad_norm": 7.1840500831604,
302
+ "learning_rate": 3.3157894736842106e-05,
303
+ "loss": 3.2211,
304
+ "mean_token_accuracy": 0.8373906314373016,
305
+ "step": 37
306
+ },
307
+ {
308
+ "epoch": 0.8042328042328042,
309
+ "grad_norm": 6.900996685028076,
310
+ "learning_rate": 3.2631578947368426e-05,
311
+ "loss": 3.4252,
312
+ "mean_token_accuracy": 0.8245490044355392,
313
+ "step": 38
314
+ },
315
+ {
316
+ "epoch": 0.8253968253968254,
317
+ "grad_norm": 6.207952976226807,
318
+ "learning_rate": 3.210526315789474e-05,
319
+ "loss": 3.1038,
320
+ "mean_token_accuracy": 0.8480600118637085,
321
+ "step": 39
322
+ },
323
+ {
324
+ "epoch": 0.8465608465608465,
325
+ "grad_norm": 6.920236587524414,
326
+ "learning_rate": 3.157894736842105e-05,
327
+ "loss": 3.3569,
328
+ "mean_token_accuracy": 0.8315872251987457,
329
+ "step": 40
330
+ },
331
+ {
332
+ "epoch": 0.8677248677248677,
333
+ "grad_norm": 7.361562728881836,
334
+ "learning_rate": 3.105263157894737e-05,
335
+ "loss": 3.6389,
336
+ "mean_token_accuracy": 0.8231257498264313,
337
+ "step": 41
338
+ },
339
+ {
340
+ "epoch": 0.8888888888888888,
341
+ "grad_norm": 6.357892036437988,
342
+ "learning_rate": 3.0526315789473684e-05,
343
+ "loss": 3.3438,
344
+ "mean_token_accuracy": 0.8264831602573395,
345
+ "step": 42
346
+ },
347
+ {
348
+ "epoch": 0.91005291005291,
349
+ "grad_norm": 6.043882369995117,
350
+ "learning_rate": 3e-05,
351
+ "loss": 3.3171,
352
+ "mean_token_accuracy": 0.8378995358943939,
353
+ "step": 43
354
+ },
355
+ {
356
+ "epoch": 0.9312169312169312,
357
+ "grad_norm": 6.81577205657959,
358
+ "learning_rate": 2.9473684210526314e-05,
359
+ "loss": 3.2854,
360
+ "mean_token_accuracy": 0.8394952565431595,
361
+ "step": 44
362
+ },
363
+ {
364
+ "epoch": 0.9523809523809523,
365
+ "grad_norm": 6.861083030700684,
366
+ "learning_rate": 2.8947368421052634e-05,
367
+ "loss": 3.1802,
368
+ "mean_token_accuracy": 0.8438083976507187,
369
+ "step": 45
370
+ },
371
+ {
372
+ "epoch": 0.9735449735449735,
373
+ "grad_norm": 7.255928039550781,
374
+ "learning_rate": 2.842105263157895e-05,
375
+ "loss": 3.7687,
376
+ "mean_token_accuracy": 0.8107610791921616,
377
+ "step": 46
378
+ },
379
+ {
380
+ "epoch": 0.9947089947089947,
381
+ "grad_norm": 6.662189483642578,
382
+ "learning_rate": 2.7894736842105263e-05,
383
+ "loss": 2.8252,
384
+ "mean_token_accuracy": 0.8516946136951447,
385
+ "step": 47
386
+ },
387
+ {
388
+ "epoch": 1.0,
389
+ "grad_norm": 2.8546807765960693,
390
+ "learning_rate": 2.7368421052631583e-05,
391
+ "loss": 0.7518,
392
+ "mean_token_accuracy": 0.8395061492919922,
393
+ "step": 48
394
+ },
395
+ {
396
+ "epoch": 1.0211640211640212,
397
+ "grad_norm": 5.928465843200684,
398
+ "learning_rate": 2.6842105263157896e-05,
399
+ "loss": 2.9837,
400
+ "mean_token_accuracy": 0.8488393574953079,
401
+ "step": 49
402
+ },
403
+ {
404
+ "epoch": 1.0423280423280423,
405
+ "grad_norm": 7.0468363761901855,
406
+ "learning_rate": 2.6315789473684212e-05,
407
+ "loss": 2.9965,
408
+ "mean_token_accuracy": 0.8516333252191544,
409
+ "step": 50
410
+ },
411
+ {
412
+ "epoch": 1.0634920634920635,
413
+ "grad_norm": 6.113859176635742,
414
+ "learning_rate": 2.578947368421053e-05,
415
+ "loss": 2.9239,
416
+ "mean_token_accuracy": 0.846625804901123,
417
+ "step": 51
418
+ },
419
+ {
420
+ "epoch": 1.0846560846560847,
421
+ "grad_norm": 6.449796199798584,
422
+ "learning_rate": 2.5263157894736845e-05,
423
+ "loss": 2.9745,
424
+ "mean_token_accuracy": 0.8498904705047607,
425
+ "step": 52
426
+ },
427
+ {
428
+ "epoch": 1.1058201058201058,
429
+ "grad_norm": 6.227660655975342,
430
+ "learning_rate": 2.4736842105263158e-05,
431
+ "loss": 2.7134,
432
+ "mean_token_accuracy": 0.8572945147752762,
433
+ "step": 53
434
+ },
435
+ {
436
+ "epoch": 1.126984126984127,
437
+ "grad_norm": 6.191722869873047,
438
+ "learning_rate": 2.4210526315789474e-05,
439
+ "loss": 2.9167,
440
+ "mean_token_accuracy": 0.8419267982244492,
441
+ "step": 54
442
+ },
443
+ {
444
+ "epoch": 1.1481481481481481,
445
+ "grad_norm": 6.0019307136535645,
446
+ "learning_rate": 2.368421052631579e-05,
447
+ "loss": 2.8168,
448
+ "mean_token_accuracy": 0.8558094352483749,
449
+ "step": 55
450
+ },
451
+ {
452
+ "epoch": 1.1693121693121693,
453
+ "grad_norm": 6.954141139984131,
454
+ "learning_rate": 2.3157894736842107e-05,
455
+ "loss": 3.0574,
456
+ "mean_token_accuracy": 0.8407768905162811,
457
+ "step": 56
458
+ },
459
+ {
460
+ "epoch": 1.1904761904761905,
461
+ "grad_norm": 6.376841068267822,
462
+ "learning_rate": 2.2631578947368423e-05,
463
+ "loss": 3.1123,
464
+ "mean_token_accuracy": 0.8525369018316269,
465
+ "step": 57
466
+ },
467
+ {
468
+ "epoch": 1.2116402116402116,
469
+ "grad_norm": 6.693148612976074,
470
+ "learning_rate": 2.2105263157894736e-05,
471
+ "loss": 2.351,
472
+ "mean_token_accuracy": 0.8728293180465698,
473
+ "step": 58
474
+ },
475
+ {
476
+ "epoch": 1.2328042328042328,
477
+ "grad_norm": 7.382028102874756,
478
+ "learning_rate": 2.1578947368421053e-05,
479
+ "loss": 3.065,
480
+ "mean_token_accuracy": 0.8475844711065292,
481
+ "step": 59
482
+ },
483
+ {
484
+ "epoch": 1.253968253968254,
485
+ "grad_norm": 6.0569682121276855,
486
+ "learning_rate": 2.105263157894737e-05,
487
+ "loss": 2.7,
488
+ "mean_token_accuracy": 0.8730548322200775,
489
+ "step": 60
490
+ },
491
+ {
492
+ "epoch": 1.2751322751322751,
493
+ "grad_norm": 6.204995632171631,
494
+ "learning_rate": 2.0526315789473685e-05,
495
+ "loss": 2.4867,
496
+ "mean_token_accuracy": 0.8747055679559708,
497
+ "step": 61
498
+ },
499
+ {
500
+ "epoch": 1.2962962962962963,
501
+ "grad_norm": 7.9132466316223145,
502
+ "learning_rate": 2e-05,
503
+ "loss": 2.634,
504
+ "mean_token_accuracy": 0.8690300732851028,
505
+ "step": 62
506
+ },
507
+ {
508
+ "epoch": 1.3174603174603174,
509
+ "grad_norm": 6.757488250732422,
510
+ "learning_rate": 1.9473684210526315e-05,
511
+ "loss": 2.4285,
512
+ "mean_token_accuracy": 0.8734888136386871,
513
+ "step": 63
514
+ },
515
+ {
516
+ "epoch": 1.3386243386243386,
517
+ "grad_norm": 6.5959930419921875,
518
+ "learning_rate": 1.8947368421052634e-05,
519
+ "loss": 2.7514,
520
+ "mean_token_accuracy": 0.861017182469368,
521
+ "step": 64
522
+ },
523
+ {
524
+ "epoch": 1.3597883597883598,
525
+ "grad_norm": 6.472837448120117,
526
+ "learning_rate": 1.8421052631578947e-05,
527
+ "loss": 2.3507,
528
+ "mean_token_accuracy": 0.8777505159378052,
529
+ "step": 65
530
+ },
531
+ {
532
+ "epoch": 1.380952380952381,
533
+ "grad_norm": 7.2989959716796875,
534
+ "learning_rate": 1.7894736842105264e-05,
535
+ "loss": 2.5765,
536
+ "mean_token_accuracy": 0.8751945346593857,
537
+ "step": 66
538
+ },
539
+ {
540
+ "epoch": 1.402116402116402,
541
+ "grad_norm": 7.222543716430664,
542
+ "learning_rate": 1.736842105263158e-05,
543
+ "loss": 2.8945,
544
+ "mean_token_accuracy": 0.8649410307407379,
545
+ "step": 67
546
+ },
547
+ {
548
+ "epoch": 1.4232804232804233,
549
+ "grad_norm": 8.021060943603516,
550
+ "learning_rate": 1.6842105263157896e-05,
551
+ "loss": 3.104,
552
+ "mean_token_accuracy": 0.841856375336647,
553
+ "step": 68
554
+ },
555
+ {
556
+ "epoch": 1.4444444444444444,
557
+ "grad_norm": 6.828577995300293,
558
+ "learning_rate": 1.6315789473684213e-05,
559
+ "loss": 2.562,
560
+ "mean_token_accuracy": 0.8617057651281357,
561
+ "step": 69
562
+ },
563
+ {
564
+ "epoch": 1.4656084656084656,
565
+ "grad_norm": 7.925837993621826,
566
+ "learning_rate": 1.5789473684210526e-05,
567
+ "loss": 3.0748,
568
+ "mean_token_accuracy": 0.8369355648756027,
569
+ "step": 70
570
+ },
571
+ {
572
+ "epoch": 1.4867724867724867,
573
+ "grad_norm": 7.627265930175781,
574
+ "learning_rate": 1.5263157894736842e-05,
575
+ "loss": 2.7155,
576
+ "mean_token_accuracy": 0.8586581945419312,
577
+ "step": 71
578
+ },
579
+ {
580
+ "epoch": 1.507936507936508,
581
+ "grad_norm": 6.797243595123291,
582
+ "learning_rate": 1.4736842105263157e-05,
583
+ "loss": 2.9972,
584
+ "mean_token_accuracy": 0.8588763475418091,
585
+ "step": 72
586
+ },
587
+ {
588
+ "epoch": 1.529100529100529,
589
+ "grad_norm": 6.557271957397461,
590
+ "learning_rate": 1.4210526315789475e-05,
591
+ "loss": 2.7672,
592
+ "mean_token_accuracy": 0.8697129487991333,
593
+ "step": 73
594
+ },
595
+ {
596
+ "epoch": 1.5502645502645502,
597
+ "grad_norm": 7.8767828941345215,
598
+ "learning_rate": 1.3684210526315791e-05,
599
+ "loss": 2.6796,
600
+ "mean_token_accuracy": 0.8595937788486481,
601
+ "step": 74
602
+ },
603
+ {
604
+ "epoch": 1.5714285714285714,
605
+ "grad_norm": 6.961939334869385,
606
+ "learning_rate": 1.3157894736842106e-05,
607
+ "loss": 2.9875,
608
+ "mean_token_accuracy": 0.8416125029325485,
609
+ "step": 75
610
+ },
611
+ {
612
+ "epoch": 1.5925925925925926,
613
+ "grad_norm": 7.682628154754639,
614
+ "learning_rate": 1.2631578947368422e-05,
615
+ "loss": 2.7506,
616
+ "mean_token_accuracy": 0.8638267368078232,
617
+ "step": 76
618
+ },
619
+ {
620
+ "epoch": 1.6137566137566137,
621
+ "grad_norm": 7.030145168304443,
622
+ "learning_rate": 1.2105263157894737e-05,
623
+ "loss": 3.016,
624
+ "mean_token_accuracy": 0.8373551815748215,
625
+ "step": 77
626
+ },
627
+ {
628
+ "epoch": 1.6349206349206349,
629
+ "grad_norm": 6.8483357429504395,
630
+ "learning_rate": 1.1578947368421053e-05,
631
+ "loss": 2.9225,
632
+ "mean_token_accuracy": 0.8537007570266724,
633
+ "step": 78
634
+ },
635
+ {
636
+ "epoch": 1.656084656084656,
637
+ "grad_norm": 6.3635358810424805,
638
+ "learning_rate": 1.1052631578947368e-05,
639
+ "loss": 2.605,
640
+ "mean_token_accuracy": 0.8712249547243118,
641
+ "step": 79
642
+ },
643
+ {
644
+ "epoch": 1.6772486772486772,
645
+ "grad_norm": 6.841208457946777,
646
+ "learning_rate": 1.0526315789473684e-05,
647
+ "loss": 2.649,
648
+ "mean_token_accuracy": 0.8548033833503723,
649
+ "step": 80
650
+ },
651
+ {
652
+ "epoch": 1.6984126984126984,
653
+ "grad_norm": 6.934281826019287,
654
+ "learning_rate": 1e-05,
655
+ "loss": 2.7121,
656
+ "mean_token_accuracy": 0.8624187707901001,
657
+ "step": 81
658
+ },
659
+ {
660
+ "epoch": 1.7195767195767195,
661
+ "grad_norm": 7.023396968841553,
662
+ "learning_rate": 9.473684210526317e-06,
663
+ "loss": 2.7811,
664
+ "mean_token_accuracy": 0.8551411479711533,
665
+ "step": 82
666
+ },
667
+ {
668
+ "epoch": 1.7407407407407407,
669
+ "grad_norm": 6.556440830230713,
670
+ "learning_rate": 8.947368421052632e-06,
671
+ "loss": 2.4777,
672
+ "mean_token_accuracy": 0.8696417659521103,
673
+ "step": 83
674
+ },
675
+ {
676
+ "epoch": 1.7619047619047619,
677
+ "grad_norm": 6.040866374969482,
678
+ "learning_rate": 8.421052631578948e-06,
679
+ "loss": 2.578,
680
+ "mean_token_accuracy": 0.8646088093519211,
681
+ "step": 84
682
+ },
683
+ {
684
+ "epoch": 1.783068783068783,
685
+ "grad_norm": 6.976686000823975,
686
+ "learning_rate": 7.894736842105263e-06,
687
+ "loss": 3.0012,
688
+ "mean_token_accuracy": 0.8455324172973633,
689
+ "step": 85
690
+ },
691
+ {
692
+ "epoch": 1.8042328042328042,
693
+ "grad_norm": 6.477259635925293,
694
+ "learning_rate": 7.3684210526315784e-06,
695
+ "loss": 2.6865,
696
+ "mean_token_accuracy": 0.8627304285764694,
697
+ "step": 86
698
+ },
699
+ {
700
+ "epoch": 1.8253968253968254,
701
+ "grad_norm": 6.601570129394531,
702
+ "learning_rate": 6.842105263157896e-06,
703
+ "loss": 2.8802,
704
+ "mean_token_accuracy": 0.8515039086341858,
705
+ "step": 87
706
+ },
707
+ {
708
+ "epoch": 1.8465608465608465,
709
+ "grad_norm": 6.802147388458252,
710
+ "learning_rate": 6.315789473684211e-06,
711
+ "loss": 2.6333,
712
+ "mean_token_accuracy": 0.8652176707983017,
713
+ "step": 88
714
+ },
715
+ {
716
+ "epoch": 1.8677248677248677,
717
+ "grad_norm": 6.9757843017578125,
718
+ "learning_rate": 5.789473684210527e-06,
719
+ "loss": 2.5824,
720
+ "mean_token_accuracy": 0.8683836162090302,
721
+ "step": 89
722
+ },
723
+ {
724
+ "epoch": 1.8888888888888888,
725
+ "grad_norm": 8.725011825561523,
726
+ "learning_rate": 5.263157894736842e-06,
727
+ "loss": 2.0392,
728
+ "mean_token_accuracy": 0.8908423334360123,
729
+ "step": 90
730
+ },
731
+ {
732
+ "epoch": 1.91005291005291,
733
+ "grad_norm": 6.747620105743408,
734
+ "learning_rate": 4.736842105263159e-06,
735
+ "loss": 2.5522,
736
+ "mean_token_accuracy": 0.8612807095050812,
737
+ "step": 91
738
+ },
739
+ {
740
+ "epoch": 1.9312169312169312,
741
+ "grad_norm": 7.072465419769287,
742
+ "learning_rate": 4.210526315789474e-06,
743
+ "loss": 3.1815,
744
+ "mean_token_accuracy": 0.836863324046135,
745
+ "step": 92
746
+ },
747
+ {
748
+ "epoch": 1.9523809523809523,
749
+ "grad_norm": 5.726354122161865,
750
+ "learning_rate": 3.6842105263157892e-06,
751
+ "loss": 2.8141,
752
+ "mean_token_accuracy": 0.8544116318225861,
753
+ "step": 93
754
+ },
755
+ {
756
+ "epoch": 1.9735449735449735,
757
+ "grad_norm": 6.540099620819092,
758
+ "learning_rate": 3.1578947368421056e-06,
759
+ "loss": 2.2286,
760
+ "mean_token_accuracy": 0.8898429274559021,
761
+ "step": 94
762
+ },
763
+ {
764
+ "epoch": 1.9947089947089947,
765
+ "grad_norm": 6.0961222648620605,
766
+ "learning_rate": 2.631578947368421e-06,
767
+ "loss": 2.634,
768
+ "mean_token_accuracy": 0.8558461666107178,
769
+ "step": 95
770
+ },
771
+ {
772
+ "epoch": 2.0,
773
+ "grad_norm": 2.9811086654663086,
774
+ "learning_rate": 2.105263157894737e-06,
775
+ "loss": 0.3701,
776
+ "mean_token_accuracy": 0.8978873491287231,
777
+ "step": 96
778
+ },
779
+ {
780
+ "epoch": 2.0211640211640214,
781
+ "grad_norm": 5.955318450927734,
782
+ "learning_rate": 1.5789473684210528e-06,
783
+ "loss": 2.499,
784
+ "mean_token_accuracy": 0.8697298467159271,
785
+ "step": 97
786
+ },
787
+ {
788
+ "epoch": 2.0423280423280423,
789
+ "grad_norm": 5.380612373352051,
790
+ "learning_rate": 1.0526315789473685e-06,
791
+ "loss": 2.2655,
792
+ "mean_token_accuracy": 0.8864545077085495,
793
+ "step": 98
794
+ },
795
+ {
796
+ "epoch": 2.0634920634920633,
797
+ "grad_norm": 5.8451457023620605,
798
+ "learning_rate": 5.263157894736843e-07,
799
+ "loss": 1.9556,
800
+ "mean_token_accuracy": 0.8944731205701828,
801
+ "step": 99
802
+ },
803
+ {
804
+ "epoch": 2.0846560846560847,
805
+ "grad_norm": 6.115093231201172,
806
+ "learning_rate": 0.0,
807
+ "loss": 2.4345,
808
+ "mean_token_accuracy": 0.8695619106292725,
809
+ "step": 100
810
+ }
811
+ ],
812
+ "logging_steps": 1,
813
+ "max_steps": 100,
814
+ "num_input_tokens_seen": 0,
815
+ "num_train_epochs": 3,
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": 514181058527232.0,
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:bef2d3375a6f8cd68fd351a3be52bb4389ece3889ed6b1093534dbfad66b710d
3
+ size 5496
vocab.json ADDED
The diff for this file is too large to render. See raw diff