Hugging Face's logo

Masnuy
/
instruct-tst

Safetensors
llama
Model card Files
xet
 Community
Masnuy commited on
Commit
7ec7204
·
verified ·
1 Parent(s): d6677ba

Upload task output fa30d435-3229-4c56-871d-51ad38cfbe7a

Browse files
Files changed (11) hide show
  1. config.json +29 -0
  2. generation_config.json +6 -0
  3. loss.txt +1 -0
  4. merges.txt +0 -0
  5. model.safetensors +3 -0
  6. special_tokens_map.json +49 -0
  7. tokenizer.json +0 -0
  8. tokenizer_config.json +170 -0
  9. trainer_state.json +191 -0
  10. training_args.bin +3 -0
  11. vocab.json +0 -0
config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "LlamaForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 0,
8
+ "eos_token_id": 0,
9
+ "head_dim": 64,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 2048,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 8192,
14
+ "max_position_embeddings": 2048,
15
+ "mlp_bias": false,
16
+ "model_type": "llama",
17
+ "num_attention_heads": 32,
18
+ "num_hidden_layers": 24,
19
+ "num_key_value_heads": 32,
20
+ "pretraining_tp": 1,
21
+ "rms_norm_eps": 1e-05,
22
+ "rope_scaling": null,
23
+ "rope_theta": 10000.0,
24
+ "tie_word_embeddings": true,
25
+ "torch_dtype": "bfloat16",
26
+ "transformers_version": "4.51.3",
27
+ "use_cache": false,
28
+ "vocab_size": 49152
29
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "eos_token_id": 0,
5
+ "transformers_version": "4.51.3"
6
+ }
loss.txt ADDED
@@ -0,0 +1 @@
 
 
1
+ 98,0.8295379281044006
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:ff3c48ddbd1b6560930818c009c824ab080d650ffade8b161890dfe739d2fd92
3
+ size 3422777952
special_tokens_map.json ADDED
@@ -0,0 +1,49 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|endoftext|>",
4
+ "<|im_start|>",
5
+ "<|im_end|>",
6
+ "<repo_name>",
7
+ "<reponame>",
8
+ "<file_sep>",
9
+ "<filename>",
10
+ "<gh_stars>",
11
+ "<issue_start>",
12
+ "<issue_comment>",
13
+ "<issue_closed>",
14
+ "<jupyter_start>",
15
+ "<jupyter_text>",
16
+ "<jupyter_code>",
17
+ "<jupyter_output>",
18
+ "<jupyter_script>",
19
+ "<empty_output>"
20
+ ],
21
+ "bos_token": {
22
+ "content": "<|endoftext|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false
27
+ },
28
+ "eos_token": {
29
+ "content": "<|endoftext|>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false
34
+ },
35
+ "pad_token": {
36
+ "content": "<empty_output>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false
41
+ },
42
+ "unk_token": {
43
+ "content": "<|endoftext|>",
44
+ "lstrip": false,
45
+ "normalized": false,
46
+ "rstrip": false,
47
+ "single_word": false
48
+ }
49
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,170 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "<|endoftext|>",
143
+ "<|im_start|>",
144
+ "<|im_end|>",
145
+ "<repo_name>",
146
+ "<reponame>",
147
+ "<file_sep>",
148
+ "<filename>",
149
+ "<gh_stars>",
150
+ "<issue_start>",
151
+ "<issue_comment>",
152
+ "<issue_closed>",
153
+ "<jupyter_start>",
154
+ "<jupyter_text>",
155
+ "<jupyter_code>",
156
+ "<jupyter_output>",
157
+ "<jupyter_script>",
158
+ "<empty_output>"
159
+ ],
160
+ "bos_token": "<|endoftext|>",
161
+ "clean_up_tokenization_spaces": false,
162
+ "eos_token": "<|endoftext|>",
163
+ "extra_special_tokens": {},
164
+ "model_max_length": 1000000000000000019884624838656,
165
+ "pad_token": "<empty_output>",
166
+ "padding_side": "left",
167
+ "tokenizer_class": "GPT2Tokenizer",
168
+ "unk_token": "<|endoftext|>",
169
+ "vocab_size": 49152
170
+ }
trainer_state.json ADDED
@@ -0,0 +1,191 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 98,
3
+ "best_metric": 0.8295379281044006,
4
+ "best_model_checkpoint": "/workspace/scripts/soutputs/fa30d435-3229-4c56-871d-51ad38cfbe7a_7/checkpoint-98",
5
+ "epoch": 2.0,
6
+ "eval_steps": 500,
7
+ "global_step": 98,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.10204081632653061,
14
+ "grad_norm": 0.74609375,
15
+ "learning_rate": 0.0005517817935364519,
16
+ "loss": 1.267,
17
+ "step": 5
18
+ },
19
+ {
20
+ "epoch": 0.20408163265306123,
21
+ "grad_norm": 0.43359375,
22
+ "learning_rate": 0.0006868981122853327,
23
+ "loss": 1.133,
24
+ "step": 10
25
+ },
26
+ {
27
+ "epoch": 0.30612244897959184,
28
+ "grad_norm": 0.3515625,
29
+ "learning_rate": 0.0006754931100325356,
30
+ "loss": 1.0545,
31
+ "step": 15
32
+ },
33
+ {
34
+ "epoch": 0.40816326530612246,
35
+ "grad_norm": 0.29296875,
36
+ "learning_rate": 0.0006556597531537671,
37
+ "loss": 0.9658,
38
+ "step": 20
39
+ },
40
+ {
41
+ "epoch": 0.5102040816326531,
42
+ "grad_norm": 0.25390625,
43
+ "learning_rate": 0.0006279625071049859,
44
+ "loss": 0.9251,
45
+ "step": 25
46
+ },
47
+ {
48
+ "epoch": 0.6122448979591837,
49
+ "grad_norm": 0.23046875,
50
+ "learning_rate": 0.0005931896468471727,
51
+ "loss": 0.9068,
52
+ "step": 30
53
+ },
54
+ {
55
+ "epoch": 0.7142857142857143,
56
+ "grad_norm": 0.2734375,
57
+ "learning_rate": 0.0005523308222182446,
58
+ "loss": 0.8653,
59
+ "step": 35
60
+ },
61
+ {
62
+ "epoch": 0.8163265306122449,
63
+ "grad_norm": 0.259765625,
64
+ "learning_rate": 0.0005065488920935338,
65
+ "loss": 0.8615,
66
+ "step": 40
67
+ },
68
+ {
69
+ "epoch": 0.9183673469387755,
70
+ "grad_norm": 0.2255859375,
71
+ "learning_rate": 0.00045714682894615636,
72
+ "loss": 0.8336,
73
+ "step": 45
74
+ },
75
+ {
76
+ "epoch": 1.0,
77
+ "eval_loss": 0.8490258455276489,
78
+ "eval_runtime": 7.2501,
79
+ "eval_samples_per_second": 27.448,
80
+ "eval_steps_per_second": 27.448,
81
+ "step": 49
82
+ },
83
+ {
84
+ "epoch": 1.0,
85
+ "eval_loss": 0.8490258455276489,
86
+ "eval_runtime": 7.2144,
87
+ "eval_samples_per_second": 27.584,
88
+ "eval_steps_per_second": 27.584,
89
+ "step": 49
90
+ },
91
+ {
92
+ "epoch": 1.0204081632653061,
93
+ "grad_norm": 0.51171875,
94
+ "learning_rate": 0.0004055306357170286,
95
+ "loss": 0.7853,
96
+ "step": 50
97
+ },
98
+ {
99
+ "epoch": 1.1224489795918366,
100
+ "grad_norm": 0.271484375,
101
+ "learning_rate": 0.00035316933039559285,
102
+ "loss": 0.5521,
103
+ "step": 55
104
+ },
105
+ {
106
+ "epoch": 1.2244897959183674,
107
+ "grad_norm": 0.265625,
108
+ "learning_rate": 0.00030155313716646496,
109
+ "loss": 0.5756,
110
+ "step": 60
111
+ },
112
+ {
113
+ "epoch": 1.3265306122448979,
114
+ "grad_norm": 0.26953125,
115
+ "learning_rate": 0.00025215107401908756,
116
+ "loss": 0.5582,
117
+ "step": 65
118
+ },
119
+ {
120
+ "epoch": 1.4285714285714286,
121
+ "grad_norm": 0.224609375,
122
+ "learning_rate": 0.00020636914389437675,
123
+ "loss": 0.5496,
124
+ "step": 70
125
+ },
126
+ {
127
+ "epoch": 1.5306122448979593,
128
+ "grad_norm": 0.2275390625,
129
+ "learning_rate": 0.0001655103192654486,
130
+ "loss": 0.5427,
131
+ "step": 75
132
+ },
133
+ {
134
+ "epoch": 1.6326530612244898,
135
+ "grad_norm": 0.267578125,
136
+ "learning_rate": 0.00013073745900763563,
137
+ "loss": 0.5402,
138
+ "step": 80
139
+ },
140
+ {
141
+ "epoch": 1.7346938775510203,
142
+ "grad_norm": 0.19140625,
143
+ "learning_rate": 0.00010304021295885433,
144
+ "loss": 0.5118,
145
+ "step": 85
146
+ },
147
+ {
148
+ "epoch": 1.836734693877551,
149
+ "grad_norm": 0.251953125,
150
+ "learning_rate": 8.320685608008573e-05,
151
+ "loss": 0.5408,
152
+ "step": 90
153
+ },
154
+ {
155
+ "epoch": 1.9387755102040818,
156
+ "grad_norm": 0.234375,
157
+ "learning_rate": 7.18018538272886e-05,
158
+ "loss": 0.5387,
159
+ "step": 95
160
+ },
161
+ {
162
+ "epoch": 2.0,
163
+ "eval_loss": 0.8295379281044006,
164
+ "eval_runtime": 7.3772,
165
+ "eval_samples_per_second": 26.975,
166
+ "eval_steps_per_second": 26.975,
167
+ "step": 98
168
+ }
169
+ ],
170
+ "logging_steps": 5,
171
+ "max_steps": 98,
172
+ "num_input_tokens_seen": 0,
173
+ "num_train_epochs": 2,
174
+ "save_steps": 500,
175
+ "stateful_callbacks": {
176
+ "TrainerControl": {
177
+ "args": {
178
+ "should_epoch_stop": false,
179
+ "should_evaluate": false,
180
+ "should_log": false,
181
+ "should_save": true,
182
+ "should_training_stop": true
183
+ },
184
+ "attributes": {}
185
+ }
186
+ },
187
+ "total_flos": 1.939659357683712e+17,
188
+ "train_batch_size": 100,
189
+ "trial_name": null,
190
+ "trial_params": null
191
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:805f16c2118d379d4d56a888bd615b163e204a82d0dc855f685664e3dd4607c5
3
+ size 5688
vocab.json ADDED
The diff for this file is too large to render. See raw diff