Hugging Face's logo

erikbeltran
/
ruby-autotab-v6

TensorBoard
Safetensors
llama
Model card Files
xet
Metrics Community
erikbeltran commited on
Commit
f56787c
·
verified ·
1 Parent(s): 502a937

Add checkpoint files

Browse files
Files changed (13) hide show
  1. config.json +29 -0
  2. generation_config.json +6 -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 +43 -0
  9. tokenizer.json +0 -0
  10. tokenizer_config.json +168 -0
  11. trainer_state.json +117 -0
  12. training_args.bin +3 -0
  13. vocab.json +0 -0
config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "HuggingFaceTB/SmolLM-135M",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 0,
9
+ "eos_token_id": 0,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 576,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 1536,
14
+ "max_position_embeddings": 2048,
15
+ "mlp_bias": false,
16
+ "model_type": "llama",
17
+ "num_attention_heads": 9,
18
+ "num_hidden_layers": 30,
19
+ "num_key_value_heads": 3,
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": "float32",
26
+ "transformers_version": "4.44.0",
27
+ "use_cache": true,
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": "4.44.0"
6
+ }
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:e60fc029fca287f98b13a92add90db482bc0b3d33800f43ee06351fad56818dd
3
+ size 538090408
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8456b3432c61b4d50e5ceb237c24c644c82a9d4514197f00c0b2c16cb0b99731
3
+ size 1076349050
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:36eb3c91b3077080e254ba8fd9a96b4afe9cf22aec04441fdc41ff8bc2a91d56
3
+ size 14244
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e6b2bf387cff0354f25938319b7416a8cb41b0b587f9026478651206d16f618a
3
+ size 1064
special_tokens_map.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "<|endoftext|>",
36
+ "unk_token": {
37
+ "content": "<|endoftext|>",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false
42
+ }
43
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,168 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "model_max_length": 1000000000000000019884624838656,
164
+ "pad_token": "<|endoftext|>",
165
+ "tokenizer_class": "GPT2Tokenizer",
166
+ "unk_token": "<|endoftext|>",
167
+ "vocab_size": 49152
168
+ }
trainer_state.json ADDED
@@ -0,0 +1,117 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 8.0,
5
+ "eval_steps": 500,
6
+ "global_step": 6424,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.6226650062266501,
13
+ "grad_norm": 2.0943491458892822,
14
+ "learning_rate": 0.00019886329318816558,
15
+ "loss": 1.2905,
16
+ "step": 500
17
+ },
18
+ {
19
+ "epoch": 1.2453300124533002,
20
+ "grad_norm": 1.3522595167160034,
21
+ "learning_rate": 0.00019197713211971837,
22
+ "loss": 0.9564,
23
+ "step": 1000
24
+ },
25
+ {
26
+ "epoch": 1.86799501867995,
27
+ "grad_norm": 1.6422098875045776,
28
+ "learning_rate": 0.00017926358149064194,
29
+ "loss": 0.8082,
30
+ "step": 1500
31
+ },
32
+ {
33
+ "epoch": 2.4906600249066004,
34
+ "grad_norm": 1.4689579010009766,
35
+ "learning_rate": 0.00016152813295420922,
36
+ "loss": 0.6228,
37
+ "step": 2000
38
+ },
39
+ {
40
+ "epoch": 3.1133250311332503,
41
+ "grad_norm": 2.0464258193969727,
42
+ "learning_rate": 0.000139894450243703,
43
+ "loss": 0.5506,
44
+ "step": 2500
45
+ },
46
+ {
47
+ "epoch": 3.7359900373599,
48
+ "grad_norm": 1.3183234930038452,
49
+ "learning_rate": 0.0001157331772776689,
50
+ "loss": 0.3943,
51
+ "step": 3000
52
+ },
53
+ {
54
+ "epoch": 4.35865504358655,
55
+ "grad_norm": 1.1212505102157593,
56
+ "learning_rate": 9.057509835660592e-05,
57
+ "loss": 0.3245,
58
+ "step": 3500
59
+ },
60
+ {
61
+ "epoch": 4.981320049813201,
62
+ "grad_norm": 1.7740994691848755,
63
+ "learning_rate": 6.601415235522544e-05,
64
+ "loss": 0.2671,
65
+ "step": 4000
66
+ },
67
+ {
68
+ "epoch": 5.603985056039851,
69
+ "grad_norm": 1.0328716039657593,
70
+ "learning_rate": 4.360644563419686e-05,
71
+ "loss": 0.192,
72
+ "step": 4500
73
+ },
74
+ {
75
+ "epoch": 6.226650062266501,
76
+ "grad_norm": 0.7897807955741882,
77
+ "learning_rate": 2.4771661904182066e-05,
78
+ "loss": 0.1778,
79
+ "step": 5000
80
+ },
81
+ {
82
+ "epoch": 6.8493150684931505,
83
+ "grad_norm": 0.8206276297569275,
84
+ "learning_rate": 1.0703115411401943e-05,
85
+ "loss": 0.1591,
86
+ "step": 5500
87
+ },
88
+ {
89
+ "epoch": 7.4719800747198,
90
+ "grad_norm": 0.5427886843681335,
91
+ "learning_rate": 2.292146199581047e-06,
92
+ "loss": 0.1427,
93
+ "step": 6000
94
+ }
95
+ ],
96
+ "logging_steps": 500,
97
+ "max_steps": 6424,
98
+ "num_input_tokens_seen": 0,
99
+ "num_train_epochs": 8,
100
+ "save_steps": 500,
101
+ "stateful_callbacks": {
102
+ "TrainerControl": {
103
+ "args": {
104
+ "should_epoch_stop": false,
105
+ "should_evaluate": false,
106
+ "should_log": false,
107
+ "should_save": true,
108
+ "should_training_stop": true
109
+ },
110
+ "attributes": {}
111
+ }
112
+ },
113
+ "total_flos": 4739003604203904.0,
114
+ "train_batch_size": 8,
115
+ "trial_name": null,
116
+ "trial_params": null
117
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:129ba933e8ae3645669037fba183ba605aeb7726ed8a5b9c934841638b01fc4d
3
+ size 5496
vocab.json ADDED
The diff for this file is too large to render. See raw diff