Hugging Face's logo

nlpguy
/
amdchess

Text Generation
Transformers
Safetensors
llama
Generated from Trainer
text-generation-inference
Model card Files
xet
Community
nlpguy commited on
Commit
6075130
·
verified ·
1 Parent(s): 27e9374

End of training

Browse files
Files changed (9) hide show
  1. README.md +141 -0
  2. config.json +29 -0
  3. generation_config.json +6 -0
  4. model.safetensors +3 -0
  5. special_tokens_map.json +24 -0
  6. tokenizer.json +0 -0
  7. tokenizer.model +3 -0
  8. tokenizer_config.json +42 -0
  9. training_args.bin +3 -0
README.md ADDED
@@ -0,0 +1,141 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: apache-2.0
4
+ base_model: reflex-ai/AMD-Llama-350M-Upgraded
5
+ tags:
6
+ - generated_from_trainer
7
+ model-index:
8
+ - name: amdchess
9
+ results: []
10
+ ---
11
+
12
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
13
+ should probably proofread and complete it, then remove this comment. -->
14
+
15
+ # amdchess
16
+
17
+ This model is a fine-tuned version of [reflex-ai/AMD-Llama-350M-Upgraded](https://huggingface.co/reflex-ai/AMD-Llama-350M-Upgraded) on an unknown dataset.
18
+ It achieves the following results on the evaluation set:
19
+ - Loss: 1.6347
20
+
21
+ ## Model description
22
+
23
+ More information needed
24
+
25
+ ## Intended uses & limitations
26
+
27
+ More information needed
28
+
29
+ ## Training and evaluation data
30
+
31
+ More information needed
32
+
33
+ ## Training procedure
34
+
35
+ ### Training hyperparameters
36
+
37
+ The following hyperparameters were used during training:
38
+ - learning_rate: 3e-05
39
+ - train_batch_size: 4
40
+ - eval_batch_size: 4
41
+ - seed: 42
42
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
43
+ - lr_scheduler_type: cosine
44
+ - num_epochs: 0.1
45
+
46
+ ### Training results
47
+
48
+ | Training Loss | Epoch | Step | Validation Loss |
49
+ |:-------------:|:------:|:----:|:---------------:|
50
+ | 8.019 | 0.0012 | 4 | 7.6135 |
51
+ | 7.7094 | 0.0024 | 8 | 7.0826 |
52
+ | 6.8737 | 0.0035 | 12 | 6.8392 |
53
+ | 6.6426 | 0.0047 | 16 | 6.6142 |
54
+ | 6.3563 | 0.0059 | 20 | 6.2879 |
55
+ | 6.0826 | 0.0071 | 24 | 5.9688 |
56
+ | 5.8464 | 0.0083 | 28 | 5.5885 |
57
+ | 5.3209 | 0.0094 | 32 | 5.4342 |
58
+ | 5.2345 | 0.0106 | 36 | 5.2125 |
59
+ | 4.9003 | 0.0118 | 40 | 4.9282 |
60
+ | 4.6779 | 0.0130 | 44 | 4.7029 |
61
+ | 4.3778 | 0.0142 | 48 | 4.3920 |
62
+ | 4.3256 | 0.0154 | 52 | 4.1814 |
63
+ | 3.9975 | 0.0165 | 56 | 4.0072 |
64
+ | 3.73 | 0.0177 | 60 | 3.8358 |
65
+ | 4.0483 | 0.0189 | 64 | 3.7093 |
66
+ | 3.7907 | 0.0201 | 68 | 3.5874 |
67
+ | 3.3881 | 0.0213 | 72 | 3.4606 |
68
+ | 3.5066 | 0.0224 | 76 | 3.4071 |
69
+ | 3.3845 | 0.0236 | 80 | 3.2889 |
70
+ | 3.2318 | 0.0248 | 84 | 3.1932 |
71
+ | 3.5897 | 0.0260 | 88 | 3.1209 |
72
+ | 3.0362 | 0.0272 | 92 | 3.0123 |
73
+ | 2.7973 | 0.0283 | 96 | 2.9055 |
74
+ | 2.8976 | 0.0295 | 100 | 2.8210 |
75
+ | 2.8188 | 0.0307 | 104 | 2.7422 |
76
+ | 2.5149 | 0.0319 | 108 | 2.6395 |
77
+ | 2.495 | 0.0331 | 112 | 2.5714 |
78
+ | 2.5654 | 0.0342 | 116 | 2.4863 |
79
+ | 2.4205 | 0.0354 | 120 | 2.4448 |
80
+ | 2.3487 | 0.0366 | 124 | 2.3561 |
81
+ | 2.413 | 0.0378 | 128 | 2.3265 |
82
+ | 2.2713 | 0.0390 | 132 | 2.2814 |
83
+ | 2.2293 | 0.0402 | 136 | 2.2361 |
84
+ | 2.2793 | 0.0413 | 140 | 2.1745 |
85
+ | 2.185 | 0.0425 | 144 | 2.1444 |
86
+ | 2.0137 | 0.0437 | 148 | 2.1245 |
87
+ | 2.1408 | 0.0449 | 152 | 2.0849 |
88
+ | 2.1539 | 0.0461 | 156 | 2.0650 |
89
+ | 2.0592 | 0.0472 | 160 | 2.0345 |
90
+ | 1.9849 | 0.0484 | 164 | 2.0390 |
91
+ | 1.8796 | 0.0496 | 168 | 1.9978 |
92
+ | 1.9646 | 0.0508 | 172 | 1.9860 |
93
+ | 1.9913 | 0.0520 | 176 | 1.9388 |
94
+ | 1.967 | 0.0531 | 180 | 1.9121 |
95
+ | 1.9141 | 0.0543 | 184 | 1.9085 |
96
+ | 1.9513 | 0.0555 | 188 | 1.9040 |
97
+ | 1.9123 | 0.0567 | 192 | 1.8606 |
98
+ | 1.8204 | 0.0579 | 196 | 1.8556 |
99
+ | 1.9311 | 0.0590 | 200 | 1.8390 |
100
+ | 1.8425 | 0.0602 | 204 | 1.8162 |
101
+ | 1.7932 | 0.0614 | 208 | 1.7914 |
102
+ | 1.591 | 0.0626 | 212 | 1.7749 |
103
+ | 1.7899 | 0.0638 | 216 | 1.7667 |
104
+ | 1.7094 | 0.0650 | 220 | 1.7637 |
105
+ | 1.8023 | 0.0661 | 224 | 1.7458 |
106
+ | 1.7368 | 0.0673 | 228 | 1.7339 |
107
+ | 1.5679 | 0.0685 | 232 | 1.7281 |
108
+ | 1.7265 | 0.0697 | 236 | 1.7221 |
109
+ | 1.7034 | 0.0709 | 240 | 1.7093 |
110
+ | 1.5902 | 0.0720 | 244 | 1.7086 |
111
+ | 1.6903 | 0.0732 | 248 | 1.6976 |
112
+ | 1.7581 | 0.0744 | 252 | 1.6944 |
113
+ | 1.656 | 0.0756 | 256 | 1.6899 |
114
+ | 1.4287 | 0.0768 | 260 | 1.6858 |
115
+ | 1.6527 | 0.0779 | 264 | 1.6754 |
116
+ | 1.7206 | 0.0791 | 268 | 1.6787 |
117
+ | 1.8268 | 0.0803 | 272 | 1.6673 |
118
+ | 1.538 | 0.0815 | 276 | 1.6590 |
119
+ | 1.7374 | 0.0827 | 280 | 1.6711 |
120
+ | 1.7255 | 0.0839 | 284 | 1.6513 |
121
+ | 1.6032 | 0.0850 | 288 | 1.6552 |
122
+ | 1.5297 | 0.0862 | 292 | 1.6458 |
123
+ | 1.7639 | 0.0874 | 296 | 1.6488 |
124
+ | 1.8029 | 0.0886 | 300 | 1.6441 |
125
+ | 1.665 | 0.0898 | 304 | 1.6425 |
126
+ | 1.6854 | 0.0909 | 308 | 1.6425 |
127
+ | 1.5418 | 0.0921 | 312 | 1.6396 |
128
+ | 1.6943 | 0.0933 | 316 | 1.6373 |
129
+ | 1.6758 | 0.0945 | 320 | 1.6359 |
130
+ | 1.9994 | 0.0957 | 324 | 1.6352 |
131
+ | 1.6326 | 0.0968 | 328 | 1.6349 |
132
+ | 1.6935 | 0.0980 | 332 | 1.6348 |
133
+ | 1.6358 | 0.0992 | 336 | 1.6347 |
134
+
135
+
136
+ ### Framework versions
137
+
138
+ - Transformers 4.44.2
139
+ - Pytorch 2.5.0+cu121
140
+ - Datasets 3.0.2
141
+ - Tokenizers 0.19.1
config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "reflex-ai/AMD-Llama-350M-Upgraded",
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
+ "hidden_act": "silu",
11
+ "hidden_size": 768,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 4096,
14
+ "max_position_embeddings": 2048,
15
+ "mlp_bias": false,
16
+ "model_type": "llama",
17
+ "num_attention_heads": 12,
18
+ "num_hidden_layers": 24,
19
+ "num_key_value_heads": 12,
20
+ "pretraining_tp": 1,
21
+ "rms_norm_eps": 1e-05,
22
+ "rope_scaling": null,
23
+ "rope_theta": 10000.0,
24
+ "tie_word_embeddings": false,
25
+ "torch_dtype": "float32",
26
+ "transformers_version": "4.44.2",
27
+ "use_cache": true,
28
+ "vocab_size": 32000
29
+ }
generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "transformers_version": "4.44.2"
6
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:725dd4e1d0f61d69609f24e34ddbc6f03d12644d82c386856b5dfbfc0be4e93c
3
+ size 1329245144
special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<unk>",
17
+ "unk_token": {
18
+ "content": "<unk>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
tokenizer_config.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "add_prefix_space": null,
5
+ "added_tokens_decoder": {
6
+ "0": {
7
+ "content": "<unk>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false,
12
+ "special": true
13
+ },
14
+ "1": {
15
+ "content": "<s>",
16
+ "lstrip": false,
17
+ "normalized": false,
18
+ "rstrip": false,
19
+ "single_word": false,
20
+ "special": true
21
+ },
22
+ "2": {
23
+ "content": "</s>",
24
+ "lstrip": false,
25
+ "normalized": false,
26
+ "rstrip": false,
27
+ "single_word": false,
28
+ "special": true
29
+ }
30
+ },
31
+ "bos_token": "<s>",
32
+ "clean_up_tokenization_spaces": false,
33
+ "eos_token": "</s>",
34
+ "legacy": true,
35
+ "model_max_length": 1000000000000000019884624838656,
36
+ "pad_token": "<unk>",
37
+ "sp_model_kwargs": {},
38
+ "spaces_between_special_tokens": false,
39
+ "tokenizer_class": "LlamaTokenizer",
40
+ "unk_token": "<unk>",
41
+ "use_default_system_prompt": true
42
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49cbe6b908078fcd2b959f042facbf06a4d644b21aa3fcf82cd3117ca00346db
3
+ size 5176