Hugging Face's logo

nlpguy
/
amdchess-v4

Text Generation
Transformers
Safetensors
llama
Generated from Trainer
text-generation-inference
Inference Endpoints
Model card Files Community
nlpguy commited on
Commit
5875f7a
•
1 Parent(s): da8c9d5

End of training

Browse files
Files changed (9) hide show
  1. README.md +141 -0
  2. config.json +30 -0
  3. generation_config.json +7 -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: amd/AMD-Llama-135m
5
+ tags:
6
+ - generated_from_trainer
7
+ model-index:
8
+ - name: amdchess-v4
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-v4
16
+
17
+ This model is a fine-tuned version of [amd/AMD-Llama-135m](https://huggingface.co/amd/AMD-Llama-135m) on an unknown dataset.
18
+ It achieves the following results on the evaluation set:
19
+ - Loss: 0.7971
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: 8
40
+ - eval_batch_size: 8
41
+ - seed: 42
42
+ - optimizer: Use grokadamw with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
43
+ - lr_scheduler_type: cosine
44
+ - num_epochs: 0.25
45
+
46
+ ### Training results
47
+
48
+ | Training Loss | Epoch | Step | Validation Loss |
49
+ |:-------------:|:------:|:----:|:---------------:|
50
+ | 9.9629 | 0.0030 | 5 | 5.6096 |
51
+ | 3.7446 | 0.0059 | 10 | 3.3680 |
52
+ | 2.524 | 0.0089 | 15 | 2.3223 |
53
+ | 1.9286 | 0.0118 | 20 | 1.7446 |
54
+ | 1.5475 | 0.0148 | 25 | 2.0681 |
55
+ | 1.2838 | 0.0177 | 30 | 1.4096 |
56
+ | 1.3152 | 0.0207 | 35 | 1.2730 |
57
+ | 1.2488 | 0.0236 | 40 | 1.2203 |
58
+ | 1.088 | 0.0266 | 45 | 1.1461 |
59
+ | 1.0479 | 0.0295 | 50 | 1.1139 |
60
+ | 1.0758 | 0.0325 | 55 | 1.0844 |
61
+ | 1.1275 | 0.0354 | 60 | 1.0443 |
62
+ | 1.1378 | 0.0384 | 65 | 1.0260 |
63
+ | 1.0147 | 0.0413 | 70 | 0.9939 |
64
+ | 0.993 | 0.0443 | 75 | 1.0074 |
65
+ | 1.0132 | 0.0472 | 80 | 0.9866 |
66
+ | 0.9155 | 0.0502 | 85 | 0.9697 |
67
+ | 0.9656 | 0.0531 | 90 | 0.9757 |
68
+ | 1.0402 | 0.0561 | 95 | 0.9633 |
69
+ | 0.9759 | 0.0590 | 100 | 0.9528 |
70
+ | 0.9505 | 0.0620 | 105 | 0.9501 |
71
+ | 1.0114 | 0.0649 | 110 | 0.9405 |
72
+ | 1.0182 | 0.0679 | 115 | 0.9212 |
73
+ | 0.9396 | 0.0708 | 120 | 0.9284 |
74
+ | 0.902 | 0.0738 | 125 | 0.9262 |
75
+ | 0.9533 | 0.0767 | 130 | 0.9121 |
76
+ | 0.8755 | 0.0797 | 135 | 0.9160 |
77
+ | 0.9349 | 0.0826 | 140 | 0.9083 |
78
+ | 0.9585 | 0.0856 | 145 | 0.8993 |
79
+ | 0.8349 | 0.0885 | 150 | 0.9000 |
80
+ | 0.9541 | 0.0915 | 155 | 0.8887 |
81
+ | 0.9108 | 0.0945 | 160 | 0.8837 |
82
+ | 0.9196 | 0.0974 | 165 | 0.8806 |
83
+ | 0.9094 | 0.1004 | 170 | 0.8776 |
84
+ | 0.8514 | 0.1033 | 175 | 0.8759 |
85
+ | 0.7515 | 0.1063 | 180 | 0.8684 |
86
+ | 0.8031 | 0.1092 | 185 | 0.8676 |
87
+ | 0.8639 | 0.1122 | 190 | 0.8661 |
88
+ | 0.8002 | 0.1151 | 195 | 0.8556 |
89
+ | 0.7812 | 0.1181 | 200 | 0.8574 |
90
+ | 0.9163 | 0.1210 | 205 | 0.8582 |
91
+ | 0.8824 | 0.1240 | 210 | 0.8515 |
92
+ | 0.8759 | 0.1269 | 215 | 0.8502 |
93
+ | 0.8384 | 0.1299 | 220 | 0.8467 |
94
+ | 0.8436 | 0.1328 | 225 | 0.8427 |
95
+ | 0.8329 | 0.1358 | 230 | 0.8398 |
96
+ | 0.87 | 0.1387 | 235 | 0.8393 |
97
+ | 0.8405 | 0.1417 | 240 | 0.8356 |
98
+ | 0.8634 | 0.1446 | 245 | 0.8339 |
99
+ | 0.8298 | 0.1476 | 250 | 0.8315 |
100
+ | 0.7582 | 0.1505 | 255 | 0.8278 |
101
+ | 0.7912 | 0.1535 | 260 | 0.8257 |
102
+ | 0.8878 | 0.1564 | 265 | 0.8247 |
103
+ | 0.8443 | 0.1594 | 270 | 0.8229 |
104
+ | 0.8965 | 0.1623 | 275 | 0.8206 |
105
+ | 0.8298 | 0.1653 | 280 | 0.8178 |
106
+ | 0.7496 | 0.1682 | 285 | 0.8177 |
107
+ | 0.7794 | 0.1712 | 290 | 0.8148 |
108
+ | 0.8354 | 0.1741 | 295 | 0.8137 |
109
+ | 0.8861 | 0.1771 | 300 | 0.8124 |
110
+ | 0.7683 | 0.1800 | 305 | 0.8118 |
111
+ | 0.8414 | 0.1830 | 310 | 0.8106 |
112
+ | 0.8624 | 0.1860 | 315 | 0.8083 |
113
+ | 0.7753 | 0.1889 | 320 | 0.8076 |
114
+ | 0.778 | 0.1919 | 325 | 0.8060 |
115
+ | 0.8171 | 0.1948 | 330 | 0.8051 |
116
+ | 0.7006 | 0.1978 | 335 | 0.8049 |
117
+ | 0.8365 | 0.2007 | 340 | 0.8032 |
118
+ | 0.8057 | 0.2037 | 345 | 0.8021 |
119
+ | 0.7914 | 0.2066 | 350 | 0.8015 |
120
+ | 0.9043 | 0.2096 | 355 | 0.8008 |
121
+ | 0.8317 | 0.2125 | 360 | 0.8001 |
122
+ | 0.7631 | 0.2155 | 365 | 0.7997 |
123
+ | 0.8301 | 0.2184 | 370 | 0.7993 |
124
+ | 0.8701 | 0.2214 | 375 | 0.7988 |
125
+ | 0.7469 | 0.2243 | 380 | 0.7985 |
126
+ | 0.7643 | 0.2273 | 385 | 0.7981 |
127
+ | 0.8388 | 0.2302 | 390 | 0.7978 |
128
+ | 0.8808 | 0.2332 | 395 | 0.7975 |
129
+ | 0.7441 | 0.2361 | 400 | 0.7974 |
130
+ | 0.7641 | 0.2391 | 405 | 0.7972 |
131
+ | 0.727 | 0.2420 | 410 | 0.7971 |
132
+ | 0.771 | 0.2450 | 415 | 0.7971 |
133
+ | 0.7442 | 0.2479 | 420 | 0.7971 |
134
+
135
+
136
+ ### Framework versions
137
+
138
+ - Transformers 4.46.0
139
+ - Pytorch 2.5.0+cu121
140
+ - Datasets 3.0.2
141
+ - Tokenizers 0.20.1
config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "amd/AMD-Llama-135m",
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": 768,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 2048,
15
+ "max_position_embeddings": 2048,
16
+ "mlp_bias": false,
17
+ "model_type": "llama",
18
+ "num_attention_heads": 12,
19
+ "num_hidden_layers": 12,
20
+ "num_key_value_heads": 12,
21
+ "pretraining_tp": 1,
22
+ "rms_norm_eps": 1e-05,
23
+ "rope_scaling": null,
24
+ "rope_theta": 10000.0,
25
+ "tie_word_embeddings": false,
26
+ "torch_dtype": "float32",
27
+ "transformers_version": "4.46.0",
28
+ "use_cache": true,
29
+ "vocab_size": 32000
30
+ }
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": 0,
6
+ "transformers_version": "4.46.0"
7
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ace4d12e9ae311bb91b4c9ae5c3f250e68c23e78a226ef6678c20c388057dcf
3
+ size 536435744
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:e58af97b73d01bc4de1f031a04de30eeefaec61b95d9f2b6cbc179b21873d5bd
3
+ size 5240