Hugging Face's logo

nlpguy
/
amdchess-v2

Text Generation
Transformers
Safetensors
llama
Generated from Trainer
text-generation-inference
Inference Endpoints
Model card Files Community
nlpguy commited on
Commit
8f057a7
·
verified ·
1 Parent(s): 31c40dd

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-v2
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-v2
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: 1.7890
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: 2e-05
39
+ - train_batch_size: 8
40
+ - eval_batch_size: 8
41
+ - seed: 42
42
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
43
+ - lr_scheduler_type: cosine
44
+ - num_epochs: 0.25
45
+
46
+ ### Training results
47
+
48
+ | Training Loss | Epoch | Step | Validation Loss |
49
+ |:-------------:|:------:|:----:|:---------------:|
50
+ | 7.881 | 0.0030 | 5 | 7.5739 |
51
+ | 7.2662 | 0.0059 | 10 | 7.0051 |
52
+ | 6.8098 | 0.0089 | 15 | 6.7687 |
53
+ | 6.5801 | 0.0118 | 20 | 6.4508 |
54
+ | 6.0821 | 0.0148 | 25 | 6.0083 |
55
+ | 5.676 | 0.0177 | 30 | 5.6640 |
56
+ | 5.3014 | 0.0207 | 35 | 5.3851 |
57
+ | 5.1438 | 0.0236 | 40 | 5.0677 |
58
+ | 4.81 | 0.0266 | 45 | 4.8327 |
59
+ | 4.6369 | 0.0295 | 50 | 4.6192 |
60
+ | 4.5722 | 0.0325 | 55 | 4.3942 |
61
+ | 4.2333 | 0.0354 | 60 | 4.2079 |
62
+ | 4.1333 | 0.0384 | 65 | 4.0590 |
63
+ | 3.9003 | 0.0413 | 70 | 3.9275 |
64
+ | 3.7871 | 0.0443 | 75 | 3.8163 |
65
+ | 3.7472 | 0.0472 | 80 | 3.7052 |
66
+ | 3.5998 | 0.0502 | 85 | 3.6333 |
67
+ | 3.5839 | 0.0531 | 90 | 3.5451 |
68
+ | 3.4021 | 0.0561 | 95 | 3.4627 |
69
+ | 3.5244 | 0.0590 | 100 | 3.3776 |
70
+ | 3.3366 | 0.0620 | 105 | 3.2479 |
71
+ | 3.132 | 0.0649 | 110 | 3.1422 |
72
+ | 3.1709 | 0.0679 | 115 | 3.0535 |
73
+ | 3.0326 | 0.0708 | 120 | 2.9746 |
74
+ | 2.9901 | 0.0738 | 125 | 2.8892 |
75
+ | 2.7284 | 0.0767 | 130 | 2.8250 |
76
+ | 2.7125 | 0.0797 | 135 | 2.7152 |
77
+ | 2.7271 | 0.0826 | 140 | 2.6612 |
78
+ | 2.568 | 0.0856 | 145 | 2.5891 |
79
+ | 2.5652 | 0.0885 | 150 | 2.5402 |
80
+ | 2.5192 | 0.0915 | 155 | 2.4705 |
81
+ | 2.5085 | 0.0945 | 160 | 2.4344 |
82
+ | 2.4132 | 0.0974 | 165 | 2.4072 |
83
+ | 2.4028 | 0.1004 | 170 | 2.3522 |
84
+ | 2.2912 | 0.1033 | 175 | 2.3617 |
85
+ | 2.3289 | 0.1063 | 180 | 2.3058 |
86
+ | 2.2414 | 0.1092 | 185 | 2.2653 |
87
+ | 2.3884 | 0.1122 | 190 | 2.2534 |
88
+ | 2.2284 | 0.1151 | 195 | 2.2314 |
89
+ | 2.312 | 0.1181 | 200 | 2.1855 |
90
+ | 2.2398 | 0.1210 | 205 | 2.1578 |
91
+ | 2.0852 | 0.1240 | 210 | 2.1418 |
92
+ | 2.0324 | 0.1269 | 215 | 2.1151 |
93
+ | 2.1423 | 0.1299 | 220 | 2.1034 |
94
+ | 2.1088 | 0.1328 | 225 | 2.0716 |
95
+ | 2.1024 | 0.1358 | 230 | 2.0702 |
96
+ | 1.979 | 0.1387 | 235 | 2.0425 |
97
+ | 1.9784 | 0.1417 | 240 | 2.0265 |
98
+ | 2.0505 | 0.1446 | 245 | 2.0018 |
99
+ | 2.0258 | 0.1476 | 250 | 1.9822 |
100
+ | 1.9377 | 0.1505 | 255 | 1.9653 |
101
+ | 2.0453 | 0.1535 | 260 | 1.9555 |
102
+ | 1.9542 | 0.1564 | 265 | 1.9502 |
103
+ | 1.9549 | 0.1594 | 270 | 1.9284 |
104
+ | 1.9209 | 0.1623 | 275 | 1.9187 |
105
+ | 1.9262 | 0.1653 | 280 | 1.9016 |
106
+ | 1.9373 | 0.1682 | 285 | 1.8991 |
107
+ | 2.0095 | 0.1712 | 290 | 1.8975 |
108
+ | 1.9144 | 0.1741 | 295 | 1.8801 |
109
+ | 1.888 | 0.1771 | 300 | 1.8833 |
110
+ | 1.963 | 0.1800 | 305 | 1.8753 |
111
+ | 1.8349 | 0.1830 | 310 | 1.8722 |
112
+ | 1.872 | 0.1860 | 315 | 1.8508 |
113
+ | 1.7128 | 0.1889 | 320 | 1.8443 |
114
+ | 1.8132 | 0.1919 | 325 | 1.8342 |
115
+ | 1.842 | 0.1948 | 330 | 1.8299 |
116
+ | 1.8079 | 0.1978 | 335 | 1.8220 |
117
+ | 1.7931 | 0.2007 | 340 | 1.8203 |
118
+ | 2.028 | 0.2037 | 345 | 1.8179 |
119
+ | 1.7255 | 0.2066 | 350 | 1.8124 |
120
+ | 1.8479 | 0.2096 | 355 | 1.8061 |
121
+ | 1.7466 | 0.2125 | 360 | 1.8032 |
122
+ | 1.7946 | 0.2155 | 365 | 1.8021 |
123
+ | 1.8123 | 0.2184 | 370 | 1.7984 |
124
+ | 1.94 | 0.2214 | 375 | 1.7968 |
125
+ | 1.7952 | 0.2243 | 380 | 1.7943 |
126
+ | 1.7571 | 0.2273 | 385 | 1.7943 |
127
+ | 1.7723 | 0.2302 | 390 | 1.7927 |
128
+ | 1.7123 | 0.2332 | 395 | 1.7954 |
129
+ | 1.7593 | 0.2361 | 400 | 1.7911 |
130
+ | 1.9268 | 0.2391 | 405 | 1.7895 |
131
+ | 1.8277 | 0.2420 | 410 | 1.7892 |
132
+ | 1.777 | 0.2450 | 415 | 1.7890 |
133
+ | 1.721 | 0.2479 | 420 | 1.7890 |
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 sha256:842ca307b1c0cffce34a8c9d98d7aae0b6beb4f9026d7e6500fd3a3258b5569a
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:c5dd3fc94e36d6f0df1dff8843983730f5f41736e75a98ca603e3d8ab001bc06
3
+ size 5176