tonyshark commited on
Commit
aaaf00f
·
verified ·
1 Parent(s): a84f2b9

Training in progress, epoch 1

Browse files
config.json CHANGED
@@ -1,14 +1,14 @@
1
  {
2
- "_name_or_path": "DeepSeek-V3-1B-Test",
3
  "architectures": [
4
  "DeepseekV3ForCausalLM"
5
  ],
6
  "attention_bias": false,
7
  "attention_dropout": 0.0,
8
  "auto_map": {
9
- "AutoConfig": "configuration_deepseek.DeepseekV3Config",
10
- "AutoModel": "modeling_deepseek.DeepseekV3Model",
11
- "AutoModelForCausalLM": "modeling_deepseek.DeepseekV3ForCausalLM"
12
  },
13
  "aux_loss_alpha": 0.001,
14
  "bos_token_id": 0,
@@ -54,8 +54,8 @@
54
  "tie_word_embeddings": false,
55
  "topk_group": 4,
56
  "topk_method": "noaux_tc",
57
- "torch_dtype": "bfloat16",
58
- "transformers_version": "4.47.1",
59
  "use_cache": true,
60
  "v_head_dim": 128,
61
  "vocab_size": 129280
 
1
  {
2
+ "_name_or_path": "tonyshark/deepseek-v3-1b",
3
  "architectures": [
4
  "DeepseekV3ForCausalLM"
5
  ],
6
  "attention_bias": false,
7
  "attention_dropout": 0.0,
8
  "auto_map": {
9
+ "AutoConfig": "tonyshark/deepseek-v3-1b--configuration_deepseek.DeepseekV3Config",
10
+ "AutoModel": "tonyshark/deepseek-v3-1b--modeling_deepseek.DeepseekV3Model",
11
+ "AutoModelForCausalLM": "tonyshark/deepseek-v3-1b--modeling_deepseek.DeepseekV3ForCausalLM"
12
  },
13
  "aux_loss_alpha": 0.001,
14
  "bos_token_id": 0,
 
54
  "tie_word_embeddings": false,
55
  "topk_group": 4,
56
  "topk_method": "noaux_tc",
57
+ "torch_dtype": "float32",
58
+ "transformers_version": "4.46.1",
59
  "use_cache": true,
60
  "v_head_dim": 128,
61
  "vocab_size": 129280
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a9db5309afa023828200507bbe04d1aaff8667510b47b24ac999f340876da1ee
3
- size 2099235336
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e4d0893b4a6f7ad8282fe4255f087a31b6c0b1f6d95b956cb1d85a85e11fa7e3
3
+ size 4198331024
runs/Jan13_01-01-54_46046415ec16/events.out.tfevents.1736730115.46046415ec16.261.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:906a12664fe166fc82b3a97f8ae7993546d54364ee2ab0b60419d4bdc75d9b7b
3
+ size 6719
tokenizer.json CHANGED
@@ -1,7 +1,19 @@
1
  {
2
  "version": "1.0",
3
- "truncation": null,
4
- "padding": null,
 
 
 
 
 
 
 
 
 
 
 
 
5
  "added_tokens": [
6
  {
7
  "id": 0,
@@ -7419,6 +7431,12 @@
7419
  "id": "A",
7420
  "type_id": 0
7421
  }
 
 
 
 
 
 
7422
  }
7423
  ],
7424
  "pair": [
@@ -7434,6 +7452,12 @@
7434
  "type_id": 0
7435
  }
7436
  },
 
 
 
 
 
 
7437
  {
7438
  "SpecialToken": {
7439
  "id": "<|begin▁of▁sentence|>",
@@ -7445,6 +7469,12 @@
7445
  "id": "B",
7446
  "type_id": 1
7447
  }
 
 
 
 
 
 
7448
  }
7449
  ],
7450
  "special_tokens": {
@@ -7456,6 +7486,15 @@
7456
  "tokens": [
7457
  "<|begin▁of▁sentence|>"
7458
  ]
 
 
 
 
 
 
 
 
 
7459
  }
7460
  }
7461
  },
 
1
  {
2
  "version": "1.0",
3
+ "truncation": {
4
+ "direction": "Right",
5
+ "max_length": 128,
6
+ "strategy": "LongestFirst",
7
+ "stride": 0
8
+ },
9
+ "padding": {
10
+ "strategy": "BatchLongest",
11
+ "direction": "Left",
12
+ "pad_to_multiple_of": null,
13
+ "pad_id": 1,
14
+ "pad_type_id": 0,
15
+ "pad_token": "<|end▁of▁sentence|>"
16
+ },
17
  "added_tokens": [
18
  {
19
  "id": 0,
 
7431
  "id": "A",
7432
  "type_id": 0
7433
  }
7434
+ },
7435
+ {
7436
+ "SpecialToken": {
7437
+ "id": "<|end▁of▁sentence|>",
7438
+ "type_id": 0
7439
+ }
7440
  }
7441
  ],
7442
  "pair": [
 
7452
  "type_id": 0
7453
  }
7454
  },
7455
+ {
7456
+ "SpecialToken": {
7457
+ "id": "<|end▁of▁sentence|>",
7458
+ "type_id": 0
7459
+ }
7460
+ },
7461
  {
7462
  "SpecialToken": {
7463
  "id": "<|begin▁of▁sentence|>",
 
7469
  "id": "B",
7470
  "type_id": 1
7471
  }
7472
+ },
7473
+ {
7474
+ "SpecialToken": {
7475
+ "id": "<|end▁of▁sentence|>",
7476
+ "type_id": 1
7477
+ }
7478
  }
7479
  ],
7480
  "special_tokens": {
 
7486
  "tokens": [
7487
  "<|begin▁of▁sentence|>"
7488
  ]
7489
+ },
7490
+ "<|end▁of▁sentence|>": {
7491
+ "id": "<|end▁of▁sentence|>",
7492
+ "ids": [
7493
+ 1
7494
+ ],
7495
+ "tokens": [
7496
+ "<|end▁of▁sentence|>"
7497
+ ]
7498
  }
7499
  }
7500
  },
tokenizer_config.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
  "add_bos_token": true,
3
- "add_eos_token": false,
4
  "add_prefix_space": null,
5
  "added_tokens_decoder": {
6
  "0": {
 
1
  {
2
  "add_bos_token": true,
3
+ "add_eos_token": true,
4
  "add_prefix_space": null,
5
  "added_tokens_decoder": {
6
  "0": {
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:64839e50b7edf20ea18785ae47789266b16e874589534193bc54617cdebab4c4
3
+ size 5560