ardanila commited on
Commit
0168876
·
1 Parent(s): b89ad69

Training in progress, step 1500

Browse files
Files changed (2) hide show
  1. config.json +23 -67
  2. training_args.bin +2 -2
config.json CHANGED
@@ -1,75 +1,31 @@
1
  {
2
- "_name_or_path": "EleutherAI/gpt-neo-1.3B",
3
- "activation_function": "gelu_new",
4
  "architectures": [
5
- "GPTNeoForCausalLM"
6
  ],
7
- "attention_dropout": 0,
8
- "attention_layers": [
9
- "global",
10
- "local",
11
- "global",
12
- "local",
13
- "global",
14
- "local",
15
- "global",
16
- "local",
17
- "global",
18
- "local",
19
- "global",
20
- "local",
21
- "global",
22
- "local",
23
- "global",
24
- "local",
25
- "global",
26
- "local",
27
- "global",
28
- "local",
29
- "global",
30
- "local",
31
- "global",
32
- "local"
33
- ],
34
- "attention_types": [
35
- [
36
- [
37
- "global",
38
- "local"
39
- ],
40
- 12
41
- ]
42
- ],
43
- "bos_token_id": 50256,
44
- "classifier_dropout": 0.1,
45
- "embed_dropout": 0,
46
- "eos_token_id": 50256,
47
- "gradient_checkpointing": false,
48
- "hidden_size": 2048,
49
- "initializer_range": 0.02,
50
- "intermediate_size": null,
51
- "layer_norm_epsilon": 1e-05,
52
- "max_position_embeddings": 2048,
53
- "model_type": "gpt_neo",
54
- "num_heads": 16,
55
- "num_layers": 24,
56
- "resid_dropout": 0,
57
- "summary_activation": null,
58
- "summary_first_dropout": 0.1,
59
- "summary_proj_to_labels": true,
60
- "summary_type": "cls_index",
61
- "summary_use_proj": true,
62
- "task_specific_params": {
63
- "text-generation": {
64
- "do_sample": true,
65
- "max_length": 50,
66
- "temperature": 0.9
67
- }
68
  },
69
- "tokenizer_class": "GPT2Tokenizer",
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
70
  "torch_dtype": "float32",
71
  "transformers_version": "4.33.3",
72
  "use_cache": true,
73
- "vocab_size": 50257,
74
- "window_size": 256
75
  }
 
1
  {
2
+ "_name_or_path": "stabilityai/stablelm-3b-4e1t",
 
3
  "architectures": [
4
+ "StableLMEpochForCausalLM"
5
  ],
6
+ "auto_map": {
7
+ "AutoConfig": "configuration_stablelm_epoch.StableLMEpochConfig",
8
+ "AutoModelForCausalLM": "modeling_stablelm_epoch.StableLMEpochForCausalLM"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
9
  },
10
+ "bos_token_id": 0,
11
+ "eos_token_id": 0,
12
+ "hidden_act": "silu",
13
+ "hidden_size": 2560,
14
+ "initializer_range": 0.02,
15
+ "intermediate_size": 6912,
16
+ "max_position_embeddings": 4096,
17
+ "model_type": "stablelm_epoch",
18
+ "norm_eps": 1e-05,
19
+ "num_attention_heads": 32,
20
+ "num_heads": 32,
21
+ "num_hidden_layers": 32,
22
+ "num_key_value_heads": 32,
23
+ "rope_pct": 0.25,
24
+ "rope_theta": 10000,
25
+ "rotary_scaling_factor": 1.0,
26
+ "tie_word_embeddings": false,
27
  "torch_dtype": "float32",
28
  "transformers_version": "4.33.3",
29
  "use_cache": true,
30
+ "vocab_size": 50304
 
31
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b1d30621d506e8198ba62a99f480d15cf7b42782df7b67c4f60a70c109b62885
3
- size 4027
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:05ce01fda0ab2122703fa9ae9850e5f1a81fd9ec9e057ed31a4013f2648f4087
3
+ size 3963