ardanila commited on
Commit
3a45c99
1 Parent(s): 4cc4c7b

Training in progress, step 1500

Browse files
Files changed (3) hide show
  1. config.json +32 -24
  2. pytorch_model.bin +2 -2
  3. training_args.bin +2 -2
config.json CHANGED
@@ -1,31 +1,39 @@
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
  }
 
1
  {
2
+ "_name_or_path": "gpt2",
3
+ "activation_function": "gelu_new",
4
  "architectures": [
5
+ "GPT2LMHeadModel"
6
  ],
7
+ "attn_pdrop": 0.1,
8
+ "bos_token_id": 50256,
9
+ "embd_pdrop": 0.1,
10
+ "eos_token_id": 50256,
 
 
 
 
11
  "initializer_range": 0.02,
12
+ "layer_norm_epsilon": 1e-05,
13
+ "model_type": "gpt2",
14
+ "n_ctx": 1024,
15
+ "n_embd": 768,
16
+ "n_head": 12,
17
+ "n_inner": null,
18
+ "n_layer": 12,
19
+ "n_positions": 1024,
20
+ "reorder_and_upcast_attn": false,
21
+ "resid_pdrop": 0.1,
22
+ "scale_attn_by_inverse_layer_idx": false,
23
+ "scale_attn_weights": true,
24
+ "summary_activation": null,
25
+ "summary_first_dropout": 0.1,
26
+ "summary_proj_to_labels": true,
27
+ "summary_type": "cls_index",
28
+ "summary_use_proj": true,
29
+ "task_specific_params": {
30
+ "text-generation": {
31
+ "do_sample": true,
32
+ "max_length": 50
33
+ }
34
+ },
35
  "torch_dtype": "float32",
36
+ "transformers_version": "4.34.0",
37
  "use_cache": true,
38
+ "vocab_size": 50257
39
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2ea4e0379cd78d7ef7a55cc6a65d78e2d23888a73e34e96de9162fd9a818aa67
3
- size 5262408809
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1fbc5d6fb7f1315d47a6228aa09a80688b749bee588b1cdcd64e7b3462029ef8
3
+ size 497807197
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:77d685a479afaea75f06e7b37d40c83ee37e5516b6cb3760ad00f9d951987b30
3
- size 3963
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4a13850af8f3c7ea0a8d664f63655526e2a1d2a3c20e04a7547c8a4458a9e9d3
3
+ size 4027