medric49 commited on
Commit
07a7f5f
1 Parent(s): 18c0d63

Training in progress, epoch 1

Browse files
Files changed (3) hide show
  1. config.json +31 -21
  2. pytorch_model.bin +2 -2
  3. training_args.bin +1 -1
config.json CHANGED
@@ -1,29 +1,39 @@
1
  {
2
- "_name_or_path": "airedefined/pythia-14m-dolly-rag",
 
3
  "architectures": [
4
- "GPTNeoXForCausalLM"
5
  ],
6
- "attention_dropout": 0.0,
7
- "bos_token_id": 0,
8
- "classifier_dropout": 0.1,
9
- "eos_token_id": 0,
10
- "hidden_act": "gelu",
11
- "hidden_dropout": 0.0,
12
- "hidden_size": 128,
13
  "initializer_range": 0.02,
14
- "intermediate_size": 512,
15
- "layer_norm_eps": 1e-05,
16
- "max_position_embeddings": 2048,
17
- "model_type": "gpt_neox",
18
- "num_attention_heads": 4,
19
- "num_hidden_layers": 6,
20
- "rope_scaling": null,
21
- "rotary_emb_base": 10000,
22
- "rotary_pct": 0.25,
23
- "tie_word_embeddings": false,
 
 
 
 
 
 
 
 
 
 
 
 
 
24
  "torch_dtype": "float32",
25
  "transformers_version": "4.34.0",
26
  "use_cache": false,
27
- "use_parallel_residual": true,
28
- "vocab_size": 50280
29
  }
 
1
  {
2
+ "_name_or_path": "airedefined/gpt2-dolly-rag",
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": false,
38
+ "vocab_size": 50260
 
39
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6a4ee1b673036cc4d76fe96043653348f1eea0e4055ee13a39d566f6010e9ae5
3
- size 56273447
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a1071a54b96f534f4f0658b18fa23bc4a4a21f7af60a9d7ddd8a62ad955befa
3
+ size 497816413
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7e31c515e47815f88e8c1990f5bc41a1684f6d52a95179168851bd5d311b841e
3
  size 4091
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f304d0fa723e2f48f673444b2b0dc60283b77c9f20d636235995cf98f44bdeb
3
  size 4091