nmthien commited on
Commit
88cc15a
·
verified ·
1 Parent(s): 1f109fd

Training in progress, step 1000

Browse files
Files changed (4) hide show
  1. config.json +41 -41
  2. generation_config.json +6 -6
  3. model.safetensors +1 -1
  4. training_args.bin +1 -1
config.json CHANGED
@@ -1,41 +1,41 @@
1
- {
2
- "activation_function": "gelu_new",
3
- "add_cross_attention": false,
4
- "architectures": [
5
- "GPT2LMHeadModel"
6
- ],
7
- "attn_pdrop": 0.1,
8
- "bos_token_id": 0,
9
- "dtype": "float32",
10
- "embd_pdrop": 0.1,
11
- "eos_token_id": 0,
12
- "initializer_range": 0.02,
13
- "layer_norm_epsilon": 1e-05,
14
- "model_type": "gpt2",
15
- "n_ctx": 1024,
16
- "n_embd": 768,
17
- "n_head": 12,
18
- "n_inner": null,
19
- "n_layer": 12,
20
- "n_positions": 1024,
21
- "pad_token_id": 0,
22
- "reorder_and_upcast_attn": false,
23
- "resid_pdrop": 0.1,
24
- "scale_attn_by_inverse_layer_idx": false,
25
- "scale_attn_weights": true,
26
- "summary_activation": null,
27
- "summary_first_dropout": 0.1,
28
- "summary_proj_to_labels": true,
29
- "summary_type": "cls_index",
30
- "summary_use_proj": true,
31
- "task_specific_params": {
32
- "text-generation": {
33
- "do_sample": true,
34
- "max_length": 50
35
- }
36
- },
37
- "tie_word_embeddings": true,
38
- "transformers_version": "5.15.0",
39
- "use_cache": false,
40
- "vocab_size": 32000
41
- }
 
1
+ {
2
+ "activation_function": "gelu_new",
3
+ "add_cross_attention": false,
4
+ "architectures": [
5
+ "GPT2LMHeadModel"
6
+ ],
7
+ "attn_pdrop": 0.1,
8
+ "bos_token_id": 0,
9
+ "dtype": "float32",
10
+ "embd_pdrop": 0.1,
11
+ "eos_token_id": 0,
12
+ "initializer_range": 0.02,
13
+ "layer_norm_epsilon": 1e-05,
14
+ "model_type": "gpt2",
15
+ "n_ctx": 1024,
16
+ "n_embd": 768,
17
+ "n_head": 12,
18
+ "n_inner": null,
19
+ "n_layer": 12,
20
+ "n_positions": 1024,
21
+ "pad_token_id": 0,
22
+ "reorder_and_upcast_attn": false,
23
+ "resid_pdrop": 0.1,
24
+ "scale_attn_by_inverse_layer_idx": false,
25
+ "scale_attn_weights": true,
26
+ "summary_activation": null,
27
+ "summary_first_dropout": 0.1,
28
+ "summary_proj_to_labels": true,
29
+ "summary_type": "cls_index",
30
+ "summary_use_proj": true,
31
+ "task_specific_params": {
32
+ "text-generation": {
33
+ "do_sample": true,
34
+ "max_length": 50
35
+ }
36
+ },
37
+ "tie_word_embeddings": true,
38
+ "transformers_version": "5.0.0",
39
+ "use_cache": false,
40
+ "vocab_size": 32000
41
+ }
generation_config.json CHANGED
@@ -1,6 +1,6 @@
1
- {
2
- "_from_model_config": true,
3
- "bos_token_id": 50256,
4
- "eos_token_id": 50256,
5
- "transformers_version": "5.15.0"
6
- }
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 50256,
4
+ "eos_token_id": 50256,
5
+ "transformers_version": "5.0.0"
6
+ }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cfd224ac4f13bb08781434397b33248f9893d360b8636d996957410f8289aae2
3
  size 441688704
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a4087613726fc5d0b7867f91ac0855708d9e2cbaad5b28e93ac47ef545a8865
3
  size 441688704
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dd37d0c02b2ccb9edd98dd633c884ff4bb66f6f9b90d58062d0802f2813269e2
3
  size 5265
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:38f17bdaa9cd4cb18678e9e465e47da05e1a2eb5afa1c0249e6c612f01f8d0fc
3
  size 5265