NeerjaK commited on
Commit
1e2945d
1 Parent(s): 14cdae0

Training in progress, step 600

Browse files
Files changed (4) hide show
  1. config.json +29 -29
  2. generation_config.json +6 -6
  3. model.safetensors +1 -1
  4. training_args.bin +2 -2
config.json CHANGED
@@ -1,29 +1,29 @@
1
- {
2
- "architectures": [
3
- "LlamaForCausalLM"
4
- ],
5
- "attention_bias": false,
6
- "attention_dropout": 0.0,
7
- "bos_token_id": 1,
8
- "eos_token_id": 2,
9
- "head_dim": 64,
10
- "hidden_act": "silu",
11
- "hidden_size": 256,
12
- "initializer_range": 0.02,
13
- "intermediate_size": 688,
14
- "max_position_embeddings": 64,
15
- "mlp_bias": false,
16
- "model_type": "llama",
17
- "num_attention_heads": 4,
18
- "num_hidden_layers": 12,
19
- "num_key_value_heads": 2,
20
- "pretraining_tp": 1,
21
- "rms_norm_eps": 1e-06,
22
- "rope_scaling": null,
23
- "rope_theta": 10000.0,
24
- "tie_word_embeddings": false,
25
- "torch_dtype": "float32",
26
- "transformers_version": "4.46.2",
27
- "use_cache": true,
28
- "vocab_size": 32769
29
- }
 
1
+ {
2
+ "architectures": [
3
+ "LlamaForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 2,
9
+ "head_dim": 64,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 256,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 688,
14
+ "max_position_embeddings": 64,
15
+ "mlp_bias": false,
16
+ "model_type": "llama",
17
+ "num_attention_heads": 4,
18
+ "num_hidden_layers": 12,
19
+ "num_key_value_heads": 2,
20
+ "pretraining_tp": 1,
21
+ "rms_norm_eps": 1e-06,
22
+ "rope_scaling": null,
23
+ "rope_theta": 10000.0,
24
+ "tie_word_embeddings": false,
25
+ "torch_dtype": "float32",
26
+ "transformers_version": "4.46.2",
27
+ "use_cache": true,
28
+ "vocab_size": 32769
29
+ }
generation_config.json CHANGED
@@ -1,6 +1,6 @@
1
- {
2
- "_from_model_config": true,
3
- "bos_token_id": 1,
4
- "eos_token_id": 2,
5
- "transformers_version": "4.46.2"
6
- }
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "transformers_version": "4.46.2"
6
+ }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:40c0c1868e6354d23fd40c7834881f6cc7cece5eff0d8e2d98bf86dcc0074d08
3
  size 101948208
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f4b3b90e9031d4ebe1ed8d97b727ae52d1f600ab700c72dd61abd00a328ac44f
3
  size 101948208
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e9efd0bb07076cf3374f01aed7663ac5426fd64dcd975b8fa2a953b8b63881d3
3
- size 5304
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f0aead81e2ddaa19eeb571dd28cbb79f9772d875426684e62c39bdacd1720a10
3
+ size 5240