minpeter commited on
Commit
1ee42cc
·
verified ·
1 Parent(s): f57124a

Training in progress, step 1000

Browse files
config.json CHANGED
@@ -4,26 +4,28 @@
4
  ],
5
  "attention_bias": false,
6
  "attention_dropout": 0.0,
7
- "bos_token_id": 128256,
8
- "eos_token_id": 128257,
9
  "head_dim": 64,
10
  "hidden_act": "silu",
11
  "hidden_size": 576,
12
- "initializer_range": 0.02,
13
  "intermediate_size": 1536,
14
- "max_position_embeddings": 2048,
 
15
  "mlp_bias": false,
16
  "model_type": "llama",
17
  "num_attention_heads": 9,
18
  "num_hidden_layers": 30,
19
  "num_key_value_heads": 3,
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": "4.51.3",
27
- "use_cache": false,
28
- "vocab_size": 128268
29
  }
 
4
  ],
5
  "attention_bias": false,
6
  "attention_dropout": 0.0,
7
+ "bos_token_id": 128000,
8
+ "eos_token_id": 128001,
9
  "head_dim": 64,
10
  "hidden_act": "silu",
11
  "hidden_size": 576,
12
+ "initializer_range": 0.041666666666666664,
13
  "intermediate_size": 1536,
14
+ "is_llama_config": true,
15
+ "max_position_embeddings": 512,
16
  "mlp_bias": false,
17
  "model_type": "llama",
18
  "num_attention_heads": 9,
19
  "num_hidden_layers": 30,
20
  "num_key_value_heads": 3,
21
  "pretraining_tp": 1,
22
+ "rms_norm_eps": 1e-05,
23
+ "rope_interleaved": false,
24
  "rope_scaling": null,
25
+ "rope_theta": 100000,
26
+ "tie_word_embeddings": true,
27
  "torch_dtype": "float32",
28
  "transformers_version": "4.51.3",
29
+ "use_cache": true,
30
+ "vocab_size": 128256
31
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c3964048014a527484410e4b9e8343cd03777ecb8f77811d7b62889f38ea55ee
3
- size 1015903256
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d230ebeee121a8d252954a27cde0c08a983b76d6649dea292ac6320db7e96b1
3
+ size 720346024
runs/Jun04_04-59-16_gpu03/events.out.tfevents.1748980760.gpu03.401561.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6deacb7f5aeb3e7ab1dea2281d0a8f53b96ed8259490ff7170590b5aaff37b3a
3
+ size 5128
runs/Jun04_05-07-40_gpu03/events.out.tfevents.1748981264.gpu03.403988.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad9c57221d3e5e0259621f277c381a56d5812e3d8731fea89390b12302679abd
3
+ size 5125
runs/Jun04_05-10-44_gpu03/events.out.tfevents.1748981448.gpu03.405168.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:03996f334bf702cc646a588505979112c462d7a8be7d34a3094021123044789c
3
+ size 6367
runs/Jun04_05-14-03_gpu03/events.out.tfevents.1748981647.gpu03.406487.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3c75c9bb34a54465bdca44f5a13da242ef9870077aee418c23392af984f3f09
3
+ size 8242
runs/Jun04_05-22-47_gpu03/events.out.tfevents.1748982171.gpu03.409079.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d26b0f7ef765c29a958a367f94c90e34b31aa04399f13e6b7731fc78f1ad8e5
3
+ size 26522
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dc85aa028e904531eb3094cca8ea7d5c1b0f768d5faeeb4854ca98a752ec3db5
3
- size 6904
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:25fb4691a1a754fc20a14c94605e92c90427fa489b3144013ed9532a2d2f0141
3
+ size 5368