vwxyzjn commited on
Commit
2ea6899
1 Parent(s): 81fdc87

End of training

Browse files
README.md CHANGED
@@ -45,7 +45,7 @@ The following hyperparameters were used during training:
45
  - total_eval_batch_size: 7
46
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
  - lr_scheduler_type: linear
48
- - num_epochs: 1.0
49
 
50
  ### Training results
51
 
 
45
  - total_eval_batch_size: 7
46
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
47
  - lr_scheduler_type: linear
48
+ - num_epochs: 0.1
49
 
50
  ### Training results
51
 
config.json CHANGED
@@ -21,7 +21,7 @@
21
  "num_attention_heads": 32,
22
  "num_hidden_layers": 32,
23
  "num_key_value_heads": 8,
24
- "pad_token_id": 32000,
25
  "rms_norm_eps": 1e-05,
26
  "rope_theta": 10000.0,
27
  "sliding_window": 4096,
 
21
  "num_attention_heads": 32,
22
  "num_hidden_layers": 32,
23
  "num_key_value_heads": 8,
24
+ "pad_token_id": 2,
25
  "rms_norm_eps": 1e-05,
26
  "rope_theta": 10000.0,
27
  "sliding_window": 4096,
model-00001-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4f076830e04679a4748a2416a56a44d1fbd1bf8d191ccbe1d2fae07d91e12dea
3
  size 4943162336
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2308e13cc8a01bd8fcb0567b271b1a2a51af2ddb8711629d08f5a7452286978
3
  size 4943162336
model-00002-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c9833b772165651a0987277aad628b67dc4c16f9344ecbccc3d55b8e17ccfb8c
3
  size 4999819336
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cef66996d526d901bf4f48766aa07a042798921f67e574f273d557c6661f6200
3
  size 4999819336
model-00003-of-00003.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c8caed9e6ae5a601a4d2c0877fcfe2be424a529187e9eab4b6d2d79cc399b74d
3
  size 4278380512
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a9830a1158d4efe14a7732803212c396b8c8fde9a8a435f30382d35b6d7921a2
3
  size 4278380512
runs/May06_18-38-28_ip-26-0-161-78/events.out.tfevents.1715020931.ip-26-0-161-78.1630064.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c63dfed3077caafa9916fef8f7873e6ea88495433dceac32887f3f6a438c77c1
3
+ size 5609
special_tokens_map.json CHANGED
@@ -18,13 +18,7 @@
18
  "rstrip": false,
19
  "single_word": false
20
  },
21
- "pad_token": {
22
- "content": "</s>",
23
- "lstrip": false,
24
- "normalized": false,
25
- "rstrip": false,
26
- "single_word": false
27
- },
28
  "unk_token": {
29
  "content": "<unk>",
30
  "lstrip": false,
 
18
  "rstrip": false,
19
  "single_word": false
20
  },
21
+ "pad_token": "</s>",
 
 
 
 
 
 
22
  "unk_token": {
23
  "content": "<unk>",
24
  "lstrip": false,
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:225071f278a1586ee5ec1f08d6e467bc9ac571f93216e75b5248e603f721e988
3
  size 6136
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:85fc913a29f8ad31753f37e6fe00059e64a1e5030aef4d88fd1cdeaf12d88120
3
  size 6136