LeTue09 commited on
Commit
ebfa303
·
verified ·
1 Parent(s): eb7d448

Upload folder using huggingface_hub

Browse files
model-00001-of-00002.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ac9c3a7c740dcc2ce673e50544ea9eb55143527de9524e486a9f2b29e6e1d609
3
  size 4957560304
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e17bdb7fa4d85f695daa40fe29b2a113627569a50b69084f7cd61f99fec8d4ca
3
  size 4957560304
model-00002-of-00002.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:62f1154ba25ccb583f2bd7b7aabad8c25e64ea5a9aaf878b4547f6af02ec72b1
3
  size 1214366696
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f0495598acb24db6029fab71a7536907bb7637f39482367274ddacbb2f5e8843
3
  size 1214366696
trainer_state.json ADDED
@@ -0,0 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 1.0,
6
+ "eval_steps": 500,
7
+ "global_step": 37,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "entropy": 1.115849182009697,
14
+ "epoch": 0.273972602739726,
15
+ "grad_norm": 0.89453125,
16
+ "learning_rate": 1.9986141830690626e-05,
17
+ "loss": 1.1036,
18
+ "mean_token_accuracy": 0.6849135965108871,
19
+ "num_tokens": 3403502.0,
20
+ "step": 10
21
+ },
22
+ {
23
+ "entropy": 0.9511253193020821,
24
+ "epoch": 0.547945205479452,
25
+ "grad_norm": 0.46484375,
26
+ "learning_rate": 1.9740841436914917e-05,
27
+ "loss": 0.9169,
28
+ "mean_token_accuracy": 0.7195438116788864,
29
+ "num_tokens": 6821458.0,
30
+ "step": 20
31
+ },
32
+ {
33
+ "entropy": 0.9001567244529725,
34
+ "epoch": 0.821917808219178,
35
+ "grad_norm": 0.376953125,
36
+ "learning_rate": 1.9196262851127695e-05,
37
+ "loss": 0.8617,
38
+ "mean_token_accuracy": 0.7317715749144554,
39
+ "num_tokens": 10282466.0,
40
+ "step": 30
41
+ }
42
+ ],
43
+ "logging_steps": 10,
44
+ "max_steps": 185,
45
+ "num_input_tokens_seen": 0,
46
+ "num_train_epochs": 5,
47
+ "save_steps": 500,
48
+ "stateful_callbacks": {
49
+ "TrainerControl": {
50
+ "args": {
51
+ "should_epoch_stop": false,
52
+ "should_evaluate": false,
53
+ "should_log": false,
54
+ "should_save": true,
55
+ "should_training_stop": false
56
+ },
57
+ "attributes": {}
58
+ }
59
+ },
60
+ "total_flos": 2.8544478491757773e+17,
61
+ "train_batch_size": 4,
62
+ "trial_name": null,
63
+ "trial_params": null
64
+ }