SodaXII commited on
Commit
8152e56
·
verified ·
1 Parent(s): b7b975f

Model save

Browse files
README.md CHANGED
@@ -34,8 +34,8 @@ More information needed
34
 
35
  The following hyperparameters were used during training:
36
  - learning_rate: 0.0003
37
- - train_batch_size: 64
38
- - eval_batch_size: 64
39
  - seed: 42
40
  - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
41
  - lr_scheduler_type: cosine_with_restarts
 
34
 
35
  The following hyperparameters were used during training:
36
  - learning_rate: 0.0003
37
+ - train_batch_size: 128
38
+ - eval_batch_size: 128
39
  - seed: 42
40
  - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
41
  - lr_scheduler_type: cosine_with_restarts
logs/events.out.tfevents.1740248351.372cc108f014.685.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:35f470c4f70ef93224951df2417f20fc15a7b011a96c6c722e9128a7061df13b
3
- size 88
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:57864ba12fb0d14b7ce485959c9413dcc394e90f188a3c1ffdf484f67c0344e0
3
+ size 5666
logs/events.out.tfevents.1740248557.372cc108f014.685.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0de7013242e0565c78acf66864f7e0cfbeff07c8dd0ca00e91fa46b2b7bb5d3e
3
+ size 88
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f6b35c8e06aca6959767b6c8bf05192798b4ef6353f08066bf8ca5eead5b5249
3
  size 343242432
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:239b41f1d8afebfa2b4ca95d6b80ca863bf42551eca9f06db4e2a69c55203ddc
3
  size 343242432
trainer_state.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0,
5
+ "eval_steps": 500,
6
+ "global_step": 0,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [],
11
+ "logging_steps": 500,
12
+ "max_steps": 2500,
13
+ "num_input_tokens_seen": 0,
14
+ "num_train_epochs": 20,
15
+ "save_steps": 500,
16
+ "stateful_callbacks": {
17
+ "TrainerControl": {
18
+ "args": {
19
+ "should_epoch_stop": false,
20
+ "should_evaluate": false,
21
+ "should_log": false,
22
+ "should_save": false,
23
+ "should_training_stop": false
24
+ },
25
+ "attributes": {}
26
+ }
27
+ },
28
+ "total_flos": 0,
29
+ "train_batch_size": 64,
30
+ "trial_name": null,
31
+ "trial_params": null
32
+ }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d0c3a86693113526e58f0f0ac6e3ac19f2e73f4c821fbca6aeaa3b69eecd2664
3
  size 5496
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5629997e92aeefc240871b3f744ed1876694f2d4685b25f8a0990a9e3f5ac6c3
3
  size 5496