robertou2 commited on
Commit
eafddd0
·
verified ·
1 Parent(s): 312eb0c

Upload folder using huggingface_hub

Browse files
Files changed (2) hide show
  1. adapter_model.safetensors +1 -1
  2. trainer_state.json +16 -37
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:64a9b2cd471e88dbe102e8ab65b8e1c870b33c4afb331c1b401d48d73a9823f1
3
  size 242273720
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1006336b1b925a5e674bf00fe362cff9981eb65e32ba3950c4fcb3826cb23626
3
  size 242273720
trainer_state.json CHANGED
@@ -2,53 +2,32 @@
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
- "epoch": 4.0,
6
  "eval_steps": 500,
7
- "global_step": 52,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
11
  "log_history": [
12
  {
13
- "epoch": 0.7843137254901961,
14
- "grad_norm": 0.9842274188995361,
15
- "learning_rate": 0.00039825281386539503,
16
- "loss": 2.3652,
17
- "step": 10
18
  },
19
  {
20
- "epoch": 1.5490196078431373,
21
- "grad_norm": 1.0785025358200073,
22
- "learning_rate": 0.0003789458659641527,
23
- "loss": 1.8778,
24
- "step": 20
25
- },
26
- {
27
- "epoch": 2.313725490196078,
28
- "grad_norm": 2.144801616668701,
29
- "learning_rate": 0.00034024735685449773,
30
- "loss": 1.2215,
31
- "step": 30
32
- },
33
- {
34
- "epoch": 3.0784313725490198,
35
- "grad_norm": 1.2375843524932861,
36
- "learning_rate": 0.00028635087046769857,
37
- "loss": 0.6955,
38
- "step": 40
39
- },
40
- {
41
- "epoch": 3.8627450980392157,
42
- "grad_norm": 1.2806615829467773,
43
- "learning_rate": 0.00022309692739391727,
44
- "loss": 0.2968,
45
- "step": 50
46
  }
47
  ],
48
- "logging_steps": 10,
49
- "max_steps": 100,
50
  "num_input_tokens_seen": 0,
51
- "num_train_epochs": 9,
52
  "save_steps": 500,
53
  "stateful_callbacks": {
54
  "TrainerControl": {
@@ -62,7 +41,7 @@
62
  "attributes": {}
63
  }
64
  },
65
- "total_flos": 9.76533894432768e+16,
66
  "train_batch_size": 1,
67
  "trial_name": null,
68
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 3.0,
6
  "eval_steps": 500,
7
+ "global_step": 39,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
11
  "log_history": [
12
  {
13
+ "epoch": 1.0784313725490196,
14
+ "grad_norm": 1.2912613153457642,
15
+ "learning_rate": 0.0006065681551404392,
16
+ "loss": 2.3505,
17
+ "step": 14
18
  },
19
  {
20
+ "epoch": 2.156862745098039,
21
+ "grad_norm": 1.3055678606033325,
22
+ "learning_rate": 0.00027211767311528996,
23
+ "loss": 1.365,
24
+ "step": 28
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
25
  }
26
  ],
27
+ "logging_steps": 14,
28
+ "max_steps": 45,
29
  "num_input_tokens_seen": 0,
30
+ "num_train_epochs": 4,
31
  "save_steps": 500,
32
  "stateful_callbacks": {
33
  "TrainerControl": {
 
41
  "attributes": {}
42
  }
43
  },
44
+ "total_flos": 7.32400420824576e+16,
45
  "train_batch_size": 1,
46
  "trial_name": null,
47
  "trial_params": null