Hugging Face's logo

tuanna08go
/
db1ed113-5386-4717-8108-42b6a35b6b96

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files
xet
 Community
tuanna08go commited on
Commit
6f621e8
·
verified ·
1 Parent(s): 665f2b4

Training in progress, step 26, checkpoint

Browse files
Files changed (5) hide show
  1. last-checkpoint/adapter_model.safetensors +1 -1
  2. last-checkpoint/optimizer.pt +1 -1
  3. last-checkpoint/rng_state.pth +1 -1
  4. last-checkpoint/scheduler.pt +1 -1
  5. last-checkpoint/trainer_state.json +32 -3
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:72c9a686ba813ae68b4035427cf8754469c77d1e0fbd9d05c402c43dc9246234
3
  size 390888
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8361971ded0ffedc76c8c205e1ebf9b86f0b9026ecdf30ca21e3ee2bc024f55b
3
  size 390888
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:53d773537d5c1fbee6e4594e43f232200c7f04d816e1b4ad9fa4d682cbcf749e
3
  size 819770
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1325400e2a8bcff34d3a29a4264238fd3d5c38f20053de441e61ea09421d3918
3
  size 819770
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:15160272ffddfe27c654df211d1192733c9457f0ce97b19578f9cd078fb647f8
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:638f0e887c7eab30601fcd15f109e577ce9025b567cf9228ffde08282c0e880e
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4395bafb1cf8adc0d9dbfe550d1b98763496e37a8fadb76c1ca1168a4a757f4e
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37841e69eda911caeb33edeefa0b2f140e72dcce247aeb757b2fe89c00d7887b
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 0.0008452123596053508,
5
  "eval_steps": 10,
6
- "global_step": 13,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -37,6 +37,35 @@
37
  "eval_samples_per_second": 84.344,
38
  "eval_steps_per_second": 42.179,
39
  "step": 10
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
40
  }
41
  ],
42
  "logging_steps": 5,
@@ -56,7 +85,7 @@
56
  "attributes": {}
57
  }
58
  },
59
- "total_flos": 1688132517888.0,
60
  "train_batch_size": 2,
61
  "trial_name": null,
62
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.0016904247192107017,
5
  "eval_steps": 10,
6
+ "global_step": 26,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
37
  "eval_samples_per_second": 84.344,
38
  "eval_steps_per_second": 42.179,
39
  "step": 10
40
+ },
41
+ {
42
+ "epoch": 0.0009752450303138663,
43
+ "grad_norm": 2.793973445892334,
44
+ "learning_rate": 9.619397662556435e-05,
45
+ "loss": 6.6605,
46
+ "step": 15
47
+ },
48
+ {
49
+ "epoch": 0.001300326707085155,
50
+ "grad_norm": 2.789121389389038,
51
+ "learning_rate": 8.535533905932738e-05,
52
+ "loss": 6.4801,
53
+ "step": 20
54
+ },
55
+ {
56
+ "epoch": 0.001300326707085155,
57
+ "eval_loss": 6.546636581420898,
58
+ "eval_runtime": 76.8222,
59
+ "eval_samples_per_second": 84.312,
60
+ "eval_steps_per_second": 42.162,
61
+ "step": 20
62
+ },
63
+ {
64
+ "epoch": 0.0016254083838564439,
65
+ "grad_norm": 2.7600698471069336,
66
+ "learning_rate": 6.91341716182545e-05,
67
+ "loss": 6.5366,
68
+ "step": 25
69
  }
70
  ],
71
  "logging_steps": 5,
 
85
  "attributes": {}
86
  }
87
  },
88
+ "total_flos": 3359875399680.0,
89
  "train_batch_size": 2,
90
  "trial_name": null,
91
  "trial_params": null