Hugging Face's logo

chauhoang
/
6dc5c693-bd8b-469b-8884-71b4941f4e88

PEFT
Safetensors
gemma2
axolotl
Generated from Trainer
Model card Files
xet
 Community
chauhoang commited on
Commit
21fe596
·
verified ·
1 Parent(s): e639967

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 sha256:98fe3439283869835102253292681b5d21925c75a62e6bb88f7bea4cea90d417
3
  size 41581360
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:63b4cc510edfca6dcb0caf8e37ce46d5b75ed3e12899ec5bf266c5c498ceb3af
3
  size 41581360
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fa7df2ad93809b6bc1feccee5a266c961f1d1ed1d07d59b2b8c69607dbb756d1
3
  size 21505540
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d8de6441df76cbe867dcd99e804d6bd79d3860dfd2cfb265d0c5b6299efb0d2
3
  size 21505540
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:41e8229120dce69fa1081c29f9ca7f12647fb8db9c60a1f8dce12e8d0bda6beb
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4bedce020016b09a6a41ada3c9ab9e3eb4de492cd0025f7e65d03cfe5dff2df5
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": 0.04744525547445255,
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": 18.166,
38
  "eval_steps_per_second": 9.083,
39
  "step": 10
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
40
  }
41
  ],
42
  "logging_steps": 5,
@@ -56,7 +85,7 @@
56
  "attributes": {}
57
  }
58
  },
59
- "total_flos": 650126529921024.0,
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": 0.0948905109489051,
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": 18.166,
38
  "eval_steps_per_second": 9.083,
39
  "step": 10
40
+ },
41
+ {
42
+ "epoch": 0.05474452554744526,
43
+ "grad_norm": 12.432720184326172,
44
+ "learning_rate": 9.619397662556435e-05,
45
+ "loss": 2.7055,
46
+ "step": 15
47
+ },
48
+ {
49
+ "epoch": 0.072992700729927,
50
+ "grad_norm": 14.823360443115234,
51
+ "learning_rate": 8.535533905932738e-05,
52
+ "loss": 1.7577,
53
+ "step": 20
54
+ },
55
+ {
56
+ "epoch": 0.072992700729927,
57
+ "eval_loss": 1.3997901678085327,
58
+ "eval_runtime": 6.3225,
59
+ "eval_samples_per_second": 18.347,
60
+ "eval_steps_per_second": 9.174,
61
+ "step": 20
62
+ },
63
+ {
64
+ "epoch": 0.09124087591240876,
65
+ "grad_norm": 6.508552551269531,
66
+ "learning_rate": 6.91341716182545e-05,
67
+ "loss": 1.757,
68
+ "step": 25
69
  }
70
  ],
71
  "logging_steps": 5,
 
85
  "attributes": {}
86
  }
87
  },
88
+ "total_flos": 1312755493109760.0,
89
  "train_batch_size": 2,
90
  "trial_name": null,
91
  "trial_params": null