Hugging Face's logo

VERSIL91
/
62772075-d4b8-4232-adfa-a16f07808995

PEFT
Safetensors
gemma2
axolotl
Generated from Trainer
Model card Files
xet
 Community
VERSIL91 commited on
Commit
2bfbd48
·
verified ·
1 Parent(s): 65e981f

Training in progress, step 5, 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 +11 -4
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7157ebc8b775157ff848c0c80a969b68dc105f23b72f115346917e5998f3a5bf
3
  size 41581360
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c27c01685ffca695b5879119a0016b177ac9e79321231c2a4ace90fd77f4531
3
  size 41581360
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:50915f688a28169ace9bf1369c1ab96aa433a84ec5ecd1df2a79320503936ada
3
  size 21505540
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:536404728284eb81f7be95a047c24cbff1a24dd38807fae74b2e06f941e0fb8f
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:b8d6b9a0e9e9502751def1097143074ef257eab24506a0f12d159e188fa21987
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:572c5653b97399d6dc550389d4e48df5479adab7c80147f357d4d04c0f7252da
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c7adb031dc938779259a07e684ea318126e92e52b40c256b93ef474d2ac57a5b
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d63217b923cb177f669d6bc2174b89abdc6a56d968d279b505491b37976d9bb
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": 0.007622677465459742,
5
  "eval_steps": 2,
6
- "global_step": 4,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -59,6 +59,13 @@
59
  "eval_samples_per_second": 73.441,
60
  "eval_steps_per_second": 36.72,
61
  "step": 4
 
 
 
 
 
 
 
62
  }
63
  ],
64
  "logging_steps": 1,
@@ -73,12 +80,12 @@
73
  "should_evaluate": false,
74
  "should_log": false,
75
  "should_save": true,
76
- "should_training_stop": false
77
  },
78
  "attributes": {}
79
  }
80
  },
81
- "total_flos": 812658162401280.0,
82
  "train_batch_size": 2,
83
  "trial_name": null,
84
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.009528346831824679,
5
  "eval_steps": 2,
6
+ "global_step": 5,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
59
  "eval_samples_per_second": 73.441,
60
  "eval_steps_per_second": 36.72,
61
  "step": 4
62
+ },
63
+ {
64
+ "epoch": 0.009528346831824679,
65
+ "grad_norm": 1.683907151222229,
66
+ "learning_rate": 5e-05,
67
+ "loss": 3.0349,
68
+ "step": 5
69
  }
70
  ],
71
  "logging_steps": 1,
 
80
  "should_evaluate": false,
81
  "should_log": false,
82
  "should_save": true,
83
+ "should_training_stop": true
84
  },
85
  "attributes": {}
86
  }
87
  },
88
+ "total_flos": 1012697094684672.0,
89
  "train_batch_size": 2,
90
  "trial_name": null,
91
  "trial_params": null