Hugging Face's logo

VERSIL91
/
3eaaf228-4375-4797-b340-78d26ee09408

PEFT
Safetensors
qwen2
axolotl
Generated from Trainer
Model card Files
xet
 Community
VERSIL91 commited on
Commit
2415b42
·
verified ·
1 Parent(s): 4e4467e

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:d33c00239b807eb645fe751b808c051a06e39e75794c017fc6f3c1da0e024b29
3
  size 124756544
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a65028e50977b55be004576fad8025f6bebaef184f158f040558d40aa337250e
3
  size 124756544
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9e5b50b1843a26cf74505cd6ac28b4c414e62da6c05691f4eb001f4e1c8a668c
3
  size 63958740
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c6b7fae9acf86e2a2268178455cdf56bb5f1e54b81d760b4cf4b139269cbb9d
3
  size 63958740
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:39dd70f78833b407302ec7a08a5ddbe1954a321879cf7446f5acb83d55b840c1
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:648a063f91ae3ab228fd410ffbd4321ad14a00c1e969d3c92bcd911e862ae5e7
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": 0.0003170875508454842,
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": 24.933,
60
  "eval_steps_per_second": 12.467,
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": 5276916944732160.0,
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": 0.00039635943855685526,
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": 24.933,
60
  "eval_steps_per_second": 12.467,
61
  "step": 4
62
+ },
63
+ {
64
+ "epoch": 0.00039635943855685526,
65
+ "grad_norm": 4.737051963806152,
66
+ "learning_rate": 5e-05,
67
+ "loss": 7.9264,
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": 6596146180915200.0,
89
  "train_batch_size": 2,
90
  "trial_name": null,
91
  "trial_params": null