Hugging Face's logo

duyphu
/
dd99cfae-4152-4304-b09a-31a00951788f

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files
xet
 Community
duyphu commited on
Commit
9c237e7
·
verified ·
1 Parent(s): da059c3

Training in progress, step 39, 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 +25 -3
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f0e742afbd1847ef2698fe226fa44c77468e3c89a6490297b211df3c28e7daf9
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:799df9563b168d61d80c3aa963e468335692b3637ba2a0b5e9457ddea635c83c
3
  size 83945296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e87f113bc9955e4fcb5f82a15aa35cef6bb0d57b913f241cea33c7bcb4ab1319
3
  size 43122580
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b372fda91b4481efc37a3e87c2b1b461cf95cd56635a8efbd8a5288538dcb8c
3
  size 43122580
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3eba564523b8e7170117124c450887f82a78e23aad68f44ac77face0466e16e2
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f6132c086c411e9bdb0c32c2a53364b7f55dda21e5dfc4747b9c3b8e7b9d6df
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:37841e69eda911caeb33edeefa0b2f140e72dcce247aeb757b2fe89c00d7887b
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c50dbaa792cda4a28fbbc2acb2a3e03c59530712bbc5107212d33064d193da4
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": 0.03728935102187164,
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,
@@ -66,6 +66,28 @@
66
  "learning_rate": 6.91341716182545e-05,
67
  "loss": 1.2905,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 9571494984155136.0,
89
  "train_batch_size": 2,
90
  "trial_name": null,
91
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.055934026532807456,
5
  "eval_steps": 10,
6
+ "global_step": 39,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
66
  "learning_rate": 6.91341716182545e-05,
67
  "loss": 1.2905,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.04302617425600574,
72
+ "grad_norm": 1.4964189529418945,
73
+ "learning_rate": 5e-05,
74
+ "loss": 1.0653,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.04302617425600574,
79
+ "eval_loss": 0.9245858788490295,
80
+ "eval_runtime": 38.0913,
81
+ "eval_samples_per_second": 7.718,
82
+ "eval_steps_per_second": 3.859,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.05019720329867336,
87
+ "grad_norm": 3.2060110569000244,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 1.1814,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 1.4380362029334528e+16,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null