Hugging Face's logo

chauhoang
/
e9b4e1e0-d991-870a-cf3d-efda9fc39bc4

PEFT
Safetensors
mistral
axolotl
Generated from Trainer
Model card Files
xet
 Community
chauhoang commited on
Commit
6615318
·
verified ·
1 Parent(s): 77dfc27

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 sha256:346497888bf0e9045d04206e1a7d3eab5bd84adfe8c6b1a23116df1478a534c7
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2aa0db68821daa81dcbb0081917c262513f068c74ac67db9f7e3e70930109245
3
  size 83945296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e5557b706131061e2fbb0158eba972530d1654bcb79fec070022a02c4f570fee
3
  size 43122580
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:13cc63919495e7957ef425fbf67f3d2b835eb08f2e5864c7d6278a731b0be419
3
  size 43122580
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2fe6cca490e6fa13d53ae6eb09e57db4f1767a72358e96edbf5d69f6c2d1789a
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a5f891767aaacfb795fc4c851c74f7dcf55cd20474ec59a43d271975d0645cf
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": 0.00045140064411399605,
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": 5.277,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 4557025195327488.0,
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": 0.000677100966170994,
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": 5.277,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.0005208468970546108,
72
+ "grad_norm": 25.659969329833984,
73
+ "learning_rate": 5e-05,
74
+ "loss": 5.2087,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.0005208468970546108,
79
+ "eval_loss": 1.267523169517517,
80
+ "eval_runtime": 1566.1685,
81
+ "eval_samples_per_second": 15.485,
82
+ "eval_steps_per_second": 7.742,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.0006076547132303793,
87
+ "grad_norm": 17.720985412597656,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 4.6799,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 6835537792991232.0,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null