Hugging Face's logo

tuanna08go
/
a45bc180-e906-4fa6-b3ca-f6bb98da93fb

PEFT
Safetensors
mistral
axolotl
Generated from Trainer
Model card Files
xet
 Community
tuanna08go commited on
Commit
850319a
·
verified ·
1 Parent(s): 298e828

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 sha256:306d029c5ce1d16e56b07754e9a20ce1c39e159f9aef1d9b228fb37ebc687928
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:19283cf2f5f8b60a4c09f96d8975b3ad32892d54420ed89028ee06da9debe909
3
  size 83945296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ee8605d46e45356c59f496c39db4eb852f1f8cab85e54bc09ddb32da6c98c73a
3
  size 43122580
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:07d81e57f8498eddd6e252b5780aa49c5d49057ea1fe6dd11ef55468c8a00dd8
3
  size 43122580
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:53f4f45187e26a4049e655bf2331e2a9bcb87445e02e0e30a1e6d4e3a5463624
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:89be65360c462d9c4812bfee4e603b36894408ac274af51796d35fb242819f3e
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": 0.0012334843560974453,
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": 5.618,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 5082835794788352.0,
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": 0.0018502265341461678,
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": 5.618,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.0014232511801124368,
72
+ "grad_norm": 8.83657169342041,
73
+ "learning_rate": 5e-05,
74
+ "loss": 5.6481,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.0014232511801124368,
79
+ "eval_loss": 1.3377556800842285,
80
+ "eval_runtime": 616.2304,
81
+ "eval_samples_per_second": 14.404,
82
+ "eval_steps_per_second": 7.202,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.0016604597101311763,
87
+ "grad_norm": 9.329240798950195,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 5.3622,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 7580436142227456.0,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null