Hugging Face's logo

tuanna08go
/
9e697b1f-e3a5-438e-85b4-d6390001d383

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files
xet
 Community
tuanna08go commited on
Commit
8207869
·
verified ·
1 Parent(s): b7bc3e4

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:c3b2daf5fa63b21d344c19ad50f533689fac34f155d540f6393c58e9fa848723
3
  size 50899792
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7014f2301f834485a93dc5cc5fe2b0c4c3adcbb557d4a9aba7119f0e7372a93d
3
  size 50899792
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3c9796da75f9d9b460485b901b755160e1db010210c26a62f2a2a944f15691b8
3
  size 26231300
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5fa43006c9de1e5d22f404b9ba58739d11bdf9a5f967e27733ab8f580cddefa3
3
  size 26231300
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e557af93914c894de252ad5739c858bc8be67dba19068d91502dd049001e333e
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da57a3a869ac100e03e854428cb96b9fe176c6ed5065d0878032c78bdd0f415e
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": 0.02056555269922879,
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": 2.2359,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 2132126528962560.0,
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": 0.030848329048843187,
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": 2.2359,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.02372948388372553,
72
+ "grad_norm": 1.2021112442016602,
73
+ "learning_rate": 5e-05,
74
+ "loss": 2.0013,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.02372948388372553,
79
+ "eval_loss": 2.030576467514038,
80
+ "eval_runtime": 20.9083,
81
+ "eval_samples_per_second": 25.492,
82
+ "eval_steps_per_second": 12.77,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.02768439786434645,
87
+ "grad_norm": 1.5344593524932861,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 2.1545,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 3198189793443840.0,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null