Hugging Face's logo

phungkhaccuong
/
8cd00615-057a-fa67-f8a9-b1c3c039a3c5

PEFT
Safetensors
gemma
axolotl
Generated from Trainer
Model card Files
xet
 Community
phungkhaccuong commited on
Commit
ca7d0a4
·
verified ·
1 Parent(s): 7d1e2b2

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:d0a6aa2909d14805a89dcc9aee4a50d6e28f958c4aec7f490b802c49bad68e9c
3
  size 100059752
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db18ca8418720971736c04784ce38e6f752b8b53986a4459ad9805cc6bef0811
3
  size 100059752
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:599cb1b8ec0bd9a297aedd13f10cb0587a92689123616fcdf61ef7028edc1b04
3
  size 51244020
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7725667e0b07becebe776947bb7d45e438483c25601c408539c35f64becb9e0a
3
  size 51244020
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a962ccec4a7478dd110cad8a060cc16f6a10859a7addf02bc167a85c5f525a81
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:59e70a1ab574f2f66c8b552d206786c4ce00824febf2b699ffd62701ef545cd7
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": 0.0010612028325952532,
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": 1.69,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 5542165107179520.0,
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": 0.0015918042488928797,
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": 1.69,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.0012244648068406767,
72
+ "grad_norm": 1.4648447036743164,
73
+ "learning_rate": 5e-05,
74
+ "loss": 1.753,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.0012244648068406767,
79
+ "eval_loss": 1.6742535829544067,
80
+ "eval_runtime": 1495.9089,
81
+ "eval_samples_per_second": 6.896,
82
+ "eval_steps_per_second": 3.448,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.0014285422746474561,
87
+ "grad_norm": 1.519839882850647,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 1.5664,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 8122138519142400.0,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null