Hugging Face's logo

shibajustfor
/
6e144f5a-a90b-4c83-a215-776d5f93ce10

PEFT
Safetensors
gemma2
axolotl
Generated from Trainer
Model card Files
xet
 Community
shibajustfor commited on
Commit
c8e06d9
·
verified ·
1 Parent(s): 72fed79

Training in progress, step 100, 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 +46 -3
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3b5f84bec3818f8479798d4bb33c499d1b1b7a1c2a477b86a5af39e53fe00038
3
  size 108113968
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:289e32236655fc4bca30f2d52cd58d22e2ff1a45ed62126779a824dc67e8f512
3
  size 108113968
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e30fc6f335b6330cebf14baf4714c2bfb9a4704c0dbf2bf7787a8a705193267f
3
  size 55549892
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:219d3eff955c6afa4d0d39f1ce8af3f8174f491576ba0bc4cea030307728a4c9
3
  size 55549892
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:14b36e35eb870dd80b115b52726492467b9515a96a3c88450b30e085f621f623
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:29a9774053c8dab88194dff5bf837d20f8496859adb946d9d42d2f3a497c9e15
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9b80fcc7599efca0c6313d990c467c2eb3001742b23ddaadc22e3499c12cea79
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:81007ec48272bbdc4f9622c046f9c026bf8120ed11d1398fd97bb5168a6f3dda
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": 0.0028107652308340947,
5
  "eval_steps": 50,
6
- "global_step": 50,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -58,6 +58,49 @@
58
  "eval_samples_per_second": 12.3,
59
  "eval_steps_per_second": 6.15,
60
  "step": 50
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
61
  }
62
  ],
63
  "logging_steps": 10,
@@ -77,7 +120,7 @@
77
  "attributes": {}
78
  }
79
  },
80
- "total_flos": 1.6573078459908096e+16,
81
  "train_batch_size": 2,
82
  "trial_name": null,
83
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.005621530461668189,
5
  "eval_steps": 50,
6
+ "global_step": 100,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
58
  "eval_samples_per_second": 12.3,
59
  "eval_steps_per_second": 6.15,
60
  "step": 50
61
+ },
62
+ {
63
+ "epoch": 0.0033729182770009134,
64
+ "grad_norm": 0.4097980260848999,
65
+ "learning_rate": 0.0002,
66
+ "loss": 0.3564,
67
+ "step": 60
68
+ },
69
+ {
70
+ "epoch": 0.003935071323167732,
71
+ "grad_norm": 0.3512555956840515,
72
+ "learning_rate": 0.0002,
73
+ "loss": 0.3117,
74
+ "step": 70
75
+ },
76
+ {
77
+ "epoch": 0.004497224369334551,
78
+ "grad_norm": 0.43151453137397766,
79
+ "learning_rate": 0.0002,
80
+ "loss": 0.3573,
81
+ "step": 80
82
+ },
83
+ {
84
+ "epoch": 0.005059377415501371,
85
+ "grad_norm": 0.6613090634346008,
86
+ "learning_rate": 0.0002,
87
+ "loss": 0.3253,
88
+ "step": 90
89
+ },
90
+ {
91
+ "epoch": 0.005621530461668189,
92
+ "grad_norm": 0.3564847409725189,
93
+ "learning_rate": 0.0002,
94
+ "loss": 0.3236,
95
+ "step": 100
96
+ },
97
+ {
98
+ "epoch": 0.005621530461668189,
99
+ "eval_loss": 0.32292038202285767,
100
+ "eval_runtime": 609.3281,
101
+ "eval_samples_per_second": 12.292,
102
+ "eval_steps_per_second": 6.146,
103
+ "step": 100
104
  }
105
  ],
106
  "logging_steps": 10,
 
120
  "attributes": {}
121
  }
122
  },
123
+ "total_flos": 3.417235372847923e+16,
124
  "train_batch_size": 2,
125
  "trial_name": null,
126
  "trial_params": null