Hugging Face's logo

Paladiso
/
369db93c-b0b2-4862-895e-e55b2f44da91

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files
xet
 Community
Paladiso commited on
Commit
28a63c9
·
verified ·
1 Parent(s): 7d62ddc

Training in progress, step 10, 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 +11 -4
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:18e27618344496386298db34e3c2638fd1d4f66033166517fb486be60b60c765
3
  size 50899792
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3be9ed06bd2faf3d941dd8e2c08c8d6ddbb048bf31f5565c217c1edefa5aea31
3
  size 50899792
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a62c9bd537a7cb8593d15376190a618373130323518fe3524a0ccdabf5192426
3
  size 26231300
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aad983915af07282ec1dd45cf4ca883699361aa9ab653c1c571b42de8391e068
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:a52de475c9ee7fccf32a03e0dd53231b1635475fc4aa087879ca1708e4c7b973
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd572261287b2f73eccfee7322d6dec64e1d1495a088c46e32ce98012b3970cd
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9c8e6b04902f17ae368c3e6cfd97a31ad4de2f025d673daea8c033ce0e260946
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
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": 0.008988764044943821,
5
  "eval_steps": 3,
6
- "global_step": 9,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -94,6 +94,13 @@
94
  "eval_samples_per_second": 19.16,
95
  "eval_steps_per_second": 9.58,
96
  "step": 9
 
 
 
 
 
 
 
97
  }
98
  ],
99
  "logging_steps": 1,
@@ -108,12 +115,12 @@
108
  "should_evaluate": false,
109
  "should_log": false,
110
  "should_save": true,
111
- "should_training_stop": false
112
  },
113
  "attributes": {}
114
  }
115
  },
116
- "total_flos": 738043798487040.0,
117
  "train_batch_size": 2,
118
  "trial_name": null,
119
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.009987515605493134,
5
  "eval_steps": 3,
6
+ "global_step": 10,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
94
  "eval_samples_per_second": 19.16,
95
  "eval_steps_per_second": 9.58,
96
  "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.009987515605493134,
100
+ "grad_norm": 0.5323424339294434,
101
+ "learning_rate": 0.0002,
102
+ "loss": 0.7955,
103
+ "step": 10
104
  }
105
  ],
106
  "logging_steps": 1,
 
115
  "should_evaluate": false,
116
  "should_log": false,
117
  "should_save": true,
118
+ "should_training_stop": true
119
  },
120
  "attributes": {}
121
  }
122
  },
123
+ "total_flos": 820048664985600.0,
124
  "train_batch_size": 2,
125
  "trial_name": null,
126
  "trial_params": null