Hugging Face's logo

shibajustfor
/
f6b703e6-c965-442e-ae76-e65988983673

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files
xet
 Community
shibajustfor commited on
Commit
bd2ac22
·
verified ·
1 Parent(s): 2fcb22d

Training in progress, step 50, 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 +18 -4
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ff5ca9e238e48d8767635f64ec528bd36b42d43272bb9859fec14b3c29929a90
3
  size 80013120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f6e1c75bbf5f04c9b7e4455dd12a87e04282add9152e3fc2292be4514922ead
3
  size 80013120
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:744c0841e14417a8fd1c6bc354aee8929792b3dc85393104e03415b6d46c7ac9
3
  size 41119636
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b18efdc05522d301ed6f4c9c6d22496167e0a30cb7470aade2e2adbfcb23f69b
3
  size 41119636
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f6772af577974c8afd4f01c292dee37aefb71155f4658c2cd442b9995c16c293
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f193d721d2c78b566d69bf5206148a72d855b794e4169c7dc96a973de157ed62
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e2ff6f184064d83b8d06f27cab522b7fa1e27d3258094d54e6a8c251936b5ccb
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b80fcc7599efca0c6313d990c467c2eb3001742b23ddaadc22e3499c12cea79
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": 0.0161976949434119,
5
  "eval_steps": 13,
6
- "global_step": 39,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -60,6 +60,20 @@
60
  "eval_samples_per_second": 17.73,
61
  "eval_steps_per_second": 8.865,
62
  "step": 39
 
 
 
 
 
 
 
 
 
 
 
 
 
 
63
  }
64
  ],
65
  "logging_steps": 10,
@@ -74,12 +88,12 @@
74
  "should_evaluate": false,
75
  "should_log": false,
76
  "should_save": true,
77
- "should_training_stop": false
78
  },
79
  "attributes": {}
80
  }
81
  },
82
- "total_flos": 1.285301880225792e+16,
83
  "train_batch_size": 2,
84
  "trial_name": null,
85
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.020766275568476794,
5
  "eval_steps": 13,
6
+ "global_step": 50,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
60
  "eval_samples_per_second": 17.73,
61
  "eval_steps_per_second": 8.865,
62
  "step": 39
63
+ },
64
+ {
65
+ "epoch": 0.016613020454781434,
66
+ "grad_norm": 0.2721776068210602,
67
+ "learning_rate": 0.0002,
68
+ "loss": 0.549,
69
+ "step": 40
70
+ },
71
+ {
72
+ "epoch": 0.020766275568476794,
73
+ "grad_norm": 0.2938651144504547,
74
+ "learning_rate": 0.0002,
75
+ "loss": 0.5445,
76
+ "step": 50
77
  }
78
  ],
79
  "logging_steps": 10,
 
88
  "should_evaluate": false,
89
  "should_log": false,
90
  "should_save": true,
91
+ "should_training_stop": true
92
  },
93
  "attributes": {}
94
  }
95
  },
96
+ "total_flos": 1.6478229233664e+16,
97
  "train_batch_size": 2,
98
  "trial_name": null,
99
  "trial_params": null