Hugging Face's logo

havinash-ai
/
f2cda622-9570-4e02-99c5-cce2f96c45a8

PEFT
Safetensors
opt
axolotl
Generated from Trainer
Model card Files
xet
 Community
havinash-ai commited on
Commit
fb79b62
·
verified ·
1 Parent(s): 1f55446

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 sha256:17ebc2bbe593a3700786b8b8753bca09f11f7d0273e525f06569f0129ddf53ea
3
  size 28351000
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c9889a5716a2e9d3fca05389d119fcf1ae28a2ae6626e49d35cec22cb1cc15ad
3
  size 28351000
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:00aed5b101ef60fe18fb2e863c6049f3be27a5fb18fb28d88cd8815322025dce
3
  size 14714068
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e44ac6603a19f0b03d2a00bc13fc15a0cec54e8c643eacda252dd2cf1f0a3e58
3
  size 14714068
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d66f33b1e5b2c0ef27fc599d33982d25847a4ce9cf07845c46b50ef9632d1f27
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aea9f7dd5933a797009671ad3be72edbb764132812c859d1cf32f1a5ad2e397f
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": 0.004615384615384616,
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,
@@ -102,6 +102,13 @@
102
  "eval_samples_per_second": 67.659,
103
  "eval_steps_per_second": 33.83,
104
  "step": 9
 
 
 
 
 
 
 
105
  }
106
  ],
107
  "logging_steps": 1,
@@ -116,12 +123,12 @@
116
  "should_evaluate": false,
117
  "should_log": false,
118
  "should_save": true,
119
- "should_training_stop": false
120
  },
121
  "attributes": {}
122
  }
123
  },
124
- "total_flos": 268889078366208.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.005128205128205128,
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,
 
102
  "eval_samples_per_second": 67.659,
103
  "eval_steps_per_second": 33.83,
104
  "step": 9
105
+ },
106
+ {
107
+ "epoch": 0.005128205128205128,
108
+ "grad_norm": 43.22773361206055,
109
+ "learning_rate": 0.0002,
110
+ "loss": 18.0903,
111
+ "step": 10
112
  }
113
  ],
114
  "logging_steps": 1,
 
123
  "should_evaluate": false,
124
  "should_log": false,
125
  "should_save": true,
126
+ "should_training_stop": true
127
  },
128
  "attributes": {}
129
  }
130
  },
131
+ "total_flos": 298765642629120.0,
132
  "train_batch_size": 2,
133
  "trial_name": null,
134
  "trial_params": null