Hugging Face's logo

kk-aivio
/
4f83fc75-c47b-4ffc-9c5d-992d2de52d08

PEFT
Safetensors
gemma2
axolotl
Generated from Trainer
Model card Files
xet
 Community
kk-aivio commited on
Commit
097df85
·
verified ·
1 Parent(s): dfa5457

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 sha256:57a0c6fd8dc84c1fdd77b45d53a458a0a001cb841405ad74427988a5a7c5412f
3
  size 41581360
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:141d1b2851898694632896521f3cd73be7f7ed2226cba2b2fdcbbd2035f3a9e3
3
  size 41581360
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:17e473a181024c9f7e0fa901f9d060151f91830408439984123e23c426a01d12
3
  size 21505540
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:267ca5698d48db8a2979382c9cec480d48900913a4e3f89f9e36a7e1fb5555d1
3
  size 21505540
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dc527ae92339ea167c2945496cfde8562215165c21050204ee36547f80f22391
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eab0aa09bbb2059eef409050846e568360b5b777e22dcbcc22066ef429c07f97
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": 0.00299028158484924,
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": 33.849,
103
  "eval_steps_per_second": 16.924,
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": 450087597637632.0,
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": 0.003322535094276933,
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": 33.849,
103
  "eval_steps_per_second": 16.924,
104
  "step": 9
105
+ },
106
+ {
107
+ "epoch": 0.003322535094276933,
108
+ "grad_norm": 1.028969407081604,
109
+ "learning_rate": 0.0002,
110
+ "loss": 0.9358,
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": 500097330708480.0,
132
  "train_batch_size": 2,
133
  "trial_name": null,
134
  "trial_params": null