Hugging Face's logo

goodlucky55555
/
6b8eef8b-003c-46d0-b15d-8334743a0d3f

PEFT
Safetensors
gemma
axolotl
Generated from Trainer
Model card Files
xet
 Community
Jackson Brune commited on
Commit
5d33dae
·
verified ·
1 Parent(s): 0a73915

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:b3e799fd566d5f88413c154e53db8f93a514336e28c40e6500dfcf0cb3e452a2
3
  size 39256456
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d1f4cd0d60a34fb3d858ad55bbd442ef8206be37762e855aade1db327e3e368b
3
  size 39256456
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fbf3715d180a84dc63bd7358c0f9567b6f89b30bf25d7390b750ee8efb3f98ba
3
  size 20632826
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:07598308c409a46c607a988ded89138af7b61359a3cfd2152f01b4297df0e923
3
  size 20632826
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:226550a406f12fab82f42e8c68b1d63060de0707c1f4b074da1ff9c052cad913
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a370f52f54bb4463c4209c15daab3dd20378accbb5e4647216ed4871ac540c8
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": 0.00511727078891258,
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": 51.739,
103
  "eval_steps_per_second": 25.904,
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": 477240848547840.0,
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": 0.005685856432125089,
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": 51.739,
103
  "eval_steps_per_second": 25.904,
104
  "step": 9
105
+ },
106
+ {
107
+ "epoch": 0.005685856432125089,
108
+ "grad_norm": 1.601119875907898,
109
+ "learning_rate": 0.0002,
110
+ "loss": 2.8724,
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": 526188627886080.0,
132
  "train_batch_size": 2,
133
  "trial_name": null,
134
  "trial_params": null