Hugging Face's logo

Paladiso
/
66034ee5-a54d-46e2-b0b2-b10a4d504ab5

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files
xet
 Community
Paladiso commited on
Commit
3a0abd7
·
verified ·
1 Parent(s): b813bed

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:d9b84bd1c659c5694fcc29e0debdfbcd4e623d31b2bdc293d6cb2f1e5121ec4e
3
  size 80013120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5bd8230a4a8f05832a7d4af757a7bcbbd11a67fb8b581ae39c114edde3546c25
3
  size 80013120
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3aaf1f52b132bbeca51bdfebd85999c675a51d31a57bc152450ce9727f87d44b
3
  size 41119636
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3a3fdf5be4d9aa506acd4039b4ca78481824c70401201e58bc8dd803fb1776ab
3
  size 41119636
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3458ef221070e43be6819fab3eb9223117d998d6b0cefa947ed4db91a7800f93
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:93e973c8fed86e7d07567831fae3659eea18701a3d012d8cdbc38ac0b6e3c812
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": 0.09473684210526316,
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": 8.697,
95
  "eval_steps_per_second": 4.349,
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": 2646691345858560.0,
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": 0.10526315789473684,
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": 8.697,
95
  "eval_steps_per_second": 4.349,
96
  "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.10526315789473684,
100
+ "grad_norm": 0.4539870321750641,
101
+ "learning_rate": 0.0002,
102
+ "loss": 1.0458,
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": 2972437973041152.0,
124
  "train_batch_size": 2,
125
  "trial_name": null,
126
  "trial_params": null