Hugging Face's logo

Paladiso
/
56e46106-55ee-42fc-b514-64b2448c7b69

PEFT
Safetensors
qwen2
axolotl
Generated from Trainer
Model card Files
xet
 Community
1
Paladiso commited on
Commit
bb52bb8
·
verified ·
1 Parent(s): e741528

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 sha256:390a101b182cb73ae204abe265d9806d02b9d0906f549f8c86968eb3855f701b
3
  size 59933632
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71d82d5c0db8c127d042b8a659783e1d36ddda940b53e132f7e2499395a360f8
3
  size 59933632
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a0a83f8b8eb6cee4dc763f570d495f60ec5f6e39a1b669870b84f047bc72b5cc
3
  size 31822948
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b54b70a6e857ea504a2dd14b1bd11085cdd4f9daa7d547b76dbbb71c2e6273e
3
  size 31822948
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:439abbe02fcba947df87386a52c344ddf41c37c93f11c43daac794f1cc139033
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a9c5a89d9a821f07580c81d14535c1b5623f00f05fbc722629e15cc666fbae9
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": 0.0002820299891888504,
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": 14.592,
95
  "eval_steps_per_second": 7.297,
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": 617045972484096.0,
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": 0.00031336665465427825,
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": 14.592,
95
  "eval_steps_per_second": 7.297,
96
  "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.00031336665465427825,
100
+ "grad_norm": 1.6040438413619995,
101
+ "learning_rate": 0.0002,
102
+ "loss": 1.4018,
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": 685606636093440.0,
124
  "train_batch_size": 2,
125
  "trial_name": null,
126
  "trial_params": null