Hugging Face's logo

VERSIL91
/
447856cb-1938-43c1-9804-902eea88a1b4

PEFT
Safetensors
qwen2
axolotl
Generated from Trainer
Model card Files
xet
 Community
VERSIL91 commited on
Commit
45c5945
·
verified ·
1 Parent(s): 92d8da5

Training in progress, step 5, 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 sha256:8012e2215905e3e0cdd2d36c7fa30d94287537aa7c5708f4ba65df3b0f318e80
3
  size 14696
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd56e2752b641de10f9a31660ff740c7baf7bf14f683de694e876f38bc96f222
3
  size 14696
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5bf9b380df4a08cfe05d74ee2da15e227811a530f19515270e9df8a1db08b6fc
3
  size 39398
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:053964752a9fe138a1ae5617a32864618dd1812de56413eb875c359221d078ed
3
  size 39398
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:017583d2bd93fe9910a82ceabe249f8fabc7dfeef29c7c3f997a8f45e0fab04d
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a8636caf43895d122986dcf9c0f3f784244e32146c2903687980280124315561
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c7adb031dc938779259a07e684ea318126e92e52b40c256b93ef474d2ac57a5b
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d63217b923cb177f669d6bc2174b89abdc6a56d968d279b505491b37976d9bb
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": 0.044630404463040445,
5
  "eval_steps": 2,
6
- "global_step": 4,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -59,6 +59,13 @@
59
  "eval_samples_per_second": 446.163,
60
  "eval_steps_per_second": 224.559,
61
  "step": 4
 
 
 
 
 
 
 
62
  }
63
  ],
64
  "logging_steps": 1,
@@ -73,12 +80,12 @@
73
  "should_evaluate": false,
74
  "should_log": false,
75
  "should_save": true,
76
- "should_training_stop": false
77
  },
78
  "attributes": {}
79
  }
80
  },
81
- "total_flos": 1920122880.0,
82
  "train_batch_size": 2,
83
  "trial_name": null,
84
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.05578800557880056,
5
  "eval_steps": 2,
6
+ "global_step": 5,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
59
  "eval_samples_per_second": 446.163,
60
  "eval_steps_per_second": 224.559,
61
  "step": 4
62
+ },
63
+ {
64
+ "epoch": 0.05578800557880056,
65
+ "grad_norm": 0.004226147197186947,
66
+ "learning_rate": 5e-05,
67
+ "loss": 11.9323,
68
+ "step": 5
69
  }
70
  ],
71
  "logging_steps": 1,
 
80
  "should_evaluate": false,
81
  "should_log": false,
82
  "should_save": true,
83
+ "should_training_stop": true
84
  },
85
  "attributes": {}
86
  }
87
  },
88
+ "total_flos": 2422308864.0,
89
  "train_batch_size": 2,
90
  "trial_name": null,
91
  "trial_params": null