Hugging Face's logo

VERSIL91
/
54cbd832-1094-46c2-8fd7-d49114a7eace

PEFT
Safetensors
qwen2
axolotl
Generated from Trainer
Model card Files
xet
 Community
VERSIL91 commited on
Commit
524d171
·
verified ·
1 Parent(s): 438afe0

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 sha256:26da9eadadd2b009bf8a160d1134bb194706cd9cf577d66b851f5dc927934ba2
3
  size 124756544
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb94d798f5f6847f6abac3bcc6664175498cef68cd1f90b21d6ff8604abcc92f
3
  size 124756544
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3441eec024dc028bf146b00bdad88bae86f040332c0e0584f20658142f678a4d
3
  size 63958740
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:697e4a075e2013de3178ff979b21b054fd62c207339e24cceced351c7fd07bf1
3
  size 63958740
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b8d6b9a0e9e9502751def1097143074ef257eab24506a0f12d159e188fa21987
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:572c5653b97399d6dc550389d4e48df5479adab7c80147f357d4d04c0f7252da
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": 0.02960222016651249,
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": 13.434,
60
  "eval_steps_per_second": 6.717,
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": 1.055383388946432e+16,
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": 0.03700277520814061,
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": 13.434,
60
  "eval_steps_per_second": 6.717,
61
  "step": 4
62
+ },
63
+ {
64
+ "epoch": 0.03700277520814061,
65
+ "grad_norm": 2.2471249103546143,
66
+ "learning_rate": 5e-05,
67
+ "loss": 2.661,
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": 1.31922923618304e+16,
89
  "train_batch_size": 2,
90
  "trial_name": null,
91
  "trial_params": null