Hugging Face's logo

duyphu
/
64d858fd-0ea9-bb1f-71f7-76dcd02f019f

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files
xet
 Community
duyphu commited on
Commit
0ba89a2
·
verified ·
1 Parent(s): dc3a2ec

Training in progress, step 39, 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 +25 -3
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:aa77daec98f4682dae9feaf287ce29fd89b4a4e2c6c0db04e33afe6dbd7b186f
3
  size 390888
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:baaf0b9e6d8ed0255da26d8c188fa1e8e5754573b3d7b09e53e292cf32ba5782
3
  size 390888
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4ac35e10218eaa88185a04809740300cf5a43901badc4d4e11921777af837f86
3
  size 819770
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c5be03ff4903b649ea7323aeab6ec12a3b39304ce65baca04c25b557e4af8ee9
3
  size 819770
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:638f0e887c7eab30601fcd15f109e577ce9025b567cf9228ffde08282c0e880e
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bebbe731bd9094c7ae8f274487d73bb48b05017603343298a02474cb28c07b94
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:37841e69eda911caeb33edeefa0b2f140e72dcce247aeb757b2fe89c00d7887b
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c50dbaa792cda4a28fbbc2acb2a3e03c59530712bbc5107212d33064d193da4
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": 0.0405458089668616,
5
  "eval_steps": 10,
6
- "global_step": 26,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -66,6 +66,28 @@
66
  "learning_rate": 6.91341716182545e-05,
67
  "loss": 9.803,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 1704522153984.0,
89
  "train_batch_size": 2,
90
  "trial_name": null,
91
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.0608187134502924,
5
  "eval_steps": 10,
6
+ "global_step": 39,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
66
  "learning_rate": 6.91341716182545e-05,
67
  "loss": 9.803,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.04678362573099415,
72
+ "grad_norm": 2.2838778495788574,
73
+ "learning_rate": 5e-05,
74
+ "loss": 9.7681,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.04678362573099415,
79
+ "eval_loss": 9.785663604736328,
80
+ "eval_runtime": 3.4281,
81
+ "eval_samples_per_second": 78.762,
82
+ "eval_steps_per_second": 39.381,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.05458089668615984,
87
+ "grad_norm": 2.3065450191497803,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 9.7152,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 2556783230976.0,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null