Hugging Face's logo

tuantmdev
/
6860d41c-54b0-429a-b48d-4e896b5c9961

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files
xet
 Community
tuantmdev commited on
Commit
a9117db
·
verified ·
1 Parent(s): 2e0e265

Training in progress, step 200, 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 +27 -5
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b7e1de38e89ac278b8b93370900b4e18a340f533a2c58aae280e5c32ed4ce52f
3
  size 2436967616
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9411c13b8340cb573e4f03480b8ae8600706fcbf0e9b7a981f763710598b70f8
3
  size 2436967616
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7d25a5ec3edde16df921f1f65067b56797bb9c4f8b23f13a47bee46b4d14e2c9
3
  size 170920084
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c07b8fac7eaebb4fb32c529dbce0d39fc754bb7c5c2185d77d75a01788ca9fea
3
  size 170920084
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fb7f11ef25ceb08ba875f4f3f38e40c6a98700a002151fbe5db7a6a9412bf9f5
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:868ad821951f198e38403ecb90036cf96fbc8ba00e7c8556addc73d912461b9a
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:321052ad5e93c8a107bd6c10f372f50285d863120fc0088befc39ec2733238fb
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:530505d607699f384741067a5f9139d72f043713adb680898a3f1b5714170c97
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 1.6026890277862549,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
- "epoch": 0.009248554913294798,
5
  "eval_steps": 50,
6
- "global_step": 150,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -60,6 +60,28 @@
60
  "eval_samples_per_second": 13.117,
61
  "eval_steps_per_second": 6.558,
62
  "step": 150
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
63
  }
64
  ],
65
  "logging_steps": 40,
@@ -88,7 +110,7 @@
88
  "attributes": {}
89
  }
90
  },
91
- "total_flos": 6.168577255774618e+16,
92
  "train_batch_size": 2,
93
  "trial_name": null,
94
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.5895808935165405,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-200",
4
+ "epoch": 0.01233140655105973,
5
  "eval_steps": 50,
6
+ "global_step": 200,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
60
  "eval_samples_per_second": 13.117,
61
  "eval_steps_per_second": 6.558,
62
  "step": 150
63
+ },
64
+ {
65
+ "epoch": 0.009865125240847785,
66
+ "grad_norm": 1.0939823389053345,
67
+ "learning_rate": 8.535533905932738e-05,
68
+ "loss": 1.6436,
69
+ "step": 160
70
+ },
71
+ {
72
+ "epoch": 0.01233140655105973,
73
+ "grad_norm": 1.1950139999389648,
74
+ "learning_rate": 6.91341716182545e-05,
75
+ "loss": 1.5907,
76
+ "step": 200
77
+ },
78
+ {
79
+ "epoch": 0.01233140655105973,
80
+ "eval_loss": 1.5895808935165405,
81
+ "eval_runtime": 1041.3859,
82
+ "eval_samples_per_second": 13.115,
83
+ "eval_steps_per_second": 6.558,
84
+ "step": 200
85
  }
86
  ],
87
  "logging_steps": 40,
 
110
  "attributes": {}
111
  }
112
  },
113
+ "total_flos": 8.206119402995712e+16,
114
  "train_batch_size": 2,
115
  "trial_name": null,
116
  "trial_params": null