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
76f30e8
·
verified ·
1 Parent(s): 85c0734

Training in progress, step 250, 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 +20 -5
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9411c13b8340cb573e4f03480b8ae8600706fcbf0e9b7a981f763710598b70f8
3
  size 2436967616
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b7ce9575af73f4c250802c095ca9e0a84a59961d961928e9285dd494381eb149
3
  size 2436967616
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c07b8fac7eaebb4fb32c529dbce0d39fc754bb7c5c2185d77d75a01788ca9fea
3
  size 170920084
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b6516bc4d8c6f54abe8b9f3b4597dea9ea861ad6cb711236d40fb7d5de34f868
3
  size 170920084
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:868ad821951f198e38403ecb90036cf96fbc8ba00e7c8556addc73d912461b9a
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c605e83c4f568f78dd8ddf3ee5cc46f84435323472643ef3617eec247c6b6371
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:530505d607699f384741067a5f9139d72f043713adb680898a3f1b5714170c97
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5182c64d745614fbc9217a3122cffdaa4b9683ea7cfb2e6909f3ad8f175d0a03
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
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,
@@ -82,6 +82,21 @@
82
  "eval_samples_per_second": 13.115,
83
  "eval_steps_per_second": 6.558,
84
  "step": 200
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
85
  }
86
  ],
87
  "logging_steps": 40,
@@ -110,7 +125,7 @@
110
  "attributes": {}
111
  }
112
  },
113
- "total_flos": 8.206119402995712e+16,
114
  "train_batch_size": 2,
115
  "trial_name": null,
116
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.5806567668914795,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-250",
4
+ "epoch": 0.015414258188824663,
5
  "eval_steps": 50,
6
+ "global_step": 250,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
82
  "eval_samples_per_second": 13.115,
83
  "eval_steps_per_second": 6.558,
84
  "step": 200
85
+ },
86
+ {
87
+ "epoch": 0.014797687861271676,
88
+ "grad_norm": 0.8904630541801453,
89
+ "learning_rate": 5e-05,
90
+ "loss": 1.587,
91
+ "step": 240
92
+ },
93
+ {
94
+ "epoch": 0.015414258188824663,
95
+ "eval_loss": 1.5806567668914795,
96
+ "eval_runtime": 1041.1372,
97
+ "eval_samples_per_second": 13.118,
98
+ "eval_steps_per_second": 6.559,
99
+ "step": 250
100
  }
101
  ],
102
  "logging_steps": 40,
 
125
  "attributes": {}
126
  }
127
  },
128
+ "total_flos": 1.0252986685902029e+17,
129
  "train_batch_size": 2,
130
  "trial_name": null,
131
  "trial_params": null