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
234efb1
·
verified ·
1 Parent(s): 8603f37

Training in progress, step 150, 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:e6558ace36b0b9f74e22d004e771a497c6df1437a4e788813faf08ce0d9831a6
3
  size 2436967616
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b7e1de38e89ac278b8b93370900b4e18a340f533a2c58aae280e5c32ed4ce52f
3
  size 2436967616
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:33513acdb2b1874b6f1904ab5882fac8851b029a1768fe65f24ccb44c7b0d8f9
3
  size 170920084
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d25a5ec3edde16df921f1f65067b56797bb9c4f8b23f13a47bee46b4d14e2c9
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:a83c079a426c7cbe23d834eb7d1da47b6fac3a5e885e37dea71be4556f69dbff
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb7f11ef25ceb08ba875f4f3f38e40c6a98700a002151fbe5db7a6a9412bf9f5
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fa172a67b17733f4f4576524fa7afa573b19fcbf0bf4ea9f180757ed71fc81e7
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:321052ad5e93c8a107bd6c10f372f50285d863120fc0088befc39ec2733238fb
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 1.608966588973999,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.006165703275529865,
5
  "eval_steps": 50,
6
- "global_step": 100,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -45,6 +45,21 @@
45
  "eval_samples_per_second": 13.115,
46
  "eval_steps_per_second": 6.557,
47
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
48
  }
49
  ],
50
  "logging_steps": 40,
@@ -73,7 +88,7 @@
73
  "attributes": {}
74
  }
75
  },
76
- "total_flos": 4.098397133655245e+16,
77
  "train_batch_size": 2,
78
  "trial_name": null,
79
  "trial_params": null
 
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,
 
45
  "eval_samples_per_second": 13.115,
46
  "eval_steps_per_second": 6.557,
47
  "step": 100
48
+ },
49
+ {
50
+ "epoch": 0.007398843930635838,
51
+ "grad_norm": 0.9106088876724243,
52
+ "learning_rate": 9.619397662556435e-05,
53
+ "loss": 1.5941,
54
+ "step": 120
55
+ },
56
+ {
57
+ "epoch": 0.009248554913294798,
58
+ "eval_loss": 1.6026890277862549,
59
+ "eval_runtime": 1041.2784,
60
+ "eval_samples_per_second": 13.117,
61
+ "eval_steps_per_second": 6.558,
62
+ "step": 150
63
  }
64
  ],
65
  "logging_steps": 40,
 
88
  "attributes": {}
89
  }
90
  },
91
+ "total_flos": 6.168577255774618e+16,
92
  "train_batch_size": 2,
93
  "trial_name": null,
94
  "trial_params": null