Hugging Face's logo

cwaud
/
29a9a50b-b225-4aac-afd7-8d1228fe1ff4

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files
xet
 Community
cwaud commited on
Commit
1dc9468
·
verified ·
1 Parent(s): abb52d6

Training in progress, step 6, checkpoint

Browse files
Files changed (4) hide show
  1. last-checkpoint/optimizer.pt +1 -1
  2. last-checkpoint/rng_state.pth +1 -1
  3. last-checkpoint/scheduler.pt +1 -1
  4. last-checkpoint/trainer_state.json +32 -3
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5cbb206d2bd5dc2059b0f2b3b4dc9eb31e1ccf942a024794b9f43d90c2190467
3
  size 43122580
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8c9c750dc3f88bb3640705e7f35ef7c14563a8cf585855709ba483e025a3c7b
3
  size 43122580
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d261144361ea855362212b7f0dabe43e1421a9588798268bc613afe8fd7dd4d0
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b2fe91e4b71ad96971401f0069a1c0bd726c6e3d3f180c7c5724b4adc2dcccdc
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ffd8c58e5d02492554dbaa495f8cf80dff41fabc0e1288cb2fd18a103d402219
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
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": 0.0002729630135116692,
5
  "eval_steps": 3,
6
- "global_step": 3,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -44,6 +44,35 @@
44
  "eval_samples_per_second": 15.449,
45
  "eval_steps_per_second": 7.725,
46
  "step": 3
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
47
  }
48
  ],
49
  "logging_steps": 1,
@@ -63,7 +92,7 @@
63
  "attributes": {}
64
  }
65
  },
66
- "total_flos": 554869274443776.0,
67
  "train_batch_size": 2,
68
  "trial_name": null,
69
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.0005459260270233384,
5
  "eval_steps": 3,
6
+ "global_step": 6,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
44
  "eval_samples_per_second": 15.449,
45
  "eval_steps_per_second": 7.725,
46
  "step": 3
47
+ },
48
+ {
49
+ "epoch": 0.00036395068468222556,
50
+ "grad_norm": NaN,
51
+ "learning_rate": 8e-05,
52
+ "loss": 0.0,
53
+ "step": 4
54
+ },
55
+ {
56
+ "epoch": 0.000454938355852782,
57
+ "grad_norm": NaN,
58
+ "learning_rate": 0.0001,
59
+ "loss": 0.0,
60
+ "step": 5
61
+ },
62
+ {
63
+ "epoch": 0.0005459260270233384,
64
+ "grad_norm": NaN,
65
+ "learning_rate": 0.00012,
66
+ "loss": 0.0,
67
+ "step": 6
68
+ },
69
+ {
70
+ "epoch": 0.0005459260270233384,
71
+ "eval_loss": NaN,
72
+ "eval_runtime": 299.561,
73
+ "eval_samples_per_second": 15.449,
74
+ "eval_steps_per_second": 7.725,
75
+ "step": 6
76
  }
77
  ],
78
  "logging_steps": 1,
 
92
  "attributes": {}
93
  }
94
  },
95
+ "total_flos": 1109738548887552.0,
96
  "train_batch_size": 2,
97
  "trial_name": null,
98
  "trial_params": null