Hugging Face's logo

shibajustfor
/
97e6c917-e820-40ce-af2e-b33a1b676b69

PEFT
Safetensors
phi
axolotl
Generated from Trainer
Model card Files
xet
 Community
shibajustfor commited on
Commit
4bd3b7f
·
verified ·
1 Parent(s): 7143942

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 +18 -3
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:296d1ce0bdac91b01808b6e68b9b4db5c7b8d2b951c380871df403de93f71fa1
3
  size 28348936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e6aae9d354355451f75d6420c0afdf175c5f046c1f9fac675cfcdcbcabafca69
3
  size 28348936
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8212b298b902642b8ca9d37efb24944c9c4f59f176e6d245b4789c245e2a1dc9
3
  size 14714068
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f903ac3cec50be540a455273e72f2e052fd541a8100108a7bc8d68312664cde8
3
  size 14714068
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d15c3bb90b41674f21ec28697ea2747023849bd9a97745d5691de1ce052b10a8
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ad26bffec2ad0f7489f7afdbb49922181fbd272c18243d0354e2f002e093aee
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:562360b448a53e7366b8643d15ad250a0f706aaefd28e30d76b7f5f4480c7196
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e2ff6f184064d83b8d06f27cab522b7fa1e27d3258094d54e6a8c251936b5ccb
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": 0.0008428833092895467,
5
  "eval_steps": 13,
6
- "global_step": 26,
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": 62.718,
46
  "eval_steps_per_second": 31.359,
47
  "step": 26
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
48
  }
49
  ],
50
  "logging_steps": 10,
@@ -64,7 +79,7 @@
64
  "attributes": {}
65
  }
66
  },
67
- "total_flos": 973571610378240.0,
68
  "train_batch_size": 2,
69
  "trial_name": null,
70
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.00126432496393432,
5
  "eval_steps": 13,
6
+ "global_step": 39,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
45
  "eval_samples_per_second": 62.718,
46
  "eval_steps_per_second": 31.359,
47
  "step": 26
48
+ },
49
+ {
50
+ "epoch": 0.0009725576645648615,
51
+ "grad_norm": 0.9726564884185791,
52
+ "learning_rate": 0.0002,
53
+ "loss": 1.7184,
54
+ "step": 30
55
+ },
56
+ {
57
+ "epoch": 0.00126432496393432,
58
+ "eval_loss": 1.7781810760498047,
59
+ "eval_runtime": 206.9688,
60
+ "eval_samples_per_second": 62.753,
61
+ "eval_steps_per_second": 31.377,
62
+ "step": 39
63
  }
64
  ],
65
  "logging_steps": 10,
 
79
  "attributes": {}
80
  }
81
  },
82
+ "total_flos": 1484696705826816.0,
83
  "train_batch_size": 2,
84
  "trial_name": null,
85
  "trial_params": null