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
51e0f39
·
verified ·
1 Parent(s): 0189a0f

Training in progress, step 50, 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 -4
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e6aae9d354355451f75d6420c0afdf175c5f046c1f9fac675cfcdcbcabafca69
3
  size 28348936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6848e5c3ea4f35c9df12864e594f1f5b936b65625e5ef52dee5b5ce5b62f602d
3
  size 28348936
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f903ac3cec50be540a455273e72f2e052fd541a8100108a7bc8d68312664cde8
3
  size 14714068
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:70ee5ef0f5768aa9bd93c29d10722f458c38da44a31ec8f1974bfeb4913905dd
3
  size 14714068
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4ad26bffec2ad0f7489f7afdbb49922181fbd272c18243d0354e2f002e093aee
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:04bedbe5267f09e4e5d77875713d66b9ec32274917ea21af9ab2f163db830207
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e2ff6f184064d83b8d06f27cab522b7fa1e27d3258094d54e6a8c251936b5ccb
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b80fcc7599efca0c6313d990c467c2eb3001742b23ddaadc22e3499c12cea79
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": 0.00126432496393432,
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,
@@ -60,6 +60,20 @@
60
  "eval_samples_per_second": 62.753,
61
  "eval_steps_per_second": 31.377,
62
  "step": 39
 
 
 
 
 
 
 
 
 
 
 
 
 
 
63
  }
64
  ],
65
  "logging_steps": 10,
@@ -74,12 +88,12 @@
74
  "should_evaluate": false,
75
  "should_log": false,
76
  "should_save": true,
77
- "should_training_stop": false
78
  },
79
  "attributes": {}
80
  }
81
  },
82
- "total_flos": 1484696705826816.0,
83
  "train_batch_size": 2,
84
  "trial_name": null,
85
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.0016209294409414358,
5
  "eval_steps": 13,
6
+ "global_step": 50,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
60
  "eval_samples_per_second": 62.753,
61
  "eval_steps_per_second": 31.377,
62
  "step": 39
63
+ },
64
+ {
65
+ "epoch": 0.0012967435527531487,
66
+ "grad_norm": 0.8452262878417969,
67
+ "learning_rate": 0.0002,
68
+ "loss": 1.5871,
69
+ "step": 40
70
+ },
71
+ {
72
+ "epoch": 0.0016209294409414358,
73
+ "grad_norm": 0.884437620639801,
74
+ "learning_rate": 0.0002,
75
+ "loss": 1.7649,
76
+ "step": 50
77
  }
78
  ],
79
  "logging_steps": 10,
 
88
  "should_evaluate": false,
89
  "should_log": false,
90
  "should_save": true,
91
+ "should_training_stop": true
92
  },
93
  "attributes": {}
94
  }
95
  },
96
+ "total_flos": 1906577736990720.0,
97
  "train_batch_size": 2,
98
  "trial_name": null,
99
  "trial_params": null