Hugging Face's logo

shibajustfor
/
26f86435-80d4-4b02-8a0b-3ac4a0a12e77

PEFT
Safetensors
llama
axolotl
Generated from Trainer
custom_code
Model card Files
xet
 Community
shibajustfor commited on
Commit
ae6f29a
·
verified ·
1 Parent(s): 1af7693

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:aab475534594054b7880881cb6e8bb0392ac75bcdbcb1458f2073c0df889c59b
3
  size 125248064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c210092f43ac57bb58caa70d64bffd44a35374d683a1712c9defa32f48d60573
3
  size 125248064
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:211c1ab79f15151b1743c2ac8f4637b6028b040fdf1ca0bf28177fc696ef6413
3
  size 64219860
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27fc7849d106dc728666c9056a00de1803b268c2d93f99183d53c937e19e399e
3
  size 64219860
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c651bf64b4cf0c42768b53053f92a52cea854fba52b90f44368eeccad9ea661b
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:397aaff116845cf69708a752dc89b24fbc3f64391c5787cbb24bcd6eca647b0d
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:216e1a9a1c53e7de93f56319b4855910155cb98dd7ebb5fa08b3717fd303059f
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e69e2b49ea642509f0c688c16fb190b7cf27dac0a18903a5e2d1467d0343d8b8
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": 0.020838899278653487,
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": 11.025,
61
  "eval_steps_per_second": 5.513,
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": 2.469639254704128e+16,
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": 0.026716537536735238,
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": 11.025,
61
  "eval_steps_per_second": 5.513,
62
  "step": 39
63
+ },
64
+ {
65
+ "epoch": 0.02137323002938819,
66
+ "grad_norm": 3.065298557281494,
67
+ "learning_rate": 2.339555568810221e-05,
68
+ "loss": 2.5602,
69
+ "step": 40
70
+ },
71
+ {
72
+ "epoch": 0.026716537536735238,
73
+ "grad_norm": 3.171158790588379,
74
+ "learning_rate": 0.0,
75
+ "loss": 2.5977,
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": 3.1662041726976e+16,
97
  "train_batch_size": 2,
98
  "trial_name": null,
99
  "trial_params": null