Hugging Face's logo

kk-aivio
/
11a07901-ea1a-4036-998d-608e5791c6d4

PEFT
Safetensors
opt
axolotl
Generated from Trainer
Model card Files
xet
 Community
kk-aivio commited on
Commit
381a8de
·
verified ·
1 Parent(s): 9ce0a7f

Training in progress, step 9, 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 +32 -3
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:770e160c0f6cf97eb2855f08148d890cdd7b84dee215c45d7abc0a3357980540
3
  size 28351000
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d686d7ded8061eabf68a22100342842380d4fac7f338af463bbbeff0e370e4ff
3
  size 28351000
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:673891495dd33c6246d3f294eac2b937fbea14cdc928ae9d031cf415c7bdd9a8
3
  size 14714068
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:facabf3f281148e7a01d57977eaed33dab129769b983c632afe3740c75871147
3
  size 14714068
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2c691ba8c9e14eb426e9b91a3e15b2f9825a24a14b7fa50f4dac31112c5ecba5
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eae60c9c2f6d1190ef8b16afe4882d8f11e0e03aaa1c8e15cad0e9e262f90ae7
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c8e6b04902f17ae368c3e6cfd97a31ad4de2f025d673daea8c033ce0e260946
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": 0.0051557465091299675,
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,
@@ -73,6 +73,35 @@
73
  "eval_samples_per_second": 62.836,
74
  "eval_steps_per_second": 31.418,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 328642206892032.0,
96
  "train_batch_size": 2,
97
  "trial_name": null,
98
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.007733619763694952,
5
  "eval_steps": 3,
6
+ "global_step": 9,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
73
  "eval_samples_per_second": 62.836,
74
  "eval_steps_per_second": 31.418,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.006015037593984963,
79
+ "grad_norm": 2.392770290374756,
80
+ "learning_rate": 0.00014,
81
+ "loss": 11.1243,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.006874328678839957,
86
+ "grad_norm": 2.50643253326416,
87
+ "learning_rate": 0.00016,
88
+ "loss": 10.2998,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.007733619763694952,
93
+ "grad_norm": 2.93513560295105,
94
+ "learning_rate": 0.00018,
95
+ "loss": 10.8094,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.007733619763694952,
100
+ "eval_loss": 2.5549163818359375,
101
+ "eval_runtime": 7.8907,
102
+ "eval_samples_per_second": 62.098,
103
+ "eval_steps_per_second": 31.049,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 492963310338048.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null