Hugging Face's logo

cwaud
/
d8a5519b-748a-4954-a590-e63634d3bbb9

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files
xet
 Community
cwaud commited on
Commit
52063aa
·
verified ·
1 Parent(s): 45a29f6

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 sha256:7fc7260eb7fc6725fb62e83920267990871f2ce05a441d8b2032ec8a43f3cd05
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8802d01bdf21ebc1cd8876fdaedd328c72b557b0ab308e984b30099f97e0bdbe
3
  size 83945296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:65a7c5912b99141d1531d6fff3ac2800ace1c832a6c02a1966fd3bd92e1c2c04
3
  size 43122580
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c3e8bee9b091f27dca0874eab22e89045985f973e3ef960f6f3b34453f13e0e
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:b2fe91e4b71ad96971401f0069a1c0bd726c6e3d3f180c7c5724b4adc2dcccdc
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7170a2d9b24ecc77552af509fa5ca848d0a66f21c29b073517cc02fd19368fe3
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": 0.005235602094240838,
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": 9.188,
74
  "eval_steps_per_second": 4.603,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 1109757876240384.0,
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": 0.007853403141361256,
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": 9.188,
74
  "eval_steps_per_second": 4.603,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.006108202443280977,
79
+ "grad_norm": 4.898016452789307,
80
+ "learning_rate": 0.00014,
81
+ "loss": 3.5061,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.006980802792321117,
86
+ "grad_norm": 3.5651161670684814,
87
+ "learning_rate": 0.00016,
88
+ "loss": 3.1235,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.007853403141361256,
93
+ "grad_norm": 3.6318469047546387,
94
+ "learning_rate": 0.00018,
95
+ "loss": 2.6002,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.007853403141361256,
100
+ "eval_loss": 2.611670732498169,
101
+ "eval_runtime": 52.6343,
102
+ "eval_samples_per_second": 9.177,
103
+ "eval_steps_per_second": 4.598,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 1664636814360576.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null