auxyus commited on
Commit
d3571bd
·
verified ·
1 Parent(s): bb4679f

Training in progress, step 27, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3e445d76ae58d11894e69b613547df1819fcf18427849ec8b2c068c26778b66c
3
  size 217931936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27b09adba50583c7229d728271362074380ff4c5d72286b7c76dd16757850b6e
3
  size 217931936
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7268dda5b03338ee90fab01cf04c935d05698d3f1c2e51882d0bac98fbc92ad5
3
  size 111412180
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6868c658edcd70ed8a41562e2a50d8c799435e0771b160fe94e9bd3e74d4dbc6
3
  size 111412180
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fabe282c318f809f95f678d3b5880b0fa8c959a134bd1d0319f0df983d97fc58
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef4f90f8dbbc0d5937a88903e5e825a06c7f092531792a1e6225739e824afb86
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5ed723721bc2dad2381ab5522e40123ba4aa738fa3e449c48809fa9c2697eb95
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd4a07944f7914b974e23583756a2e0907223f4627a9b1ba247bd8f732140689
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": 0.24242424242424243,
5
  "eval_steps": 9,
6
- "global_step": 18,
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": 11.079,
74
  "eval_steps_per_second": 1.418,
75
  "step": 18
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 3,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 3.051179717374771e+16,
96
  "train_batch_size": 8,
97
  "trial_name": null,
98
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.36363636363636365,
5
  "eval_steps": 9,
6
+ "global_step": 27,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
73
  "eval_samples_per_second": 11.079,
74
  "eval_steps_per_second": 1.418,
75
  "step": 18
76
+ },
77
+ {
78
+ "epoch": 0.2828282828282828,
79
+ "grad_norm": 0.008192160166800022,
80
+ "learning_rate": 9.635919272833938e-05,
81
+ "loss": 0.0002,
82
+ "step": 21
83
+ },
84
+ {
85
+ "epoch": 0.32323232323232326,
86
+ "grad_norm": 0.002964617684483528,
87
+ "learning_rate": 9.414737964294636e-05,
88
+ "loss": 0.0001,
89
+ "step": 24
90
+ },
91
+ {
92
+ "epoch": 0.36363636363636365,
93
+ "grad_norm": 0.0018415789818391204,
94
+ "learning_rate": 9.145187862775209e-05,
95
+ "loss": 0.0,
96
+ "step": 27
97
+ },
98
+ {
99
+ "epoch": 0.36363636363636365,
100
+ "eval_loss": 3.535100768203847e-05,
101
+ "eval_runtime": 11.2827,
102
+ "eval_samples_per_second": 11.079,
103
+ "eval_steps_per_second": 1.418,
104
+ "step": 27
105
  }
106
  ],
107
  "logging_steps": 3,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 4.576769576062157e+16,
125
  "train_batch_size": 8,
126
  "trial_name": null,
127
  "trial_params": null