brixeus commited on
Commit
80c2af6
·
verified ·
1 Parent(s): 696a34a

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 sha256:9d4ec839628739a86b262803631999848d351c9b63f09660c4dc8f610626c475
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8354570fb497f9a3376c9622903a026631f74201972848896a8830f91128ee6d
3
  size 83945296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b2fb6a596178dde6ec0dfd9480c47f7b15287b60719f259409633cbeb51e3ad5
3
  size 43122580
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed6d653f5d3cfb5cfb7843e2e1ee22d85138f82efc41e1aa1ca99e635ac78db7
3
  size 43122580
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6cf30c4e1dfd3b199f004d48c615f0058d9d8168fc7715316fa0d2b53a3286f2
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b4f63aec6d8b3291c19fe2b4497f750eeddd6b87b84886cefc94a6bfc39de55
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": 0.0207732256203116,
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": 13.956,
74
  "eval_steps_per_second": 1.749,
75
  "step": 18
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 3,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 2.523847390868275e+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": 0.031159838430467397,
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": 13.956,
74
  "eval_steps_per_second": 1.749,
75
  "step": 18
76
+ },
77
+ {
78
+ "epoch": 0.024235429890363532,
79
+ "grad_norm": 3.75036358833313,
80
+ "learning_rate": 9.635919272833938e-05,
81
+ "loss": 7.5972,
82
+ "step": 21
83
+ },
84
+ {
85
+ "epoch": 0.027697634160415464,
86
+ "grad_norm": 3.694056510925293,
87
+ "learning_rate": 9.414737964294636e-05,
88
+ "loss": 7.325,
89
+ "step": 24
90
+ },
91
+ {
92
+ "epoch": 0.031159838430467397,
93
+ "grad_norm": 3.767008066177368,
94
+ "learning_rate": 9.145187862775209e-05,
95
+ "loss": 7.8502,
96
+ "step": 27
97
+ },
98
+ {
99
+ "epoch": 0.031159838430467397,
100
+ "eval_loss": 1.9282969236373901,
101
+ "eval_runtime": 104.5512,
102
+ "eval_samples_per_second": 13.964,
103
+ "eval_steps_per_second": 1.75,
104
+ "step": 27
105
  }
106
  ],
107
  "logging_steps": 3,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 3.785771086302413e+16,
125
  "train_batch_size": 8,
126
  "trial_name": null,
127
  "trial_params": null