ardaspear commited on
Commit
215b3b4
·
verified ·
1 Parent(s): 605baf1

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:a5c30e4bf9a24912c25e52d1d010bbf5835e780580823a41794363bc45a6815e
3
  size 83115256
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2bca11cf8876cb00cca1bfc27920a86760d462916bd5b7544e1f82b70f0acf66
3
  size 83115256
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b51b0bb6079109ea03c3c887cf359260722f0efc5a5a5edd28967cefba95796b
3
  size 42608388
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:304e942077c19c3d4ffe673b5b31d24e86d5a03ad7ccd45018b189b9b8e24c70
3
  size 42608388
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9a8b8bbe690433f77d32baf5b5e01cabaff83cf87f66efe1da5c9f425fad7ba6
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:26874276c6417ee8aa16ea6cd2c302eb82bd3a827f551027b6e19cf69be8977a
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e7f75dad5b4fa698adb63b89c53682112a536ec6b4f570bd7793123dfd2a0133
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:95e5b5e126f269e3dd52e13e2ce68743557810f4e2bb59a1eda63231c7828066
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": 0.00747896540978498,
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": 23.394,
74
  "eval_steps_per_second": 2.926,
75
  "step": 18
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 3,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 7238147691773952.0,
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": 0.01121844811467747,
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": 23.394,
74
  "eval_steps_per_second": 2.926,
75
  "step": 18
76
+ },
77
+ {
78
+ "epoch": 0.008725459644749143,
79
+ "grad_norm": 0.8779253959655762,
80
+ "learning_rate": 4.817959636416969e-05,
81
+ "loss": 1.3657,
82
+ "step": 21
83
+ },
84
+ {
85
+ "epoch": 0.009971953879713306,
86
+ "grad_norm": 0.9482561945915222,
87
+ "learning_rate": 4.707368982147318e-05,
88
+ "loss": 1.2238,
89
+ "step": 24
90
+ },
91
+ {
92
+ "epoch": 0.01121844811467747,
93
+ "grad_norm": 0.7827633023262024,
94
+ "learning_rate": 4.572593931387604e-05,
95
+ "loss": 1.2321,
96
+ "step": 27
97
+ },
98
+ {
99
+ "epoch": 0.01121844811467747,
100
+ "eval_loss": 1.3266533613204956,
101
+ "eval_runtime": 173.524,
102
+ "eval_samples_per_second": 23.363,
103
+ "eval_steps_per_second": 2.922,
104
+ "step": 27
105
  }
106
  ],
107
  "logging_steps": 3,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 1.0857221537660928e+16,
125
  "train_batch_size": 8,
126
  "trial_name": null,
127
  "trial_params": null