Paladiso commited on
Commit
b4af477
·
verified ·
1 Parent(s): 1de7bd5

Training in progress, step 10, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:231312d3d084819bd330873c7cdd98ecf59b402f561069b294fa997c746f9a36
3
  size 604317736
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ed24d5a3b50f44ac069262df77d898e7657861e932f10ebe717fdf1081e4240
3
  size 604317736
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4068f4d02ccda0df579e98cbf0c559ed1ecc2ddf05476ee0167813df1a796bda
3
  size 41119636
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2f3af8b7b06b843cc45511e8f14188c77c141aa8e7f3344a4a2730999fd7e72
3
  size 41119636
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:332d05b227720963e561614b208f5e39d94130cc5b67b712d8aec704897dc6e6
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d6b6662714e5b994bba16e514b50ddc831eee9d5bb5c1d43535e2d3b4f207d3
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9c8e6b04902f17ae368c3e6cfd97a31ad4de2f025d673daea8c033ce0e260946
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
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": 0.00011639335781904713,
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,
@@ -94,6 +94,13 @@
94
  "eval_samples_per_second": 17.971,
95
  "eval_steps_per_second": 8.985,
96
  "step": 9
 
 
 
 
 
 
 
97
  }
98
  ],
99
  "logging_steps": 1,
@@ -108,12 +115,12 @@
108
  "should_evaluate": false,
109
  "should_log": false,
110
  "should_save": true,
111
- "should_training_stop": false
112
  },
113
  "attributes": {}
114
  }
115
  },
116
- "total_flos": 1465860728291328.0,
117
  "train_batch_size": 2,
118
  "trial_name": null,
119
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.0001293259531322746,
5
  "eval_steps": 3,
6
+ "global_step": 10,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
94
  "eval_samples_per_second": 17.971,
95
  "eval_steps_per_second": 8.985,
96
  "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.0001293259531322746,
100
+ "grad_norm": 1.1890869140625,
101
+ "learning_rate": 0.0002,
102
+ "loss": 0.4355,
103
+ "step": 10
104
  }
105
  ],
106
  "logging_steps": 1,
 
115
  "should_evaluate": false,
116
  "should_log": false,
117
  "should_save": true,
118
+ "should_training_stop": true
119
  },
120
  "attributes": {}
121
  }
122
  },
123
+ "total_flos": 1628734142545920.0,
124
  "train_batch_size": 2,
125
  "trial_name": null,
126
  "trial_params": null