ClarenceDan commited on
Commit
67a637e
·
verified ·
1 Parent(s): ec8c7fe

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:d1a6e6df49ec25f043a7adf1ed39da32f89264b24318b1665bf732a3eaa7047f
3
  size 6804608
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c833779f522f28d59f78a6efdb1995145d9f79fff69a0116eddb3f43728a3e50
3
  size 6804608
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fe3f09e6c3596175a48ad9db219bacecd8ac584bc7ab406a256a805d8a40e61e
3
  size 3633530
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:07be7c19d27d2d30755b4efb418b7233cf37b97d4f36eef3e7c2b0ace5016820
3
  size 3633530
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0ebb3a935f103fde8d7d593f6c636206ae47877a48e671f781108f4a0a6cbb96
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d648a1322336ba65450c8c6b38551a9c8a4b8d3ca0a43997d4dca4e78ff923ae
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": 0.0001149410607782787,
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,
@@ -102,6 +102,13 @@
102
  "eval_samples_per_second": 106.572,
103
  "eval_steps_per_second": 53.288,
104
  "step": 9
 
 
 
 
 
 
 
105
  }
106
  ],
107
  "logging_steps": 1,
@@ -116,12 +123,12 @@
116
  "should_evaluate": false,
117
  "should_log": false,
118
  "should_save": true,
119
- "should_training_stop": false
120
  },
121
  "attributes": {}
122
  }
123
  },
124
- "total_flos": 30863385427968.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.000127712289753643,
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,
 
102
  "eval_samples_per_second": 106.572,
103
  "eval_steps_per_second": 53.288,
104
  "step": 9
105
+ },
106
+ {
107
+ "epoch": 0.000127712289753643,
108
+ "grad_norm": 0.981518030166626,
109
+ "learning_rate": 0.0002,
110
+ "loss": 3.4075,
111
+ "step": 10
112
  }
113
  ],
114
  "logging_steps": 1,
 
123
  "should_evaluate": false,
124
  "should_log": false,
125
  "should_save": true,
126
+ "should_training_stop": true
127
  },
128
  "attributes": {}
129
  }
130
  },
131
+ "total_flos": 34292650475520.0,
132
  "train_batch_size": 2,
133
  "trial_name": null,
134
  "trial_params": null