jssky commited on
Commit
d4afa3c
1 Parent(s): ad06739

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 sha256:14b85205546931cc573d8d5684631f8740cdba9735b9f91b6ca09f4c2874fec3
3
  size 19552
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c6c16cb66c4b12e61c9eac9684946b331c00a23e649df788811a7a05d4c8f674
3
  size 19552
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4f7bf68912e71367087f4870bc9524b2a2f429f76d34d867a386d4e1f0dfc8ef
3
  size 44354
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:43472a8cc19a241578f8afdfb21ff33f9146c73b1868e2f8aedd2e1f497fbc6a
3
  size 44354
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:06f3828ea52b194ed76e01c62f9f5be77b2bd9f9cfe728db3d9d8cc44a4f67a8
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d53389285e1a574b35c681421511ed4fd865190d0dbcc7ca577aba5847d929e5
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": 0.005419238295950625,
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": 51.258,
103
  "eval_steps_per_second": 51.258,
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": 5549064192.0,
125
  "train_batch_size": 1,
126
  "trial_name": null,
127
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.006021375884389583,
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": 51.258,
103
  "eval_steps_per_second": 51.258,
104
  "step": 9
105
+ },
106
+ {
107
+ "epoch": 0.006021375884389583,
108
+ "grad_norm": 0.006291355937719345,
109
+ "learning_rate": 0.0002,
110
+ "loss": 12.442,
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": 6165626880.0,
132
  "train_batch_size": 1,
133
  "trial_name": null,
134
  "trial_params": null