Aivesa commited on
Commit
b7779f0
·
verified ·
1 Parent(s): 29f8a0f

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:c986d32aebffa74667451b9654278dd833a283e4a2d5a06ff11cb13084e77ed9
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b3630cf05fd59ec733ee1fc4307829bd132d2148dbbbb628f16c81c551b76ab1
3
  size 83945296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a460a76e2ee1ce5d5c9f9ec32df8731d633be47af65cbe63dfefe7b4199224df
3
  size 43122580
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b89206622693aaf93c544d91ef2ce6abc271bdd369eaddff505d3424ae27f27
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:c388edef795d5fdb631eb1ef65eedde4d1d8a203e750e4a560bddd528a88ff70
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d0b2aa336c635db46b901cf447ca964d0d0e956a72eff2779eb99e70b9711bf
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": 0.00048554819740231713,
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": 13.238,
95
  "eval_steps_per_second": 6.62,
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": 2385107579043840.0,
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": 0.0005394979971136857,
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": 13.238,
95
  "eval_steps_per_second": 6.62,
96
  "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.0005394979971136857,
100
+ "grad_norm": 1.6321094036102295,
101
+ "learning_rate": 0.0002,
102
+ "loss": 0.752,
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": 2610117728010240.0,
124
  "train_batch_size": 2,
125
  "trial_name": null,
126
  "trial_params": null