mrferr3t commited on
Commit
6f09422
·
verified ·
1 Parent(s): 18a371d

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:f637200692146f70168a0f4c7ded9a56521106e2e4046371644d47991715c79b
3
  size 14293800
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac55efb3f82f0f4910425195086ee7e7a7af7d62c6eb9dd15a4f1d00e7bfd79f
3
  size 14293800
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e19907eb39b23d3c0962b1dae88b6a93d4cefea1e967c13e318a2b3eab754334
3
  size 7579748
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e40810dc2a51bf20851b72a9ad6a12f57f90974e0f21c8b0327a62788f2fc2cf
3
  size 7579748
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ef0ef582e555b2318afd484104e122f2ed17bee7953ab960b85fd42965e00786
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f12b760dc734d672225ff98a688a0e04e0886707e66c2239851a166da3e1e37b
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": 0.001866832607342875,
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": 82.734,
103
  "eval_steps_per_second": 41.367,
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": 118800708009984.0,
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": 0.0020742584526031943,
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": 82.734,
103
  "eval_steps_per_second": 41.367,
104
  "step": 9
105
+ },
106
+ {
107
+ "epoch": 0.0020742584526031943,
108
+ "grad_norm": 2.522325038909912,
109
+ "learning_rate": 0.0002,
110
+ "loss": 3.2933,
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": 133886512201728.0,
132
  "train_batch_size": 2,
133
  "trial_name": null,
134
  "trial_params": null