Aivesa commited on
Commit
69a853d
·
verified ·
1 Parent(s): ae6cf38

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:b6f05ca6b5c548e1523a60d420f1494556c9f1f9603be9d688b89f6a952e8fb1
3
  size 36981072
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6568ba74acab48ceda82b306ae84b72812295a6711c20673f1307c2133cce5eb
3
  size 36981072
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:476ea86efae19fce14debbd2ea3a6ecc0f8779bbb220a0a5788a6a8f9af33035
3
  size 19859140
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd98681be6bb9f6171383a164667afbb273114000d956be351eb086da04e991e
3
  size 19859140
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ed657ca35a3b26ab39201e05f010d681b5d27ca2e383b370948911cf5bec9601
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d57765ccdbd3b79c135f681da7122fdba173117294579537d75e298a46d06671
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": 0.001918669722325854,
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": 17.81,
95
  "eval_steps_per_second": 8.91,
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": 291868432662528.0,
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": 0.0021318552470287267,
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": 17.81,
95
  "eval_steps_per_second": 8.91,
96
  "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.0021318552470287267,
100
+ "grad_norm": 0.8884080648422241,
101
+ "learning_rate": 0.0002,
102
+ "loss": 1.0179,
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": 324298258513920.0,
124
  "train_batch_size": 2,
125
  "trial_name": null,
126
  "trial_params": null