Aivesa commited on
Commit
576fcec
·
verified ·
1 Parent(s): 5327b5a

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 sha256:1ccbdd80c67d29832b346402d88768c809a027bb5297c183dbfbcb12b6b3baad
3
  size 5327744
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f7e40205a38970f0c243f3e11c1995111775e11fb67306d1a2fc39e48d636337
3
  size 5327744
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3477bdf9e4a3d94ed3422acf3ebb96d004c853b2e28d0bca1c399f41c6d6437e
3
  size 2857722
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d9556b2eaf6df7ce0215ea77e23b34847e4470b41290435efbb3246aaaaf6709
3
  size 2857722
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5bdefab5aa8d905d152c0bac1bafc70c7308dfeec0e2f67ed1564906f50f6085
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e3f1943bf342c1b177d6f50476f912e01bb829b1e60aab3d70e1f9ea71e4812d
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": 0.0003310070890684909,
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": 39.738,
95
  "eval_steps_per_second": 19.871,
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": 38213120950272.0,
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": 0.00036778565452054543,
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": 39.738,
95
  "eval_steps_per_second": 19.871,
96
  "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.00036778565452054543,
100
+ "grad_norm": 3.707268238067627,
101
+ "learning_rate": 0.0002,
102
+ "loss": 14.3637,
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": 42459023278080.0,
124
  "train_batch_size": 2,
125
  "trial_name": null,
126
  "trial_params": null