Aivesa commited on
Commit
3892d84
·
verified ·
1 Parent(s): 0c5336b

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:d0efe60cf3f4d435af9c37b1a1ff27d7acebbea33eb172cc21d4f4526ecddd48
3
  size 39256456
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d39ea21e7ff79939cf6acfa2b850dc9d31fa168dd2a10361286d882f1737dda
3
  size 39256456
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:746ebb2520fb94b20ccab30a876c07a5215b85d579f3b5364432e62253e002d1
3
  size 20632826
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:13dd5e913cfc2fb2ee02d1899458839c0e6304f9418384e361e6e8c07bfb5c04
3
  size 20632826
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:574b2f0aac69a88223246e1abbe4d7331cee680c2262f30a429273e330af5c7f
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e8c9bc14ee53dc49326cd1371a32f212479a5ffa79a9f0a2ddd9ad8b1378f3d0
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": 0.0006585084782966581,
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": 10.889,
95
  "eval_steps_per_second": 5.445,
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": 538425572720640.0,
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": 0.0007316760869962867,
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": 10.889,
95
  "eval_steps_per_second": 5.445,
96
  "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.0007316760869962867,
100
+ "grad_norm": 1.1383073329925537,
101
+ "learning_rate": 0.0002,
102
+ "loss": 0.1835,
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": 624084186562560.0,
124
  "train_batch_size": 2,
125
  "trial_name": null,
126
  "trial_params": null