kk-aivio commited on
Commit
082ea61
·
verified ·
1 Parent(s): 3b194e8

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:d47ff42cac365ccb56684603ed373722aab9daf1080d24637e1166451a2f18c4
3
  size 39256456
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e2c614380db82790118000d32b12119502937c842da5d1a338ea66b1c166d6a0
3
  size 39256456
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:35426ba23d8507e1001e3055a9f7ac2d328a30fb9c674c7226eb43abe351a678
3
  size 20632826
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9210b85dc1576be912532219a2fa6d0a8e0d9aec7107a2b1245e8ec36efd5c13
3
  size 20632826
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0fa1a0d0cdffee0e67ae7ed6391afabb997ee4a313c59720dcb7806763499936
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:16fec04f5f7d4c92e309d5097746e652135b11943ea9640b53c8226bd2b75476
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": 0.036072144288577156,
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": 47.037,
103
  "eval_steps_per_second": 23.742,
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": 599610296893440.0,
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": 0.04008016032064128,
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": 47.037,
103
  "eval_steps_per_second": 23.742,
104
  "step": 9
105
+ },
106
+ {
107
+ "epoch": 0.04008016032064128,
108
+ "grad_norm": 2.9328107833862305,
109
+ "learning_rate": 0.0002,
110
+ "loss": 1.3019,
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": 673031965900800.0,
132
  "train_batch_size": 2,
133
  "trial_name": null,
134
  "trial_params": null