Paladiso commited on
Commit
67c2831
·
verified ·
1 Parent(s): db38b09

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 sha256:764a44757c7b2d5b85197bfce4d60c417a68102ca1685c46b15ecea44ca69369
3
  size 48679352
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c87824c4cb2fac02b24d81a2c9bc8fe43b6fe08f859e7eea578bb71f1034960
3
  size 48679352
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:47d37afcfc73c9a4828237c552a8fe6f9e042f5b520a2321a67ef07fc48d9092
3
  size 25152500
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1257f0fe69538bba606451d281b38a99968ccefa5f2aca787f44586d287c5042
3
  size 25152500
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c013662eb3d2cf5fd75b84bce4f03835c6a78f724775d1abe2fb6d699b6aa4ed
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ce86d528d2e2afdc1a96e205683d118ce6d266706f82c629264a20268228dc95
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": 0.0018302913213686513,
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": 16.506,
95
  "eval_steps_per_second": 8.257,
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": 626150741114880.0,
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": 0.002033657023742946,
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": 16.506,
95
  "eval_steps_per_second": 8.257,
96
  "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.002033657023742946,
100
+ "grad_norm": 0.3822064697742462,
101
+ "learning_rate": 0.0002,
102
+ "loss": 1.2059,
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": 695723045683200.0,
124
  "train_batch_size": 2,
125
  "trial_name": null,
126
  "trial_params": null