Aivesa commited on
Commit
5d751e5
·
verified ·
1 Parent(s): 3e9e896

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 sha256:73e1cf7fac43ab0110ac032162a9d103986e54965663f9cc13d2b29aacce072a
3
  size 51431872
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:775ce230e3cd2b842e9547b8dcbffb4e5e187800603b88715f4ded63ead27733
3
  size 51431872
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7a09c20042e6df46e023bed37c252da32ca921e61a565bd98455af4a21c93a85
3
  size 26550260
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e1275643b2d2cd9809fb0a89b9a42f962baa6b74a54bde14aa963bc25d30245
3
  size 26550260
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7ba74afa0c42946643885d2bdc990f5514233d2f80bbe5a0e8ba5ba52d2fd479
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:16f8dce4ea8db55fab98810852c3b7d6da325bbb69e21644a5658ad81a5d8213
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": 18.502,
95
  "eval_steps_per_second": 9.255,
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": 684748858982400.0,
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": 18.502,
95
  "eval_steps_per_second": 9.255,
96
  "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.002033657023742946,
100
+ "grad_norm": 1.9238121509552002,
101
+ "learning_rate": 0.0002,
102
+ "loss": 1.3964,
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": 760832065536000.0,
124
  "train_batch_size": 2,
125
  "trial_name": null,
126
  "trial_params": null