willtensora commited on
Commit
5a231f7
·
verified ·
1 Parent(s): 9200508

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 sha256:92c6adf8f4340fa05c4cff561b05ac7aa6717ed5aad94be8bc13ae5db386177f
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e4e4f720bc79744c1a4ca39cf1ef4427f82369f32ae5753fa426c566c1eacdd6
3
  size 83945296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:55b354e2c22ea89e6399c1e15f99a845b4c91668f457d64756465efbbd682d2e
3
  size 43122580
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4712f588db00e2d326cf01b70f4520b731d9d2a4f3194b12940bf5a238ba795e
3
  size 43122580
last-checkpoint/rng_state_0.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ef12b6dfbbd8e9ffb3ee559ac88ba28ccd4ecbca575ae9e6bba9374f75ce34ca
3
  size 14512
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1460aba4e9ce5e94ff519d2a40ad739b51c8355ba556d1e43c6b81b85168a7e9
3
  size 14512
last-checkpoint/rng_state_1.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6771eaea8d119793794214c4189a1e1af4912c9df24e2598e943f186f276b24a
3
  size 14512
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:52ab89f405a2e690da743d8c2fafb7b8f7434c4b17f42fa4c78df280523b2484
3
  size 14512
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": 0.009287925696594427,
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": 63.739,
103
  "eval_steps_per_second": 15.993,
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": 3329215646662656.0,
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": 0.010319917440660475,
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": 63.739,
103
  "eval_steps_per_second": 15.993,
104
  "step": 9
105
+ },
106
+ {
107
+ "epoch": 0.010319917440660475,
108
+ "grad_norm": 12.331144332885742,
109
+ "learning_rate": 0.0002,
110
+ "loss": 4.0536,
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": 3699128496291840.0,
132
  "train_batch_size": 2,
133
  "trial_name": null,
134
  "trial_params": null