jssky commited on
Commit
4306bb9
1 Parent(s): 7223b40

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:e5a7c9ab9ca34ddc9e464d415e468c25fd925db5f70f8a8e107b6a055bd3ded1
3
  size 247944
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a5dfd442280ba3614a49e58c7c1a964f66149a46c25f2b256db20cdc87bc0d4d
3
  size 247944
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7a20888a879cf31c4a13dc3ecf491c2e0111f2e124da5c9cc06aaf691534a896
3
  size 263088
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ce7f301da698861cb98a61f3edb72e265dd85e9a91ab4300905845e10555c86e
3
  size 263088
last-checkpoint/rng_state_0.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f8809c96bed7e6c896e7eff1b04f154442b7d50108eb01132ca9236ef709bbfd
3
  size 15984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:512a2af5c1d9245d8a996dd66430b2f6a85cd70b86c194638fd2d00bc450a988
3
  size 15984
last-checkpoint/rng_state_1.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b799eb1351996defa336c883fefd88e74c06daab5df0bce4017e8c1479d94380
3
  size 15984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:08a1d187e4bf28043cedb6eeed3256595705434498ccd86e59f4db65a4eb8a72
3
  size 15984
last-checkpoint/rng_state_2.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2cc96250a43e632cb5ae9a7107ce24b7457153290af9cf9897e264556e71a99d
3
  size 15984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:95eb1b3788848cf7544bf54ca03a28952e6b2a17431ea7bf4f89cd2181e5170e
3
  size 15984
last-checkpoint/rng_state_3.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b6bdbf9f09105bc5b75430990cc4806889374b706a5d72a98a7a4c5572f58c90
3
  size 15984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0dd27b0498c2de2a5b755061a84c6d861eaefba7823ebd6536556a4aa5f22614
3
  size 15984
last-checkpoint/rng_state_4.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:121c075a7ce23987cdf5c15e739fd91b8847af12854b7686f3ca78a6bd4525e2
3
  size 15984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:385d4cd03f7e02aca5437770f13156f5e7b710128112cff9f7619204c587aad2
3
  size 15984
last-checkpoint/rng_state_5.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c1ed112ff99ef0735a0ef90c244ffe14da9ac21f00ecbe3f03d76ef8efc02f15
3
  size 15984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1cf3c666cf8cc9c934cb8ff4096f142e56372073b853dd1231daee15bd378ead
3
  size 15984
last-checkpoint/rng_state_6.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:823be00465c529ec2e81df753933cee16cc7fa8be0987893a34b063c1a819cb9
3
  size 15984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8801e4b5728e439ec8f3d747e4002af6d9bbb23f5ae7b460a281f460a12c8751
3
  size 15984
last-checkpoint/rng_state_7.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a3820d50e85079de6cf344fe2d67b6b136bed4e19bda6730e22c79f77817e74a
3
  size 15984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:809b25c38de0d6467f4fc784b3800183b76b1d06a17b2a76ed1dee5abec31ba8
3
  size 15984
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": 0.000987844030403644,
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": 638.024,
103
  "eval_steps_per_second": 79.789,
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": 2995135709184.0,
125
  "train_batch_size": 1,
126
  "trial_name": null,
127
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.0010976044782262712,
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": 638.024,
103
  "eval_steps_per_second": 79.789,
104
  "step": 9
105
+ },
106
+ {
107
+ "epoch": 0.0010976044782262712,
108
+ "grad_norm": 3.691930055618286,
109
+ "learning_rate": 0.0002,
110
+ "loss": 44.1788,
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": 3327928565760.0,
132
  "train_batch_size": 1,
133
  "trial_name": null,
134
  "trial_params": null