jssky commited on
Commit
ecfb248
·
verified ·
1 Parent(s): edf3133

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 sha256:89f15dc22b8ff7e224522e79c6564ebc8c4f7ef902ff3950d044052c9c667a40
3
  size 159967880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:975be470a99735648377116a2bcc4211d3abe0c3cbdcb0af23fe0b172527e5af
3
  size 159967880
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e9e0270f93cd654f8cb18787ca33e2c1cac7cc754f1aabda384b9f2f25fee59a
3
  size 81730196
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d5cd46cc96862273f6f6d7cca464ee1e121259d4e522c969a00e4c78798cb85
3
  size 81730196
last-checkpoint/rng_state_0.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b0e7f447e27f453b92bcc2d66c2ac0c3d7835d9b1676358b9971ba3ec7667078
3
  size 15984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:50afd84b72e33dc4fa1c8766f8bfa7f034af09651ee660d0f10fe20e73b99884
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:d10bc2712f3c056a78e7e8b2de5ea76be887ed3d14e0782d265c7f63954d5a5d
3
  size 15984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:408578e54a9ec49723e552146094a8e8586e52d8a8e03328c31fe0533edde34f
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 sha256:9cb8273d15bb98237e8cc79fab834d1622a5bd71bd1f64f73114a7c2d57715f1
3
  size 15984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d570b24084f505cd11850e55cc5d99ef9f025c8bfdde21b13a148959122dee5
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 sha256:82570c81ad2b37a76096ba755b2ddf2ca7c1d8189277ddbed245cf52f9f07b55
3
  size 15984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ada47d6a30594024da8631fca9cf1b2c6feac0ed2262ff5ff9d9748875d31d2f
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 sha256:96136822f5afc6b4bddfc0e13f4ec414b4dd526b059a6aa156834159d34ca1ec
3
  size 15984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cec2eae823044c16edd6b6abcd708be814fed75f8ead886e454f4910aff86e88
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:ed4698fbedecddb68628eb1c9410d2236a64115134757be7a216be2525cb56cb
3
  size 15984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ea0d1ac735de6b195bb8f45da786f2a57379be9a344770a4a782ef3ad4bd976d
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:b3ab6c06a6e71d0b0f197faa31dfc3d35d94bffb3aff0f693cde32dddcbaae89
3
  size 15984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a03cc5c9ada7ebbeece1970d5239df65a24343c415ad9702330e73b386924c8e
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:a6a2c1079167854862782cfddb9d3b64b12cbc594c6ea4a97653a0a8aead9b45
3
  size 15984
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5aca0a7f03994ab8a6bcb85c8f6f097484079dc56c8af6dbf1cf2c51babcf8c2
3
  size 15984
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8bdda546a1390be3b85a90dd4ef31050dfb7b691765ffc12ed691b6786ed6e3d
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:26a93b2a1f4b5368650119fe6e0d6eec6d19cda6badeba4d21943ab48964fa00
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": 0.06164383561643835,
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": 36.42,
103
  "eval_steps_per_second": 4.59,
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": 4.746460593232282e+16,
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": 0.0684931506849315,
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": 36.42,
103
  "eval_steps_per_second": 4.59,
104
  "step": 9
105
+ },
106
+ {
107
+ "epoch": 0.0684931506849315,
108
+ "grad_norm": 0.9450744390487671,
109
+ "learning_rate": 0.00016,
110
+ "loss": 2.2093,
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": 5.273845103591424e+16,
132
  "train_batch_size": 1,
133
  "trial_name": null,
134
  "trial_params": null