ardaspear commited on
Commit
a0d3308
·
verified ·
1 Parent(s): 44ac701

Training in progress, step 27, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6980d9cb6578d5a45c451abfa4b28749e0e69ddada4527c1d325b81416221f68
3
  size 1001465824
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f56a69f057cb7c8031e381f90914b1622ee0f92586d39e84bd490c243aa0f608
3
  size 1001465824
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c67d0c2b0ec893fb4cdb2a72036fd20fadca00f782e395d7dbfc5c60269fa4d7
3
  size 509176980
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0edb2191892719ab57cd4ed2eb900a37d19bbf18b1a1e9d2ede4fc81fb6eecbb
3
  size 509176980
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:57be20421170f25d7026a038ec19d4695b917e87817a59b2840e1f4390ced113
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4575d55a0919f81b5422546e48dd159a99e2a81e8e7b02331f8aa416b2acfa58
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5ed723721bc2dad2381ab5522e40123ba4aa738fa3e449c48809fa9c2697eb95
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd4a07944f7914b974e23583756a2e0907223f4627a9b1ba247bd8f732140689
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": 0.1592920353982301,
5
  "eval_steps": 9,
6
- "global_step": 18,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -73,6 +73,35 @@
73
  "eval_samples_per_second": 7.769,
74
  "eval_steps_per_second": 1.963,
75
  "step": 18
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 3,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 2.479445457764352e+16,
96
  "train_batch_size": 4,
97
  "trial_name": null,
98
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.23893805309734514,
5
  "eval_steps": 9,
6
+ "global_step": 27,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
73
  "eval_samples_per_second": 7.769,
74
  "eval_steps_per_second": 1.963,
75
  "step": 18
76
+ },
77
+ {
78
+ "epoch": 0.18584070796460178,
79
+ "grad_norm": 0.012934673577547073,
80
+ "learning_rate": 9.635919272833938e-05,
81
+ "loss": 0.0003,
82
+ "step": 21
83
+ },
84
+ {
85
+ "epoch": 0.21238938053097345,
86
+ "grad_norm": 0.00015438912669196725,
87
+ "learning_rate": 9.414737964294636e-05,
88
+ "loss": 0.0002,
89
+ "step": 24
90
+ },
91
+ {
92
+ "epoch": 0.23893805309734514,
93
+ "grad_norm": 0.0381203256547451,
94
+ "learning_rate": 9.145187862775209e-05,
95
+ "loss": 0.0001,
96
+ "step": 27
97
+ },
98
+ {
99
+ "epoch": 0.23893805309734514,
100
+ "eval_loss": 1.8848184026865056e-06,
101
+ "eval_runtime": 12.2379,
102
+ "eval_samples_per_second": 7.763,
103
+ "eval_steps_per_second": 1.961,
104
+ "step": 27
105
  }
106
  ],
107
  "logging_steps": 3,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 3.86407084326912e+16,
125
  "train_batch_size": 4,
126
  "trial_name": null,
127
  "trial_params": null