avsolatorio commited on
Commit
5a6e0bb
1 Parent(s): a883bc0

Training in progress, step 4000, checkpoint

Browse files
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6b93cc327305cb2797063eb09bd10f6c29672eb24765a303f74aab4d3e4f90ad
3
  size 567860028
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e9b2d6969dd83bc1c43996563873904653a70fa8a0de29bcd1b7f7ddd8775f7
3
  size 567860028
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:41b446f984dffebd1b5b2b55823ae399565b61f07ee724284c5c50aa01030a14
3
  size 1135783354
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:05d78afae041207d004fc4f244d7c3f8f3af6e6fe32125d24890dd0317f62e40
3
  size 1135783354
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e64b28e054193eaeff0d625fef705a5122942e1a18af84585e7031e05f4d367e
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f8a5b7fde4c37eeccbe4aca8abd49518b2e855ca1720563c5af4866d40338cb0
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bf1f1d71c2538f4e6c4311b28c8abb9dab5ee4ce70ffee85f9b380b76dcf0420
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c4834ce2586dc426079f90c930b0e0d6ec21ad9d8a256946c64bb3fc73152baa
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 0.05700037255883217,
3
- "best_model_checkpoint": "doc-topic-model_eval-01_train-03/checkpoint-3000",
4
- "epoch": 1.4792899408284024,
5
  "eval_steps": 1000,
6
- "global_step": 3000,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -85,6 +85,32 @@
85
  "eval_samples_per_second": 567.375,
86
  "eval_steps_per_second": 2.239,
87
  "step": 3000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
88
  }
89
  ],
90
  "logging_steps": 500,
@@ -113,7 +139,7 @@
113
  "attributes": {}
114
  }
115
  },
116
- "total_flos": 67624319430180.0,
117
  "train_batch_size": 4,
118
  "trial_name": null,
119
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.049796320497989655,
3
+ "best_model_checkpoint": "doc-topic-model_eval-01_train-03/checkpoint-4000",
4
+ "epoch": 1.972386587771203,
5
  "eval_steps": 1000,
6
+ "global_step": 4000,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
85
  "eval_samples_per_second": 567.375,
86
  "eval_steps_per_second": 2.239,
87
  "step": 3000
88
+ },
89
+ {
90
+ "epoch": 1.725838264299803,
91
+ "grad_norm": 0.3490855395793915,
92
+ "learning_rate": 1.965483234714004e-05,
93
+ "loss": 0.056,
94
+ "step": 3500
95
+ },
96
+ {
97
+ "epoch": 1.972386587771203,
98
+ "grad_norm": 0.4068734347820282,
99
+ "learning_rate": 1.9605522682445763e-05,
100
+ "loss": 0.0542,
101
+ "step": 4000
102
+ },
103
+ {
104
+ "epoch": 1.972386587771203,
105
+ "eval_accuracy": 0.9839533993792253,
106
+ "eval_f1": 0.2863985881759738,
107
+ "eval_loss": 0.049796320497989655,
108
+ "eval_precision": 0.8319296960820213,
109
+ "eval_recall": 0.17297297297297298,
110
+ "eval_runtime": 14.4691,
111
+ "eval_samples_per_second": 560.505,
112
+ "eval_steps_per_second": 2.212,
113
+ "step": 4000
114
  }
115
  ],
116
  "logging_steps": 500,
 
139
  "attributes": {}
140
  }
141
  },
142
+ "total_flos": 90160058450772.0,
143
  "train_batch_size": 4,
144
  "trial_name": null,
145
  "trial_params": null