BayesTensor commited on
Commit
019aee7
·
verified ·
1 Parent(s): 06a0186

Training in progress, epoch 7, checkpoint

Browse files
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:378616275dd28ae8ef3fb021671ac2c63e4878776b178abbe76454993736c3cf
3
  size 598442860
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:edc722e2de5365cfeec2fc913b04dc080b1d0a8df2a77b935b8e7d687bb0a41c
3
  size 598442860
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e73b82a76b93127980577899166d22cbabb4c0f6ae31a0bab950f99f4683b932
3
  size 1196973562
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b00f472daa01b7422c27895a4a520d611143b4fd9e58668debdb120fe7ebf07c
3
  size 1196973562
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e3e5d946241df2516b06d7074d8779088eae7607173ad780df56583910a9589b
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d3b7102895eb0637b0cab516bd672f216b2bf79078a83eb301011a90444f44c
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9999a9549cef0f45d8550ab27d9259d2df992c9bc69b780bc916dcde494fe003
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:34501ac964621bff9788a01b10e8298751b6c8e0d517313f2150b06ce29b2619
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 0.5668988939449298,
3
- "best_model_checkpoint": "modernbert-medical-classifier/checkpoint-552",
4
- "epoch": 6.0,
5
  "eval_steps": 500,
6
- "global_step": 552,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -96,6 +96,22 @@
96
  "eval_samples_per_second": 12.571,
97
  "eval_steps_per_second": 3.143,
98
  "step": 552
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
99
  }
100
  ],
101
  "logging_steps": 100,
@@ -115,7 +131,7 @@
115
  "attributes": {}
116
  }
117
  },
118
- "total_flos": 3789626223708000.0,
119
  "train_batch_size": 4,
120
  "trial_name": null,
121
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.6268890955591723,
3
+ "best_model_checkpoint": "modernbert-medical-classifier/checkpoint-644",
4
+ "epoch": 7.0,
5
  "eval_steps": 500,
6
+ "global_step": 644,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
96
  "eval_samples_per_second": 12.571,
97
  "eval_steps_per_second": 3.143,
98
  "step": 552
99
+ },
100
+ {
101
+ "epoch": 6.521739130434782,
102
+ "grad_norm": 26.001848220825195,
103
+ "learning_rate": 1.6425120772946863e-05,
104
+ "loss": 0.9261,
105
+ "step": 600
106
+ },
107
+ {
108
+ "epoch": 7.0,
109
+ "eval_f1": 0.6268890955591723,
110
+ "eval_loss": 0.8952301740646362,
111
+ "eval_runtime": 7.2679,
112
+ "eval_samples_per_second": 12.658,
113
+ "eval_steps_per_second": 3.165,
114
+ "step": 644
115
  }
116
  ],
117
  "logging_steps": 100,
 
131
  "attributes": {}
132
  }
133
  },
134
+ "total_flos": 4421230594326000.0,
135
  "train_batch_size": 4,
136
  "trial_name": null,
137
  "trial_params": null