BayesTensor commited on
Commit
ecabe1e
·
verified ·
1 Parent(s): e7585af

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:cbe78db83f80e44a56d71c01113ab20f96731102522f454eea4b518d20a6cdd1
3
  size 598439784
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:51408732b655a2dfb6e7bf3e309c9410b13496f6df35524dc654def6cf309e78
3
  size 598439784
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:28b237199d7a061460bc306c88e0fdf31c24ce530dfe29c16d2a2bb466702135
3
  size 1196967418
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d6a58f30c9a2218e3c402c09328bc00ed493fed3e8d44aded8054c392e28d608
3
  size 1196967418
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:64b35a5dbf48e38ea0c5075e0936455402ab060974fea77a6c3c00c74f36d985
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d2832d03d3fb6cbb91ea98f5322ac5af4656fbe22723cdd1394d7fa1e740165
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:10dddcf385ec4dbe433a5f8602b31d3b2947d119562dee7ace906d5e86629977
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:315dcc590c85422fa00dd75e1cf3185167f7979dd20636fe3d14baaeb9dd6950
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 0.6304912478825522,
3
- "best_model_checkpoint": "modernbert-medical-classifier/checkpoint-276",
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": 12.691,
97
  "eval_steps_per_second": 3.173,
98
  "step": 552
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
99
  }
100
  ],
101
  "logging_steps": 100,
@@ -115,7 +131,7 @@
115
  "attributes": {}
116
  }
117
  },
118
- "total_flos": 3789599951592000.0,
119
  "train_batch_size": 4,
120
  "trial_name": null,
121
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.6857289002557545,
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": 12.691,
97
  "eval_steps_per_second": 3.173,
98
  "step": 552
99
+ },
100
+ {
101
+ "epoch": 6.521739130434782,
102
+ "grad_norm": 5.186334133148193,
103
+ "learning_rate": 3.695652173913043e-05,
104
+ "loss": 0.6183,
105
+ "step": 600
106
+ },
107
+ {
108
+ "epoch": 7.0,
109
+ "eval_f1": 0.6857289002557545,
110
+ "eval_loss": 0.5537915825843811,
111
+ "eval_runtime": 7.1555,
112
+ "eval_samples_per_second": 12.857,
113
+ "eval_steps_per_second": 3.214,
114
+ "step": 644
115
  }
116
  ],
117
  "logging_steps": 100,
 
131
  "attributes": {}
132
  }
133
  },
134
+ "total_flos": 4421199943524000.0,
135
  "train_batch_size": 4,
136
  "trial_name": null,
137
  "trial_params": null