mgh6 commited on
Commit
114fd0d
·
verified ·
1 Parent(s): 64498ee

Training in progress, epoch 14, checkpoint

Browse files
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6c0219eb07980e63b09e7bd8de4d2708bc22718bff14c5bd59ee18a97eccd127
3
  size 2708740080
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d78990c742db05f7322a291fc40ce156805942387a759ec65f51174ecb4b9caa
3
  size 2708740080
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:38624959d42ebf3bfd7b3a819585a2ab43cd4a71c39727e183f7e7c86f302451
3
  size 52521338
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:716f5cd153bf538498e2c668f41632b6974ee0f6658552013b7fd0d1539f0a2d
3
  size 52521338
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0b1829b902e6bdaec88f1230ae02d13eef41f76ce20823fc71b57ce8bb43dbf1
3
  size 15006
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f75193245e65869ca07a16a2caab41ba86286fcae28542136bb36df639a39935
3
  size 15006
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e82ce163f895513f9596e2fe7d224df4da3d605a883d85ca766973e89895c869
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4b510d1d1b89dffa740a4b5dd69da40dc0ea1cd7da205e5d9953a7b7121364b2
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 2.7399117946624756,
3
- "best_model_checkpoint": "mgh6/HTH_biCLIP_mean/checkpoint-1677",
4
- "epoch": 13.0,
5
  "eval_steps": 500,
6
- "global_step": 1677,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -215,6 +215,22 @@
215
  "eval_samples_per_second": 22.807,
216
  "eval_steps_per_second": 1.425,
217
  "step": 1677
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
218
  }
219
  ],
220
  "logging_steps": 500,
 
1
  {
2
+ "best_metric": 2.7374284267425537,
3
+ "best_model_checkpoint": "mgh6/HTH_biCLIP_mean/checkpoint-1806",
4
+ "epoch": 14.0,
5
  "eval_steps": 500,
6
+ "global_step": 1806,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
215
  "eval_samples_per_second": 22.807,
216
  "eval_steps_per_second": 1.425,
217
  "step": 1677
218
+ },
219
+ {
220
+ "epoch": 14.0,
221
+ "grad_norm": 0.012850044295191765,
222
+ "learning_rate": 0.00076484375,
223
+ "loss": 2.7134,
224
+ "step": 1806
225
+ },
226
+ {
227
+ "epoch": 14.0,
228
+ "eval_cosine_similarity": 0.37954288721084595,
229
+ "eval_loss": 2.7374284267425537,
230
+ "eval_runtime": 18.9452,
231
+ "eval_samples_per_second": 22.803,
232
+ "eval_steps_per_second": 1.425,
233
+ "step": 1806
234
  }
235
  ],
236
  "logging_steps": 500,