Hugging Face's logo

mgh6
/
TCS_Pair_base

TensorBoard
Safetensors
esm
Model card Files
xet
Metrics Community
mgh6 commited on
Commit
625977f
·
verified ·
1 Parent(s): 2847ce9

Training in progress, step 900, checkpoint

Browse files
Files changed (9) hide show
  1. last-checkpoint/model.safetensors +1 -1
  2. last-checkpoint/optimizer.pt +1 -1
  3. last-checkpoint/rng_state.pth +1 -1
  4. last-checkpoint/rng_state_0.pth +1 -1
  5. last-checkpoint/rng_state_1.pth +1 -1
  6. last-checkpoint/rng_state_2.pth +1 -1
  7. last-checkpoint/rng_state_3.pth +1 -1
  8. last-checkpoint/scheduler.pt +1 -1
  9. last-checkpoint/trainer_state.json +19 -4
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f57434a20fa14e3b8ce236cd4f51eb3aef80faef3597a7084b79537529932cd1
3
  size 136989964
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f5da96ce1f6d61d06fd417e65b5054464adc5f99f538ee3205301300e3bbfc1
3
  size 136989964
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:32b2ee780344f54d72a7778c20b9e0ae2298b9c3cc0577a7adb253fcae873e55
3
  size 270158266
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91e86b4ca69d10a97cd710c5f04480a72b525cad400cea245be68d7f877b810a
3
  size 270158266
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6744e6f6a39f22d53af65611a311fabf1e2f6900bc4f039649af461e3a04bcb9
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d11e662b15fafd271ac5933a58342ffd5fc9bdf20fc3ba21d9dc5a4d7cf6186c
3
  size 14244
last-checkpoint/rng_state_0.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:12ce5a78cf0ceaab8f9b8c7c054b9d2f6cf900bb9674288e7be0b539148ab70a
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e6af87013985ab57c4e29d50573f46694941fd8fddbf3534a07c5b8b5e70cd89
3
  size 15024
last-checkpoint/rng_state_1.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8cbac95fc850ca63e48aae2fc609444d4c2d56a0ab66827c371e030e05a4bddd
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:792d9b3b57b165e2ffca163e2f09f3baba7eb9f4f527f6f3c15a1c4173f6889c
3
  size 15024
last-checkpoint/rng_state_2.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fc05471ff7cef7eea1951b3b67f932237ba98787792acc0cd81fd8048f2c2b72
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c45dd29b8787989fd3f443e41b3fb2c6268bcaea9c905806bf6b3ebd386f2c5
3
  size 15024
last-checkpoint/rng_state_3.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:882729464717fa029c7bcee67aece963bee4b7f9329f52785885670c1d21e353
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:412526ad07301940fd28f88ebe6c15fb858d91196dd8253bcefaecd05cb341ed
3
  size 15024
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0cd4d8da32c9f49631e36330fe6a94ebc60af6fc242d8fe9f49a9281af029c38
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd14424febf05775817471baa584586dc24f272095138014ce37bfecc857c347
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": 0.10389433056116104,
3
  "best_model_checkpoint": "mgh6/TCS_Pair_base/checkpoint-650",
4
- "epoch": 0.2000235321802565,
5
  "eval_steps": 50,
6
- "global_step": 850,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -262,6 +262,21 @@
262
  "eval_samples_per_second": 2036.916,
263
  "eval_steps_per_second": 7.986,
264
  "step": 850
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
265
  }
266
  ],
267
  "logging_steps": 50,
@@ -276,7 +291,7 @@
276
  "early_stopping_threshold": 0.0
277
  },
278
  "attributes": {
279
- "early_stopping_patience_counter": 4
280
  }
281
  },
282
  "TrainerControl": {
@@ -285,7 +300,7 @@
285
  "should_evaluate": false,
286
  "should_log": false,
287
  "should_save": true,
288
- "should_training_stop": false
289
  },
290
  "attributes": {}
291
  }
 
1
  {
2
  "best_metric": 0.10389433056116104,
3
  "best_model_checkpoint": "mgh6/TCS_Pair_base/checkpoint-650",
4
+ "epoch": 0.21178962230850687,
5
  "eval_steps": 50,
6
+ "global_step": 900,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
262
  "eval_samples_per_second": 2036.916,
263
  "eval_steps_per_second": 7.986,
264
  "step": 850
265
+ },
266
+ {
267
+ "epoch": 0.21178962230850687,
268
+ "grad_norm": 0.712462306022644,
269
+ "learning_rate": 9.788185455401271e-05,
270
+ "loss": 0.0832,
271
+ "step": 900
272
+ },
273
+ {
274
+ "epoch": 0.21178962230850687,
275
+ "eval_loss": 0.10970053821802139,
276
+ "eval_runtime": 13.7864,
277
+ "eval_samples_per_second": 2035.119,
278
+ "eval_steps_per_second": 7.979,
279
+ "step": 900
280
  }
281
  ],
282
  "logging_steps": 50,
 
291
  "early_stopping_threshold": 0.0
292
  },
293
  "attributes": {
294
+ "early_stopping_patience_counter": 5
295
  }
296
  },
297
  "TrainerControl": {
 
300
  "should_evaluate": false,
301
  "should_log": false,
302
  "should_save": true,
303
+ "should_training_stop": true
304
  },
305
  "attributes": {}
306
  }