Hugging Face's logo

lyan62
/
ar_norm_input_cosine

Transformers
PyTorch
pixel
Inference Endpoints
Model card Files Community
lyan62 commited on
Commit
6b50247
•
1 Parent(s): 762e797

Training in progress, step 220000

Browse files
Files changed (10) hide show
  1. last-checkpoint/optimizer.pt +1 -1
  2. last-checkpoint/pytorch_model.bin +1 -1
  3. last-checkpoint/rng_state_0.pth +1 -1
  4. last-checkpoint/rng_state_1.pth +1 -1
  5. last-checkpoint/rng_state_2.pth +1 -1
  6. last-checkpoint/rng_state_3.pth +1 -1
  7. last-checkpoint/scaler.pt +1 -1
  8. last-checkpoint/scheduler.pt +1 -1
  9. last-checkpoint/trainer_state.json +62 -2
  10. pytorch_model.bin +1 -1
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9e83e911431daddbb5fb07546fcd0ead35a24a9d92caf98379399cb3838b4b73
3
  size 402588883
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:23ad25468e4976ad356c489ff9de5e4c29c45d72b9ad898ab44604c1735d5242
3
  size 402588883
last-checkpoint/pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b64554b1d34db97dfdbb800052b39ab43a21dec4e876d8b88d7b75afdcefbe88
3
  size 201355195
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:81504f00d1476d46795ad7661bb9dd3cce0e3b34e6dbb42a795318db4fca7d75
3
  size 201355195
last-checkpoint/rng_state_0.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b87eefc0a506b1050cb06c38c784da5f6b4431ded291f8c7b8382ea602c6b00d
3
  size 14503
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee2707666e6c7a8def868f81ca47e73ce94f4a6c51cea81c3c277b3144ea3665
3
  size 14503
last-checkpoint/rng_state_1.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:11d8f5d8f125cd22a6ad5c501ed968acc092a0af6afb6186ba7d3d4be0c715e3
3
  size 14503
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2fe453041a1ef69b9f76a6ad7eaaaabaa16df5e5897736ce1fd0389d49af5e8d
3
  size 14503
last-checkpoint/rng_state_2.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d76923756bc10bf0153eff8cd1f84631296a2fa97d8a64a30bb5a36a533e1119
3
  size 14503
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:10d49f5030c11ac17c769e132afcac76be5010c8f6689315786413bc5d6a1915
3
  size 14503
last-checkpoint/rng_state_3.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f6e0f0c845a4ed1511dd45a62a8a544c473a93c4a6e6df62309fc4f47cf7e634
3
  size 14503
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:023e578a11b41b3489c2463eeb4e215ba05a1e3d40fd6a117618630fc634702a
3
  size 14503
last-checkpoint/scaler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e4eb1b41c7c061aff1a8cf4d4b29ca4f1b06eb8036887e7db173c41b67cce439
3
  size 559
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e92b0700bb181d8ec04bb405e4281e6135a07379cd92ad2d3e2e3a7f7d5ff4d
3
  size 559
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a29aa394da4020a18d0273538f9a534d932e35dbf12a0267366fecf45a649ba9
3
  size 623
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c1c26bd3f13243d197acaedea2ad1ddc3602f0e2685b06d1fa05a341140be98
3
  size 623
last-checkpoint/trainer_state.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 3.6595744680851063,
5
- "global_step": 215000,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
@@ -2586,6 +2586,66 @@
2586
  "learning_rate": 9.530522177949888e-05,
2587
  "loss": 0.3326,
2588
  "step": 215000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2589
  }
2590
  ],
2591
  "max_steps": 500000,
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 3.74468085106383,
5
+ "global_step": 220000,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
 
2586
  "learning_rate": 9.530522177949888e-05,
2587
  "loss": 0.3326,
2588
  "step": 215000
2589
+ },
2590
+ {
2591
+ "epoch": 3.67,
2592
+ "learning_rate": 9.509098552481625e-05,
2593
+ "loss": 0.3326,
2594
+ "step": 215500
2595
+ },
2596
+ {
2597
+ "epoch": 3.68,
2598
+ "learning_rate": 9.487617114738049e-05,
2599
+ "loss": 0.3326,
2600
+ "step": 216000
2601
+ },
2602
+ {
2603
+ "epoch": 3.69,
2604
+ "learning_rate": 9.466164001565799e-05,
2605
+ "loss": 0.333,
2606
+ "step": 216500
2607
+ },
2608
+ {
2609
+ "epoch": 3.69,
2610
+ "learning_rate": 9.444653440347767e-05,
2611
+ "loss": 0.3327,
2612
+ "step": 217000
2613
+ },
2614
+ {
2615
+ "epoch": 3.7,
2616
+ "learning_rate": 9.423128620983511e-05,
2617
+ "loss": 0.3324,
2618
+ "step": 217500
2619
+ },
2620
+ {
2621
+ "epoch": 3.71,
2622
+ "learning_rate": 9.401589755914307e-05,
2623
+ "loss": 0.3324,
2624
+ "step": 218000
2625
+ },
2626
+ {
2627
+ "epoch": 3.72,
2628
+ "learning_rate": 9.380037057720053e-05,
2629
+ "loss": 0.3321,
2630
+ "step": 218500
2631
+ },
2632
+ {
2633
+ "epoch": 3.73,
2634
+ "learning_rate": 9.358470739117187e-05,
2635
+ "loss": 0.3322,
2636
+ "step": 219000
2637
+ },
2638
+ {
2639
+ "epoch": 3.74,
2640
+ "learning_rate": 9.336891012956562e-05,
2641
+ "loss": 0.3321,
2642
+ "step": 219500
2643
+ },
2644
+ {
2645
+ "epoch": 3.74,
2646
+ "learning_rate": 9.31529809222136e-05,
2647
+ "loss": 0.3317,
2648
+ "step": 220000
2649
  }
2650
  ],
2651
  "max_steps": 500000,
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b64554b1d34db97dfdbb800052b39ab43a21dec4e876d8b88d7b75afdcefbe88
3
  size 201355195
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:81504f00d1476d46795ad7661bb9dd3cce0e3b34e6dbb42a795318db4fca7d75
3
  size 201355195