Hugging Face's logo

Azrail
/
smallm_70

Text Generation
Transformers
Safetensors
English
smallm
transformer
language-model
experimental
conversational
custom_code
Model card Files
xet
 Community
Azrail commited on
Commit
906e5e4
·
verified ·
1 Parent(s): 4e56ae7

Training in progress, step 37000, checkpoint

Browse files
Files changed (5) 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/scheduler.pt +1 -1
  5. last-checkpoint/trainer_state.json +182 -4
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3d32729aeb48161cbdc54b05ec5cbc234135d345a2bc5ca5566ff54b08196dde
3
  size 301235464
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:34963d5c26d5ee100ad78ff70d6babf6454b60ab86262514f0fba74286fe480c
3
  size 301235464
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a567d16611a25ca9a7afd735d1dc2d70458501ccb5e7c9f4823c5baf838db1d8
3
  size 602335994
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:53cdb7b7679aca9d40cce25304d61b08c05ada6ed86bf14d1de5660c21278776
3
  size 602335994
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3838e67d8efd23149e101bbfd0e2039c1de5341a7fd4f1a0cf8de1b3c5587f7e
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c573cfef4ade4dee5492002b343d03eedb5c0a687c2c578260100ad349b1098
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c5a2a9a97378c1b7631d78a28de277749231ad65f077c045df73323c2c2b85da
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:90815e584013ee668de6d5b656c515902fbacbb32f54a71d2d1d29e05110019f
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -2,9 +2,9 @@
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
- "epoch": 0.17172090582777824,
6
  "eval_steps": 500,
7
- "global_step": 36000,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -6416,11 +6416,189 @@
6416
  "eval_steps_per_second": 24.302,
6417
  "num_input_tokens_seen": 9437179456,
6418
  "step": 36000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
6419
  }
6420
  ],
6421
  "logging_steps": 50,
6422
  "max_steps": 70000,
6423
- "num_input_tokens_seen": 9437179456,
6424
  "num_train_epochs": 1,
6425
  "save_steps": 1000,
6426
  "stateful_callbacks": {
@@ -6435,7 +6613,7 @@
6435
  "attributes": {}
6436
  }
6437
  },
6438
- "total_flos": 2.5245376113514906e+18,
6439
  "train_batch_size": 64,
6440
  "trial_name": null,
6441
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.17649093098966098,
6
  "eval_steps": 500,
7
+ "global_step": 37000,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
6416
  "eval_steps_per_second": 24.302,
6417
  "num_input_tokens_seen": 9437179456,
6418
  "step": 36000
6419
+ },
6420
+ {
6421
+ "epoch": 0.17195940708587237,
6422
+ "grad_norm": 0.19696597754955292,
6423
+ "learning_rate": 0.001,
6424
+ "loss": 2.6521,
6425
+ "num_input_tokens_seen": 9450286656,
6426
+ "step": 36050
6427
+ },
6428
+ {
6429
+ "epoch": 0.1721979083439665,
6430
+ "grad_norm": 0.18839424848556519,
6431
+ "learning_rate": 0.001,
6432
+ "loss": 2.6484,
6433
+ "num_input_tokens_seen": 9463393856,
6434
+ "step": 36100
6435
+ },
6436
+ {
6437
+ "epoch": 0.17243640960206066,
6438
+ "grad_norm": 0.33748558163642883,
6439
+ "learning_rate": 0.001,
6440
+ "loss": 2.6496,
6441
+ "num_input_tokens_seen": 9476501056,
6442
+ "step": 36150
6443
+ },
6444
+ {
6445
+ "epoch": 0.1726749108601548,
6446
+ "grad_norm": 0.19529207050800323,
6447
+ "learning_rate": 0.001,
6448
+ "loss": 2.6484,
6449
+ "num_input_tokens_seen": 9489608256,
6450
+ "step": 36200
6451
+ },
6452
+ {
6453
+ "epoch": 0.17291341211824893,
6454
+ "grad_norm": 0.21542242169380188,
6455
+ "learning_rate": 0.001,
6456
+ "loss": 2.6572,
6457
+ "num_input_tokens_seen": 9502715456,
6458
+ "step": 36250
6459
+ },
6460
+ {
6461
+ "epoch": 0.17315191337634306,
6462
+ "grad_norm": 0.37017494440078735,
6463
+ "learning_rate": 0.001,
6464
+ "loss": 2.6517,
6465
+ "num_input_tokens_seen": 9515822656,
6466
+ "step": 36300
6467
+ },
6468
+ {
6469
+ "epoch": 0.1733904146344372,
6470
+ "grad_norm": 0.27284151315689087,
6471
+ "learning_rate": 0.001,
6472
+ "loss": 2.66,
6473
+ "num_input_tokens_seen": 9528929856,
6474
+ "step": 36350
6475
+ },
6476
+ {
6477
+ "epoch": 0.17362891589253132,
6478
+ "grad_norm": 0.4666242003440857,
6479
+ "learning_rate": 0.001,
6480
+ "loss": 2.6514,
6481
+ "num_input_tokens_seen": 9542037056,
6482
+ "step": 36400
6483
+ },
6484
+ {
6485
+ "epoch": 0.17386741715062548,
6486
+ "grad_norm": 0.2031467854976654,
6487
+ "learning_rate": 0.001,
6488
+ "loss": 2.6577,
6489
+ "num_input_tokens_seen": 9555144256,
6490
+ "step": 36450
6491
+ },
6492
+ {
6493
+ "epoch": 0.1741059184087196,
6494
+ "grad_norm": 0.2086576223373413,
6495
+ "learning_rate": 0.001,
6496
+ "loss": 2.6372,
6497
+ "num_input_tokens_seen": 9568251456,
6498
+ "step": 36500
6499
+ },
6500
+ {
6501
+ "epoch": 0.1741059184087196,
6502
+ "eval_loss": 2.5252223014831543,
6503
+ "eval_runtime": 51.1282,
6504
+ "eval_samples_per_second": 97.793,
6505
+ "eval_steps_per_second": 24.448,
6506
+ "num_input_tokens_seen": 9568251456,
6507
+ "step": 36500
6508
+ },
6509
+ {
6510
+ "epoch": 0.17434441966681374,
6511
+ "grad_norm": 0.19739161431789398,
6512
+ "learning_rate": 0.001,
6513
+ "loss": 2.6184,
6514
+ "num_input_tokens_seen": 9581358656,
6515
+ "step": 36550
6516
+ },
6517
+ {
6518
+ "epoch": 0.17458292092490788,
6519
+ "grad_norm": 0.22384846210479736,
6520
+ "learning_rate": 0.001,
6521
+ "loss": 2.6504,
6522
+ "num_input_tokens_seen": 9594465856,
6523
+ "step": 36600
6524
+ },
6525
+ {
6526
+ "epoch": 0.174821422183002,
6527
+ "grad_norm": 0.2055511772632599,
6528
+ "learning_rate": 0.001,
6529
+ "loss": 2.6333,
6530
+ "num_input_tokens_seen": 9607573056,
6531
+ "step": 36650
6532
+ },
6533
+ {
6534
+ "epoch": 0.17505992344109614,
6535
+ "grad_norm": 0.18193551898002625,
6536
+ "learning_rate": 0.001,
6537
+ "loss": 2.6518,
6538
+ "num_input_tokens_seen": 9620680256,
6539
+ "step": 36700
6540
+ },
6541
+ {
6542
+ "epoch": 0.1752984246991903,
6543
+ "grad_norm": 0.1968860775232315,
6544
+ "learning_rate": 0.001,
6545
+ "loss": 2.6211,
6546
+ "num_input_tokens_seen": 9633787456,
6547
+ "step": 36750
6548
+ },
6549
+ {
6550
+ "epoch": 0.17553692595728443,
6551
+ "grad_norm": 0.20429988205432892,
6552
+ "learning_rate": 0.001,
6553
+ "loss": 2.6269,
6554
+ "num_input_tokens_seen": 9646894656,
6555
+ "step": 36800
6556
+ },
6557
+ {
6558
+ "epoch": 0.17577542721537856,
6559
+ "grad_norm": 0.18364110589027405,
6560
+ "learning_rate": 0.001,
6561
+ "loss": 2.6337,
6562
+ "num_input_tokens_seen": 9660001856,
6563
+ "step": 36850
6564
+ },
6565
+ {
6566
+ "epoch": 0.1760139284734727,
6567
+ "grad_norm": 0.2051621973514557,
6568
+ "learning_rate": 0.001,
6569
+ "loss": 2.6297,
6570
+ "num_input_tokens_seen": 9673109056,
6571
+ "step": 36900
6572
+ },
6573
+ {
6574
+ "epoch": 0.17625242973156682,
6575
+ "grad_norm": 0.25841349363327026,
6576
+ "learning_rate": 0.001,
6577
+ "loss": 2.6678,
6578
+ "num_input_tokens_seen": 9686216256,
6579
+ "step": 36950
6580
+ },
6581
+ {
6582
+ "epoch": 0.17649093098966098,
6583
+ "grad_norm": 0.198688805103302,
6584
+ "learning_rate": 0.001,
6585
+ "loss": 2.6521,
6586
+ "num_input_tokens_seen": 9699323456,
6587
+ "step": 37000
6588
+ },
6589
+ {
6590
+ "epoch": 0.17649093098966098,
6591
+ "eval_loss": 2.5248863697052,
6592
+ "eval_runtime": 51.363,
6593
+ "eval_samples_per_second": 97.346,
6594
+ "eval_steps_per_second": 24.337,
6595
+ "num_input_tokens_seen": 9699323456,
6596
+ "step": 37000
6597
  }
6598
  ],
6599
  "logging_steps": 50,
6600
  "max_steps": 70000,
6601
+ "num_input_tokens_seen": 9699323456,
6602
  "num_train_epochs": 1,
6603
  "save_steps": 1000,
6604
  "stateful_callbacks": {
 
6613
  "attributes": {}
6614
  }
6615
  },
6616
+ "total_flos": 2.5946636898769306e+18,
6617
  "train_batch_size": 64,
6618
  "trial_name": null,
6619
  "trial_params": null