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
626ab01
·
verified ·
1 Parent(s): eba9c11

Training in progress, step 32000, 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 sha256:70f1cdddb9f75a2fd759bfc8b301efce489dff346384028ee1a1e25b8ab6c007
3
  size 301235464
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2cef3edc11233bd02d8a0fce925583abfb5c9dd14aa68691d119c85f02da0c2c
3
  size 301235464
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:476450d57fc5db9120e50036dbb2e57619d711c16c3c3c582090ea71796feba0
3
  size 602335994
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:802c539bacfaec7683d6ba2f0a942347dfcc3e86cdff0695306776a8172eb9e5
3
  size 602335994
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1899a3d78ad5399a3069709cf6568cbc2795c59a09fc2c0ae16ae590f002b504
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bee3fafd3f39d206bc71937649788266030036a262f517651404c02bc2d21bc8
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:277f21680b959b596662b48a96a00aaa486d9a86675c2da90af20e0783552321
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b45d7a8e84e284c770af40e442ab0efb2fec2b035c2481cdfd246cdf35d0dd1
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": 0.1478707800183646,
6
  "eval_steps": 500,
7
- "global_step": 31000,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -5526,11 +5526,189 @@
5526
  "eval_steps_per_second": 24.969,
5527
  "num_input_tokens_seen": 8126464000,
5528
  "step": 31000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
5529
  }
5530
  ],
5531
  "logging_steps": 50,
5532
  "max_steps": 70000,
5533
- "num_input_tokens_seen": 8126464000,
5534
  "num_train_epochs": 1,
5535
  "save_steps": 1000,
5536
  "stateful_callbacks": {
@@ -5545,7 +5723,7 @@
5545
  "attributes": {}
5546
  }
5547
  },
5548
- "total_flos": 2.17390843428864e+18,
5549
  "train_batch_size": 64,
5550
  "trial_name": null,
5551
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.15264080518024734,
6
  "eval_steps": 500,
7
+ "global_step": 32000,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
5526
  "eval_steps_per_second": 24.969,
5527
  "num_input_tokens_seen": 8126464000,
5528
  "step": 31000
5529
+ },
5530
+ {
5531
+ "epoch": 0.14810928127645873,
5532
+ "grad_norm": 0.20207786560058594,
5533
+ "learning_rate": 0.001,
5534
+ "loss": 2.6493,
5535
+ "num_input_tokens_seen": 8139571200,
5536
+ "step": 31050
5537
+ },
5538
+ {
5539
+ "epoch": 0.14834778253455286,
5540
+ "grad_norm": 0.20135898888111115,
5541
+ "learning_rate": 0.001,
5542
+ "loss": 2.6555,
5543
+ "num_input_tokens_seen": 8152678400,
5544
+ "step": 31100
5545
+ },
5546
+ {
5547
+ "epoch": 0.14858628379264702,
5548
+ "grad_norm": 0.19284267723560333,
5549
+ "learning_rate": 0.001,
5550
+ "loss": 2.6637,
5551
+ "num_input_tokens_seen": 8165785600,
5552
+ "step": 31150
5553
+ },
5554
+ {
5555
+ "epoch": 0.14882478505074115,
5556
+ "grad_norm": 0.17214693129062653,
5557
+ "learning_rate": 0.001,
5558
+ "loss": 2.6663,
5559
+ "num_input_tokens_seen": 8178892800,
5560
+ "step": 31200
5561
+ },
5562
+ {
5563
+ "epoch": 0.14906328630883528,
5564
+ "grad_norm": 0.19444549083709717,
5565
+ "learning_rate": 0.001,
5566
+ "loss": 2.6541,
5567
+ "num_input_tokens_seen": 8192000000,
5568
+ "step": 31250
5569
+ },
5570
+ {
5571
+ "epoch": 0.1493017875669294,
5572
+ "grad_norm": 0.19992901384830475,
5573
+ "learning_rate": 0.001,
5574
+ "loss": 2.6419,
5575
+ "num_input_tokens_seen": 8205107200,
5576
+ "step": 31300
5577
+ },
5578
+ {
5579
+ "epoch": 0.14954028882502354,
5580
+ "grad_norm": 0.16732315719127655,
5581
+ "learning_rate": 0.001,
5582
+ "loss": 2.6559,
5583
+ "num_input_tokens_seen": 8218214400,
5584
+ "step": 31350
5585
+ },
5586
+ {
5587
+ "epoch": 0.1497787900831177,
5588
+ "grad_norm": 0.4210798442363739,
5589
+ "learning_rate": 0.001,
5590
+ "loss": 2.6478,
5591
+ "num_input_tokens_seen": 8231321600,
5592
+ "step": 31400
5593
+ },
5594
+ {
5595
+ "epoch": 0.15001729134121183,
5596
+ "grad_norm": 0.2139436900615692,
5597
+ "learning_rate": 0.001,
5598
+ "loss": 2.6753,
5599
+ "num_input_tokens_seen": 8244428800,
5600
+ "step": 31450
5601
+ },
5602
+ {
5603
+ "epoch": 0.15025579259930597,
5604
+ "grad_norm": 0.19131046533584595,
5605
+ "learning_rate": 0.001,
5606
+ "loss": 2.6675,
5607
+ "num_input_tokens_seen": 8257536000,
5608
+ "step": 31500
5609
+ },
5610
+ {
5611
+ "epoch": 0.15025579259930597,
5612
+ "eval_loss": 2.5402350425720215,
5613
+ "eval_runtime": 50.477,
5614
+ "eval_samples_per_second": 99.055,
5615
+ "eval_steps_per_second": 24.764,
5616
+ "num_input_tokens_seen": 8257536000,
5617
+ "step": 31500
5618
+ },
5619
+ {
5620
+ "epoch": 0.1504942938574001,
5621
+ "grad_norm": 0.20711492002010345,
5622
+ "learning_rate": 0.001,
5623
+ "loss": 2.6654,
5624
+ "num_input_tokens_seen": 8270643200,
5625
+ "step": 31550
5626
+ },
5627
+ {
5628
+ "epoch": 0.15073279511549423,
5629
+ "grad_norm": 0.1888076812028885,
5630
+ "learning_rate": 0.001,
5631
+ "loss": 2.6603,
5632
+ "num_input_tokens_seen": 8283750400,
5633
+ "step": 31600
5634
+ },
5635
+ {
5636
+ "epoch": 0.15097129637358836,
5637
+ "grad_norm": 0.18534335494041443,
5638
+ "learning_rate": 0.001,
5639
+ "loss": 2.6539,
5640
+ "num_input_tokens_seen": 8296857600,
5641
+ "step": 31650
5642
+ },
5643
+ {
5644
+ "epoch": 0.15120979763168252,
5645
+ "grad_norm": 0.2024192214012146,
5646
+ "learning_rate": 0.001,
5647
+ "loss": 2.6514,
5648
+ "num_input_tokens_seen": 8309964800,
5649
+ "step": 31700
5650
+ },
5651
+ {
5652
+ "epoch": 0.15144829888977665,
5653
+ "grad_norm": 0.18967773020267487,
5654
+ "learning_rate": 0.001,
5655
+ "loss": 2.6457,
5656
+ "num_input_tokens_seen": 8323072000,
5657
+ "step": 31750
5658
+ },
5659
+ {
5660
+ "epoch": 0.15168680014787078,
5661
+ "grad_norm": 0.18823806941509247,
5662
+ "learning_rate": 0.001,
5663
+ "loss": 2.6579,
5664
+ "num_input_tokens_seen": 8336179200,
5665
+ "step": 31800
5666
+ },
5667
+ {
5668
+ "epoch": 0.1519253014059649,
5669
+ "grad_norm": 0.20198485255241394,
5670
+ "learning_rate": 0.001,
5671
+ "loss": 2.6623,
5672
+ "num_input_tokens_seen": 8349286400,
5673
+ "step": 31850
5674
+ },
5675
+ {
5676
+ "epoch": 0.15216380266405904,
5677
+ "grad_norm": 0.19362477958202362,
5678
+ "learning_rate": 0.001,
5679
+ "loss": 2.6473,
5680
+ "num_input_tokens_seen": 8362393600,
5681
+ "step": 31900
5682
+ },
5683
+ {
5684
+ "epoch": 0.15240230392215318,
5685
+ "grad_norm": 0.18454812467098236,
5686
+ "learning_rate": 0.001,
5687
+ "loss": 2.6411,
5688
+ "num_input_tokens_seen": 8375500800,
5689
+ "step": 31950
5690
+ },
5691
+ {
5692
+ "epoch": 0.15264080518024734,
5693
+ "grad_norm": 0.1968630850315094,
5694
+ "learning_rate": 0.001,
5695
+ "loss": 2.6405,
5696
+ "num_input_tokens_seen": 8388608000,
5697
+ "step": 32000
5698
+ },
5699
+ {
5700
+ "epoch": 0.15264080518024734,
5701
+ "eval_loss": 2.5325138568878174,
5702
+ "eval_runtime": 51.0134,
5703
+ "eval_samples_per_second": 98.013,
5704
+ "eval_steps_per_second": 24.503,
5705
+ "num_input_tokens_seen": 8388608000,
5706
+ "step": 32000
5707
  }
5708
  ],
5709
  "logging_steps": 50,
5710
  "max_steps": 70000,
5711
+ "num_input_tokens_seen": 8388608000,
5712
  "num_train_epochs": 1,
5713
  "save_steps": 1000,
5714
  "stateful_callbacks": {
 
5723
  "attributes": {}
5724
  }
5725
  },
5726
+ "total_flos": 2.24403451281408e+18,
5727
  "train_batch_size": 64,
5728
  "trial_name": null,
5729
  "trial_params": null