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
32ddfb5
·
verified ·
1 Parent(s): 0035ddd

Training in progress, step 26000, 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:a22f16e2dd2b29aa40f2175fb180759e3755c48afb9a7b16a4e40892ea1e8650
3
  size 301235464
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff5bec1c908d3674f0271db365b68b65eba5fcb240a0cdef465444744537e1b2
3
  size 301235464
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:821e030d21e90d9365e4c58bb2e1edf266aac9b33a64a2e640f2c249d1e73f51
3
  size 602335994
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:11bfd45a2b9dbe2a73500711ce838dcbec4327e5390757e20fb5c745b36e7ec1
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:b667d32288809b9fcfdf3fe2149eef069d72c05197267d06b59175efb787195f
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2f4f94ed5b86c54ed9f04920c1d057728a5c151ee0d04fd210f18196febf93b7
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b8c565830d05eccabcd7df396792d29e3638ccbd6988e240ff15902ef690b7e6
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ced8856b9ff194699de7fca54070bd17a17efd31d5f5d4d7e4c8ff1ec712ca9
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": 0.11925062904706822,
6
  "eval_steps": 500,
7
- "global_step": 25000,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -4458,11 +4458,189 @@
4458
  "eval_steps_per_second": 24.996,
4459
  "num_input_tokens_seen": 6553600000,
4460
  "step": 25000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
4461
  }
4462
  ],
4463
  "logging_steps": 50,
4464
  "max_steps": 70000,
4465
- "num_input_tokens_seen": 6553600000,
4466
  "num_train_epochs": 1,
4467
  "save_steps": 1000,
4468
  "stateful_callbacks": {
@@ -4477,7 +4655,7 @@
4477
  "attributes": {}
4478
  }
4479
  },
4480
- "total_flos": 1.753151963136e+18,
4481
  "train_batch_size": 64,
4482
  "trial_name": null,
4483
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.12402065420895095,
6
  "eval_steps": 500,
7
+ "global_step": 26000,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
4458
  "eval_steps_per_second": 24.996,
4459
  "num_input_tokens_seen": 6553600000,
4460
  "step": 25000
4461
+ },
4462
+ {
4463
+ "epoch": 0.11948913030516237,
4464
+ "grad_norm": 0.19173742830753326,
4465
+ "learning_rate": 0.001,
4466
+ "loss": 2.6871,
4467
+ "num_input_tokens_seen": 6566707200,
4468
+ "step": 25050
4469
+ },
4470
+ {
4471
+ "epoch": 0.1197276315632565,
4472
+ "grad_norm": 0.1746075600385666,
4473
+ "learning_rate": 0.001,
4474
+ "loss": 2.7003,
4475
+ "num_input_tokens_seen": 6579814400,
4476
+ "step": 25100
4477
+ },
4478
+ {
4479
+ "epoch": 0.11996613282135063,
4480
+ "grad_norm": 0.17817530035972595,
4481
+ "learning_rate": 0.001,
4482
+ "loss": 2.6944,
4483
+ "num_input_tokens_seen": 6592921600,
4484
+ "step": 25150
4485
+ },
4486
+ {
4487
+ "epoch": 0.12020463407944477,
4488
+ "grad_norm": 0.201807901263237,
4489
+ "learning_rate": 0.001,
4490
+ "loss": 2.6766,
4491
+ "num_input_tokens_seen": 6606028800,
4492
+ "step": 25200
4493
+ },
4494
+ {
4495
+ "epoch": 0.1204431353375389,
4496
+ "grad_norm": 0.18620917201042175,
4497
+ "learning_rate": 0.001,
4498
+ "loss": 2.6802,
4499
+ "num_input_tokens_seen": 6619136000,
4500
+ "step": 25250
4501
+ },
4502
+ {
4503
+ "epoch": 0.12068163659563304,
4504
+ "grad_norm": 0.17383818328380585,
4505
+ "learning_rate": 0.001,
4506
+ "loss": 2.6698,
4507
+ "num_input_tokens_seen": 6632243200,
4508
+ "step": 25300
4509
+ },
4510
+ {
4511
+ "epoch": 0.12092013785372718,
4512
+ "grad_norm": 0.1766287237405777,
4513
+ "learning_rate": 0.001,
4514
+ "loss": 2.6705,
4515
+ "num_input_tokens_seen": 6645350400,
4516
+ "step": 25350
4517
+ },
4518
+ {
4519
+ "epoch": 0.12115863911182131,
4520
+ "grad_norm": 0.19551052153110504,
4521
+ "learning_rate": 0.001,
4522
+ "loss": 2.678,
4523
+ "num_input_tokens_seen": 6658457600,
4524
+ "step": 25400
4525
+ },
4526
+ {
4527
+ "epoch": 0.12139714036991545,
4528
+ "grad_norm": 0.18625982105731964,
4529
+ "learning_rate": 0.001,
4530
+ "loss": 2.6688,
4531
+ "num_input_tokens_seen": 6671564800,
4532
+ "step": 25450
4533
+ },
4534
+ {
4535
+ "epoch": 0.12163564162800959,
4536
+ "grad_norm": 0.18274050951004028,
4537
+ "learning_rate": 0.001,
4538
+ "loss": 2.6818,
4539
+ "num_input_tokens_seen": 6684672000,
4540
+ "step": 25500
4541
+ },
4542
+ {
4543
+ "epoch": 0.12163564162800959,
4544
+ "eval_loss": 2.5602569580078125,
4545
+ "eval_runtime": 50.4187,
4546
+ "eval_samples_per_second": 99.17,
4547
+ "eval_steps_per_second": 24.792,
4548
+ "num_input_tokens_seen": 6684672000,
4549
+ "step": 25500
4550
+ },
4551
+ {
4552
+ "epoch": 0.12187414288610372,
4553
+ "grad_norm": 0.18547837436199188,
4554
+ "learning_rate": 0.001,
4555
+ "loss": 2.6754,
4556
+ "num_input_tokens_seen": 6697779200,
4557
+ "step": 25550
4558
+ },
4559
+ {
4560
+ "epoch": 0.12211264414419785,
4561
+ "grad_norm": 0.18558937311172485,
4562
+ "learning_rate": 0.001,
4563
+ "loss": 2.6767,
4564
+ "num_input_tokens_seen": 6710886400,
4565
+ "step": 25600
4566
+ },
4567
+ {
4568
+ "epoch": 0.122351145402292,
4569
+ "grad_norm": 0.17276135087013245,
4570
+ "learning_rate": 0.001,
4571
+ "loss": 2.6775,
4572
+ "num_input_tokens_seen": 6723993600,
4573
+ "step": 25650
4574
+ },
4575
+ {
4576
+ "epoch": 0.12258964666038613,
4577
+ "grad_norm": 0.18483039736747742,
4578
+ "learning_rate": 0.001,
4579
+ "loss": 2.6818,
4580
+ "num_input_tokens_seen": 6737100800,
4581
+ "step": 25700
4582
+ },
4583
+ {
4584
+ "epoch": 0.12282814791848028,
4585
+ "grad_norm": 0.18036937713623047,
4586
+ "learning_rate": 0.001,
4587
+ "loss": 2.6669,
4588
+ "num_input_tokens_seen": 6750208000,
4589
+ "step": 25750
4590
+ },
4591
+ {
4592
+ "epoch": 0.12306664917657441,
4593
+ "grad_norm": 0.1728815734386444,
4594
+ "learning_rate": 0.001,
4595
+ "loss": 2.6789,
4596
+ "num_input_tokens_seen": 6763315200,
4597
+ "step": 25800
4598
+ },
4599
+ {
4600
+ "epoch": 0.12330515043466854,
4601
+ "grad_norm": 0.19193877279758453,
4602
+ "learning_rate": 0.001,
4603
+ "loss": 2.6487,
4604
+ "num_input_tokens_seen": 6776422400,
4605
+ "step": 25850
4606
+ },
4607
+ {
4608
+ "epoch": 0.12354365169276268,
4609
+ "grad_norm": 0.1584886610507965,
4610
+ "learning_rate": 0.001,
4611
+ "loss": 2.6638,
4612
+ "num_input_tokens_seen": 6789529600,
4613
+ "step": 25900
4614
+ },
4615
+ {
4616
+ "epoch": 0.12378215295085682,
4617
+ "grad_norm": 0.18792498111724854,
4618
+ "learning_rate": 0.001,
4619
+ "loss": 2.6754,
4620
+ "num_input_tokens_seen": 6802636800,
4621
+ "step": 25950
4622
+ },
4623
+ {
4624
+ "epoch": 0.12402065420895095,
4625
+ "grad_norm": 0.1689581423997879,
4626
+ "learning_rate": 0.001,
4627
+ "loss": 2.6682,
4628
+ "num_input_tokens_seen": 6815744000,
4629
+ "step": 26000
4630
+ },
4631
+ {
4632
+ "epoch": 0.12402065420895095,
4633
+ "eval_loss": 2.5587522983551025,
4634
+ "eval_runtime": 50.7858,
4635
+ "eval_samples_per_second": 98.453,
4636
+ "eval_steps_per_second": 24.613,
4637
+ "num_input_tokens_seen": 6815744000,
4638
+ "step": 26000
4639
  }
4640
  ],
4641
  "logging_steps": 50,
4642
  "max_steps": 70000,
4643
+ "num_input_tokens_seen": 6815744000,
4644
  "num_train_epochs": 1,
4645
  "save_steps": 1000,
4646
  "stateful_callbacks": {
 
4655
  "attributes": {}
4656
  }
4657
  },
4658
+ "total_flos": 1.82327804166144e+18,
4659
  "train_batch_size": 64,
4660
  "trial_name": null,
4661
  "trial_params": null