AlekseyKorshuk commited on
Commit
742dd5b
1 Parent(s): ebd4b29

huggingartists

Browse files
README.md CHANGED
@@ -45,15 +45,15 @@ from datasets import load_dataset
45
  dataset = load_dataset("huggingartists/eminem")
46
  ```
47
 
48
- [Explore the data](https://wandb.ai/huggingartists/huggingartists/runs/w7y07ejq/artifacts), which is tracked with [W&B artifacts](https://docs.wandb.com/artifacts) at every step of the pipeline.
49
 
50
  ## Training procedure
51
 
52
  The model is based on a pre-trained [GPT-2](https://huggingface.co/gpt2) which is fine-tuned on Eminem's lyrics.
53
 
54
- Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/1j6e92ir) for full transparency and reproducibility.
55
 
56
- At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/1j6e92ir/artifacts) is logged and versioned.
57
 
58
  ## How to use
59
 
 
45
  dataset = load_dataset("huggingartists/eminem")
46
  ```
47
 
48
+ [Explore the data](https://wandb.ai/huggingartists/huggingartists/runs/3j11lytq/artifacts), which is tracked with [W&B artifacts](https://docs.wandb.com/artifacts) at every step of the pipeline.
49
 
50
  ## Training procedure
51
 
52
  The model is based on a pre-trained [GPT-2](https://huggingface.co/gpt2) which is fine-tuned on Eminem's lyrics.
53
 
54
+ Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/1zieygbg) for full transparency and reproducibility.
55
 
56
+ At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/1zieygbg/artifacts) is logged and versioned.
57
 
58
  ## How to use
59
 
evaluation.txt CHANGED
@@ -1 +1 @@
1
- {"eval_loss": 2.026026487350464, "eval_runtime": 32.1272, "eval_samples_per_second": 20.699, "eval_steps_per_second": 2.615, "epoch": 5.0}
 
1
+ {"eval_loss": 1.8596649169921875, "eval_runtime": 29.521, "eval_samples_per_second": 21.138, "eval_steps_per_second": 2.642, "epoch": 2.0}
flax_model.msgpack CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:464d4e7e6e4c6382358d88fef714b72f5deae64e28bfb5b9bf00f9ff6030918b
3
  size 497764120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b135877e250da289f866a54700c125f37a80174dcc1e12dfb1f5dbd2249cdec2
3
  size 497764120
optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9f578f796fe425b739c57c93d4870307639bdede01ade17192cbfd7dade1337c
3
  size 995604017
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eecd9ef518643711b9927ae1f9897be18a83cabb4c9d4cb783637ffd91b94e92
3
  size 995604017
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5744d9da42094b4502ba2c2c52176dfb839e8656df36cf0783b4832a5444d42b
3
  size 510403817
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d63665b8addacc515cc738fbaa06e7fafcd26d90f9625949551144aaa6f57495
3
  size 510403817
rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1bd5d70a0d7170f2240ff3effc84cd6446ab98ec4b12f17cec590991fb7f5f94
3
- size 14503
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c4cd04e3d531ff616086aabe0842d017287cb7d6aa18753bc57ea83f5c6ec09
3
+ size 14567
scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5606edb00c1d85c79a7e6e65c60470a6b50e72dc1246597e70873019f5c126ed
3
  size 623
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6cde66d2336c18c91f6044376f78eeeea90a1182517e78de002b9f811e407360
3
  size 623
trainer_state.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
- "best_metric": 2.026026487350464,
3
- "best_model_checkpoint": "output/eminem/checkpoint-452",
4
  "epoch": 1.0,
5
- "global_step": 452,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
@@ -554,11 +554,25 @@
554
  "eval_samples_per_second": 20.779,
555
  "eval_steps_per_second": 2.625,
556
  "step": 452
 
 
 
 
 
 
 
 
 
 
 
 
 
 
557
  }
558
  ],
559
- "max_steps": 2260,
560
- "num_train_epochs": 5,
561
- "total_flos": 472024055808000.0,
562
  "trial_name": null,
563
  "trial_params": null
564
  }
 
1
  {
2
+ "best_metric": 1.8596649169921875,
3
+ "best_model_checkpoint": "output/eminem/checkpoint-457",
4
  "epoch": 1.0,
5
+ "global_step": 457,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
 
554
  "eval_samples_per_second": 20.779,
555
  "eval_steps_per_second": 2.625,
556
  "step": 452
557
+ },
558
+ {
559
+ "epoch": 1.0,
560
+ "learning_rate": 1.757624254440622e-06,
561
+ "loss": 2.2171,
562
+ "step": 455
563
+ },
564
+ {
565
+ "epoch": 1.0,
566
+ "eval_loss": 1.8596649169921875,
567
+ "eval_runtime": 29.8564,
568
+ "eval_samples_per_second": 20.9,
569
+ "eval_steps_per_second": 2.613,
570
+ "step": 457
571
  }
572
  ],
573
+ "max_steps": 914,
574
+ "num_train_epochs": 2,
575
+ "total_flos": 476857958400000.0,
576
  "trial_name": null,
577
  "trial_params": null
578
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:42cd89b75d7c0f3fe6da69fe6e477354496b002c63ce374ba6ee57264a045ed7
3
  size 2671
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a79cbab9dd97447de0d3db9f15d21e846aff0e011af608b06d64e13678d93e8a
3
  size 2671