AlekseyKorshuk commited on
Commit
b5b1787
1 Parent(s): 2ecbf23

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/2mu8rlhb/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/1q4coblt) for full transparency and reproducibility.
55
 
56
- At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/1q4coblt/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/4s2qerso/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/1ck5hcvf) for full transparency and reproducibility.
55
 
56
+ At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/1ck5hcvf/artifacts) is logged and versioned.
57
 
58
  ## How to use
59
 
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "huggingartists/eminem",
3
  "activation_function": "gelu_new",
4
  "architectures": [
5
  "GPT2LMHeadModel"
@@ -37,7 +37,7 @@
37
  }
38
  },
39
  "torch_dtype": "float32",
40
- "transformers_version": "4.12.3",
41
  "use_cache": true,
42
  "vocab_size": 50257
43
  }
 
1
  {
2
+ "_name_or_path": "eminem",
3
  "activation_function": "gelu_new",
4
  "architectures": [
5
  "GPT2LMHeadModel"
 
37
  }
38
  },
39
  "torch_dtype": "float32",
40
+ "transformers_version": "4.15.0",
41
  "use_cache": true,
42
  "vocab_size": 50257
43
  }
evaluation.txt CHANGED
@@ -1 +1 @@
1
- {"eval_loss": 0.6314056515693665, "eval_runtime": 29.1648, "eval_samples_per_second": 22.733, "eval_steps_per_second": 2.846, "epoch": 13.0}
 
1
+ {"eval_loss": 0.4552081823348999, "eval_runtime": 28.3596, "eval_samples_per_second": 21.827, "eval_steps_per_second": 2.75, "epoch": 3.0}
flax_model.msgpack CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d53934603e76bd1cc6dbaa3653dfe3ef3e8368445ee4bfb94e039bbde67a7ac6
3
  size 497764120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:640dfd549bcdb5c64e303572f085c95c16d5ebe61a0058350dffda9fb32874d6
3
  size 497764120
optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a16aa18678c770ac196d53588640c9561fd9d548849b15993a4867d230b4bd96
3
  size 995604017
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba7722fce58191c71466f428a64d01c61d0bb9f30ab7cb137fbcff4ec53807f1
3
  size 995604017
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:462a6a517830a28f8813a5a4aa035ae13859bf6fde9a6ed55cc4cef7924f9166
3
  size 510403817
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:613eedc4210abf9b706cb2585b2830a5899ff79ebf8f9e7495fc42c8a1eaae2b
3
  size 510403817
rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3e00ffb84d3fc3a295652f9d6fe02a9b95ec5523997f990cc24f5bbe440e9171
3
  size 14503
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f7d12d6ed174599698df42e61c41e77e967775fb83fe49c3b8ec3abca5189394
3
  size 14503
scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f461262713d9105e94c19b3e22fda3c3bd5c05297eb98bbd2be82f70f0da5b64
3
  size 623
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1139e789b0088456b7b72a6f40cd54de1755f78a857dcab2dd97ebfb52b3f533
3
  size 623
trainer_state.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
- "best_metric": 0.6314056515693665,
3
- "best_model_checkpoint": "output/eminem/checkpoint-904",
4
  "epoch": 2.0,
5
- "global_step": 904,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
@@ -1102,11 +1102,37 @@
1102
  "eval_samples_per_second": 22.451,
1103
  "eval_steps_per_second": 2.811,
1104
  "step": 904
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1105
  }
1106
  ],
1107
- "max_steps": 5876,
1108
- "num_train_epochs": 13,
1109
- "total_flos": 944309403648000.0,
1110
  "trial_name": null,
1111
  "trial_params": null
1112
  }
 
1
  {
2
+ "best_metric": 0.4552081823348999,
3
+ "best_model_checkpoint": "output/eminem/checkpoint-916",
4
  "epoch": 2.0,
5
+ "global_step": 916,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
 
1102
  "eval_samples_per_second": 22.451,
1103
  "eval_steps_per_second": 2.811,
1104
  "step": 904
1105
+ },
1106
+ {
1107
+ "epoch": 1.98,
1108
+ "learning_rate": 4.5530896428035615e-05,
1109
+ "loss": 0.6893,
1110
+ "step": 905
1111
+ },
1112
+ {
1113
+ "epoch": 1.99,
1114
+ "learning_rate": 4.3329156273475095e-05,
1115
+ "loss": 0.9131,
1116
+ "step": 910
1117
+ },
1118
+ {
1119
+ "epoch": 2.0,
1120
+ "learning_rate": 4.115713866225047e-05,
1121
+ "loss": 0.8774,
1122
+ "step": 915
1123
+ },
1124
+ {
1125
+ "epoch": 2.0,
1126
+ "eval_loss": 0.4552081823348999,
1127
+ "eval_runtime": 27.3413,
1128
+ "eval_samples_per_second": 22.64,
1129
+ "eval_steps_per_second": 2.853,
1130
+ "step": 916
1131
  }
1132
  ],
1133
+ "max_steps": 1374,
1134
+ "num_train_epochs": 3,
1135
+ "total_flos": 956198191104000.0,
1136
  "trial_name": null,
1137
  "trial_params": null
1138
  }
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2ed41b50721ec908b04ec01203c5cd320d7547c9b186f01fce593a22f969ca01
3
- size 2863
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9cc1c03bcdb4ec1c737f7dc9de1e37f89cc954f6f5a4e9df5cfc717cc7aac606
3
+ size 2991