huggingartists

README.md

@@ -45,15 +45,15 @@ from datasets import load_dataset
 dataset = load_dataset("huggingartists/linkin-park")
 ```
 
-[Explore the data](https://wandb.ai/huggingartists/huggingartists/runs/61imxmf7/artifacts), which is tracked with [W&B artifacts](https://docs.wandb.com/artifacts) at every step of the pipeline.
+[Explore the data](https://wandb.ai/huggingartists/huggingartists/runs/1s6xt77z/artifacts), which is tracked with [W&B artifacts](https://docs.wandb.com/artifacts) at every step of the pipeline.
 
 ## Training procedure
 
 The model is based on a pre-trained [GPT-2](https://huggingface.co/gpt2) which is fine-tuned on Linkin Park's lyrics.
 
-Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/30bao19p) for full transparency and reproducibility.
+Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/1i4je18p) for full transparency and reproducibility.
 
-At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/30bao19p/artifacts) is logged and versioned.
+At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/1i4je18p/artifacts) is logged and versioned.
 
 ## How to use
 

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "gpt2",
+  "_name_or_path": "huggingartists/linkin-park",
   "activation_function": "gelu_new",
   "architectures": [
     "GPT2LMHeadModel"
@@ -35,7 +35,7 @@
     }
   },
   "torch_dtype": "float32",
-  "transformers_version": "4.10.0",
+  "transformers_version": "4.10.2",
   "use_cache": true,
   "vocab_size": 50257
 }

evaluation.txt

@@ -1 +1 @@
-{"eval_loss": 2.4942777156829834, "eval_runtime": 4.8043, "eval_samples_per_second": 21.439, "eval_steps_per_second": 2.706, "epoch": 1.0}
+{"eval_loss": 2.248004913330078, "eval_runtime": 4.6644, "eval_samples_per_second": 20.796, "eval_steps_per_second": 2.787, "epoch": 2.0}

flax_model.msgpack

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3208488eb8a76359b91c5f0bcb42e743fd33177fa09ca655a2567a963e0c180d
+oid sha256:225d151b89706812d44a3b7db2ec9b070074c0f7ba7e9d0ffe24145cc0990adb
 size 497764120

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1206dbf80f117e63d80ada5a1728e8c17090ada59b26470e6c6b91f11486b786
+oid sha256:35bd95469cbf0ab080be66768e5242378073c1190b28bd15f2700cf295d526f6
 size 995603825

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46872cad32b888e5fc94b4b1f89e48bd36340a9597d796786bef927a7a461253
+oid sha256:8a3eb8db73abd6dfffd1f85d4cbb59cf5647bfbe01d3c02e21a5a72a96906a3a
 size 510403817

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0976725c0d4eaf6ed363fdbc33ae0847a7f2f713cfa856fca8a76185db8645ed
+oid sha256:db7af3f0fec071276d1a4d8600845adbb6ac8e80806a422d4311d79890098c71
 size 14503

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d0b184ff8c170aeca1cf617a0d3c2cf6bc519b4e19b5b5aa61d3bdba28929c5
+oid sha256:03b8c59abd7807eb31fbb6b182b880936157d534c8d17e22038fc44702f9354e
 size 623

tokenizer_config.json

@@ -1 +1 @@
-{"unk_token": "<|endoftext|>", "bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "add_prefix_space": false, "model_max_length": 1024, "special_tokens_map_file": null, "name_or_path": "gpt2", "tokenizer_class": "GPT2Tokenizer"}
+{"unk_token": "<|endoftext|>", "bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "add_prefix_space": false, "model_max_length": 1024, "special_tokens_map_file": null, "name_or_path": "huggingartists/linkin-park", "tokenizer_class": "GPT2Tokenizer"}

trainer_state.json

@@ -1,8 +1,8 @@
 {
-  "best_metric": 2.4942777156829834,
-  "best_model_checkpoint": "output/linkin-park/checkpoint-69",
-  "epoch": 1.0,
-  "global_step": 69,
+  "best_metric": 2.248004913330078,
+  "best_model_checkpoint": "output/linkin-park/checkpoint-140",
+  "epoch": 2.0,
+  "global_step": 140,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -92,11 +92,117 @@
       "eval_samples_per_second": 22.041,
       "eval_steps_per_second": 2.782,
       "step": 69
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 0.0,
+      "loss": 1.9438,
+      "step": 70
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 2.463841438293457,
+      "eval_runtime": 4.6348,
+      "eval_samples_per_second": 20.929,
+      "eval_steps_per_second": 2.805,
+      "step": 70
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 1.7199452243268996e-06,
+      "loss": 2.4952,
+      "step": 75
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 6.793535661894047e-06,
+      "loss": 2.5481,
+      "step": 80
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 1.4966360302693133e-05,
+      "loss": 2.6492,
+      "step": 85
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 2.582859959249087e-05,
+      "loss": 2.3078,
+      "step": 90
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 3.88355754965355e-05,
+      "loss": 2.6034,
+      "step": 95
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 5.333506393059682e-05,
+      "loss": 2.4777,
+      "step": 100
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 6.859999999999999e-05,
+      "loss": 2.2842,
+      "step": 105
+    },
+    {
+      "epoch": 1.57,
+      "learning_rate": 8.386493606940316e-05,
+      "loss": 2.577,
+      "step": 110
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 9.836442450346448e-05,
+      "loss": 2.3194,
+      "step": 115
+    },
+    {
+      "epoch": 1.71,
+      "learning_rate": 0.00011137140040750911,
+      "loss": 2.3364,
+      "step": 120
+    },
+    {
+      "epoch": 1.79,
+      "learning_rate": 0.00012223363969730684,
+      "loss": 2.3984,
+      "step": 125
+    },
+    {
+      "epoch": 1.86,
+      "learning_rate": 0.00013040646433810595,
+      "loss": 2.2814,
+      "step": 130
+    },
+    {
+      "epoch": 1.93,
+      "learning_rate": 0.0001354800547756731,
+      "loss": 2.2059,
+      "step": 135
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 0.0001372,
+      "loss": 1.9945,
+      "step": 140
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 2.248004913330078,
+      "eval_runtime": 4.6064,
+      "eval_samples_per_second": 21.058,
+      "eval_steps_per_second": 2.822,
+      "step": 140
     }
   ],
-  "max_steps": 69,
-  "num_train_epochs": 1,
-  "total_flos": 71724662784000.0,
+  "max_steps": 140,
+  "num_train_epochs": 2,
+  "total_flos": 144625139712000.0,
   "trial_name": null,
   "trial_params": null
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f08dfbf974d9e232bd44dc9b12a890181fd646e177b0335280e7a732d83daff
+oid sha256:3c394c879763a7ac8c43760c1791f5a9aee9dc1f21c84e74abc5a6b80af9588a
 size 2671