huggingartists

README.md

@@ -45,15 +45,15 @@ from datasets import load_dataset
 dataset = load_dataset("huggingartists/og-buda")
 ```
 
-[Explore the data](https://wandb.ai/huggingartists/huggingartists/runs/3fm004ry/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/19koddag/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 OG Buda's lyrics.
 
-Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/3r1oo0se) for full transparency and reproducibility.
+Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/2pjx3dty) for full transparency and reproducibility.
 
-At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/3r1oo0se/artifacts) is logged and versioned.
+At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/2pjx3dty/artifacts) is logged and versioned.
 
 ## How to use
 

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "gpt2",
+  "_name_or_path": "huggingartists/og-buda",
   "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": 1.7267966270446777, "eval_runtime": 9.827, "eval_samples_per_second": 22.082, "eval_steps_per_second": 2.849, "epoch": 3.0}
+{"eval_loss": 1.6688779592514038, "eval_runtime": 9.5584, "eval_samples_per_second": 20.819, "eval_steps_per_second": 2.616, "epoch": 4.0}

flax_model.msgpack

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a2b95c809621b3aecc74a1c90f3c824a1a3a2d6ce143dee337193937ebba7bd0
+oid sha256:e333fb388e02210c1f3ff984ad6c4d21e6d008bcab46dfd83e150235f59d89bc
 size 497764120

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f804530839f0ce5add3c90035df250c1e521fbcfc6c6b9411ff5d93495bc79f
+oid sha256:2ebbd0aa38a33ae4017b166fd8f1134893410206219de2130750e6d7d5f39b3e
 size 995604017

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:860c0ba6e9c4d2a7b8cf3014a15ef0dd7d194bc3e7624e85d836256662aaeb56
+oid sha256:1cb6cef5d2d7cbde31a058ffa3aefb7f08a7a2e4806e882a70db75aeff20abb1
 size 510403817

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b9ef718cfc6030c7cccdc844d0b97e7bd680aadecd264b3ef13b83e80663d3b7
+oid sha256:a598a815349f8b1988c86709fdd881dafa589aaad49c7f20d98d3860abe8f36f
 size 14567

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a5824e0331cc12edcb39b03d3f95b3b9ecd34a42ea9c54b7208dfa4115ef580e
+oid sha256:e86c0f8b5c2b1ad48d13df79807268e5d50299fba1287501961674ecf5c92d8c
 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/og-buda", "tokenizer_class": "GPT2Tokenizer"}

trainer_state.json

@@ -1,8 +1,8 @@
 {
-  "best_metric": 1.7267966270446777,
-  "best_model_checkpoint": "output/og-buda/checkpoint-456",
+  "best_metric": 1.6688779592514038,
+  "best_model_checkpoint": "output/og-buda/checkpoint-462",
   "epoch": 3.0,
-  "global_step": 456,
+  "global_step": 462,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -576,11 +576,25 @@
       "eval_samples_per_second": 22.262,
       "eval_steps_per_second": 2.872,
       "step": 456
+    },
+    {
+      "epoch": 2.99,
+      "learning_rate": 5.708896496161406e-08,
+      "loss": 1.777,
+      "step": 460
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 1.6688779592514038,
+      "eval_runtime": 9.6717,
+      "eval_samples_per_second": 20.576,
+      "eval_steps_per_second": 2.585,
+      "step": 462
     }
   ],
-  "max_steps": 456,
-  "num_train_epochs": 3,
-  "total_flos": 475028914176000.0,
+  "max_steps": 616,
+  "num_train_epochs": 4,
+  "total_flos": 481038630912000.0,
   "trial_name": null,
   "trial_params": null
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c861e4bf6fefedbd0432d0ecc6f44737e89f7d8fcebe4c1d079577fd5ea0a59
+oid sha256:14e6c3bf99fa49e34d3e8e2fd8f9080f73be0573bb5ad5de841304e2c8bb6fc0
 size 2671