huggingartists

README.md

@@ -45,15 +45,15 @@ from datasets import load_dataset
 dataset = load_dataset("huggingartists/bob-dylan")
 ```
 
-[Explore the data](https://wandb.ai/huggingartists/huggingartists/runs/31a7e0lm/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/3mj0lvel/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 Bob Dylan's lyrics.
 
-Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/1h7wqver) for full transparency and reproducibility.
+Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/2rt8ywgd) for full transparency and reproducibility.
 
-At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/1h7wqver/artifacts) is logged and versioned.
+At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/2rt8ywgd/artifacts) is logged and versioned.
 
 ## How to use
 

config.json

@@ -36,7 +36,7 @@
     }
   },
   "torch_dtype": "float32",
-  "transformers_version": "4.19.2",
+  "transformers_version": "4.21.0",
   "use_cache": true,
   "vocab_size": 50257
 }

evaluation.txt

@@ -1 +1 @@
-{"eval_loss": 1.1156859397888184, "eval_runtime": 5.2897, "eval_samples_per_second": 82.046, "eval_steps_per_second": 10.398, "epoch": 11.0}
+{"eval_loss": 1.0779144763946533, "eval_runtime": 9.1991, "eval_samples_per_second": 44.787, "eval_steps_per_second": 5.653, "epoch": 12.0}

flax_model.msgpack

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:52eb735612f0abe86a36c99bbc88e4b736d213924b487ddc439a7fda4f3738ba
+oid sha256:4421ceea92622de8494b95903bff7cda6d82883839516b7c317c2f2311032257
 size 497764120

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:20df6e4328ecf349bf08cc74a4faa3ceabf0373ff1ce5c11ee4657c56c5ebe05
+oid sha256:8c3bd6228ea2eec8b01df04b245f6638ed0f75a4497fd243362287540e38e841
 size 995604017

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6cbda632eba71ca8a5a6d2b2a32f60a0e0d89f0b2b5f27757234f2f9dea5b2bc
+oid sha256:bc253aac8cd1a12067cfc9355ddf901c50181d59d9e017d1e6d7648a5fcb6d39
 size 510396521

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7446d5500cdd6761e0d9b127f879a785bc53369d1cd3923b64bfed4fdcf6b5a3
+oid sha256:6314f0cb6701a11f2f7f767a9faf928846c32fdfc712debd57e46930cf18eb3c
 size 14567

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:07ca2fdd8c3e336181f82585738bd2cd39530e31bea6189b6d35d926f6c48442
+oid sha256:fa5febbb8fd869636181bd682c3f67a65a34b578ea9188e4f8a7d80e9273a343
 size 623

special_tokens_map.json

@@ -1 +1,5 @@
-{"bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "unk_token": "<|endoftext|>"}
+{
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
+}

tokenizer_config.json

@@ -1 +1,10 @@
-{"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/bob-dylan", "tokenizer_class": "GPT2Tokenizer"}
+{
+  "add_prefix_space": false,
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1024,
+  "name_or_path": "huggingartists/bob-dylan",
+  "special_tokens_map_file": null,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

trainer_state.json

@@ -1,8 +1,8 @@
 {
-  "best_metric": 1.1156859397888184,
-  "best_model_checkpoint": "output/bob-dylan/checkpoint-3520",
+  "best_metric": 1.0779144763946533,
+  "best_model_checkpoint": "output/bob-dylan/checkpoint-3542",
   "epoch": 11.0,
-  "global_step": 3520,
+  "global_step": 3542,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -4326,11 +4326,43 @@
       "eval_samples_per_second": 82.33,
       "eval_steps_per_second": 10.433,
       "step": 3520
+    },
+    {
+      "epoch": 10.95,
+      "learning_rate": 9.414215321223168e-07,
+      "loss": 1.3031,
+      "step": 3525
+    },
+    {
+      "epoch": 10.96,
+      "learning_rate": 4.696220449804098e-07,
+      "loss": 1.0973,
+      "step": 3530
+    },
+    {
+      "epoch": 10.98,
+      "learning_rate": 1.5992243352901425e-07,
+      "loss": 1.1205,
+      "step": 3535
+    },
+    {
+      "epoch": 10.99,
+      "learning_rate": 1.3059553632214649e-08,
+      "loss": 1.5828,
+      "step": 3540
+    },
+    {
+      "epoch": 11.0,
+      "eval_loss": 1.0779144763946533,
+      "eval_runtime": 8.8469,
+      "eval_samples_per_second": 46.57,
+      "eval_steps_per_second": 5.878,
+      "step": 3542
     }
   ],
-  "max_steps": 3520,
-  "num_train_epochs": 11,
-  "total_flos": 3668148191232000.0,
+  "max_steps": 3864,
+  "num_train_epochs": 12,
+  "total_flos": 3691011244032000.0,
   "trial_name": null,
   "trial_params": null
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8998c8154106cd43a7d424edf953518beb4d146ebea8364f94c30b8bca6902f7
-size 3247
+oid sha256:647f2b42971df5194cbc30178f0c27f133e73cc31198b4a11422e02c744f8538
+size 3375