huggingartists

README.md

@@ -45,15 +45,15 @@ from datasets import load_dataset
 dataset = load_dataset("huggingartists/tanzy-minus")
 ```
 
-[Explore the data](https://wandb.ai/huggingartists/huggingartists/runs/17sshu4k/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/14vmwaxq/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 Танцы Минус (Tanzy Minus)'s lyrics.
 
-Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/30av9l8d) for full transparency and reproducibility.
+Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/ru5wxieh) for full transparency and reproducibility.
 
-At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/30av9l8d/artifacts) is logged and versioned.
+At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/ru5wxieh/artifacts) is logged and versioned.
 
 ## How to use
 

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "gpt2",
+  "_name_or_path": "huggingartists/tanzy-minus",
   "activation_function": "gelu_new",
   "architectures": [
     "GPT2LMHeadModel"

evaluation.txt

@@ -1 +1 @@
-{"eval_loss": 2.3025755882263184, "eval_runtime": 0.0684, "eval_samples_per_second": 14.628, "eval_steps_per_second": 14.628, "epoch": 1.0}
+{"eval_loss": 2.2600128650665283, "eval_runtime": 0.0702, "eval_samples_per_second": 14.242, "eval_steps_per_second": 14.242, "epoch": 2.0}

flax_model.msgpack

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a51a4f2a2967f74397b7fd94bf6b1b988bae0854a168721170a55f426ad0ca84
+oid sha256:deea6216f8bd0fc3ecd3c921e0294f800b584b7c0470e376e4deaed72cd729c9
 size 497764120

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c675fdebdd92cc6c93793a6c883f866602cd0e2e0d3a605740d28f9a6df02ec9
+oid sha256:36b2f63ea74e748017933e056f13001e95e1cb0383acd18b6fc37604fa60c00a
 size 995603825

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f6b20329a63e2d962c173b530a08535b50829ccbe9d69a462adab696216abcd9
+oid sha256:e0a084eb21589a31d2f71fdd846ad97bf74fe5a77c379cd435f159619fb85a42
 size 510403817

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f05ab89097ecebe552ad2f2339170c107b7844ee48669607b1b463055a12c92e
-size 14503
+oid sha256:34de8d1658e0de5a34053983dc4c4f7d60b43f48aa10eaadbd98f3546900423c
+size 14567

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:65743554f2ecb2daf21a2ff122c42c16f71111e187870af247c6234935d13ea2
+oid sha256:bed544ea42e37a9349fba621b6d9d0a1264bcf93ade35290aea045a6f78dd156
 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/tanzy-minus", "tokenizer_class": "GPT2Tokenizer"}

trainer_state.json

@@ -1,8 +1,8 @@
 {
-  "best_metric": 2.3025755882263184,
-  "best_model_checkpoint": "output/tanzy-minus/checkpoint-3",
-  "epoch": 1.0,
-  "global_step": 3,
+  "best_metric": 2.2600128650665283,
+  "best_model_checkpoint": "output/tanzy-minus/checkpoint-6",
+  "epoch": 2.0,
+  "global_step": 6,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -14,11 +14,25 @@
       "eval_samples_per_second": 12.994,
       "eval_steps_per_second": 12.994,
       "step": 3
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 0.00010290000000000001,
+      "loss": 2.2031,
+      "step": 5
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 2.2600128650665283,
+      "eval_runtime": 0.0621,
+      "eval_samples_per_second": 16.098,
+      "eval_steps_per_second": 16.098,
+      "step": 6
     }
   ],
-  "max_steps": 3,
-  "num_train_epochs": 1,
-  "total_flos": 2482274304000.0,
+  "max_steps": 6,
+  "num_train_epochs": 2,
+  "total_flos": 4964548608000.0,
   "trial_name": null,
   "trial_params": null
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b98969a3260a09b2c0aff1884f9c7feff1d176efab4a24d83b2f5a8246c0ebe1
+oid sha256:1306bb5b67c8064524955487b58bead8a4593dcddbc57da84258f4313a5a5126
 size 2863