huggingartists

README.md

@@ -45,15 +45,15 @@ from datasets import load_dataset
 dataset = load_dataset("huggingartists/miyagi")
 ```
 
-[Explore the data](https://wandb.ai/huggingartists/huggingartists/runs/33axhvp7/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/1ai9l9x0/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 MiyaGi's lyrics.
 
-Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/560sm315) for full transparency and reproducibility.
+Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/1jowduev) for full transparency and reproducibility.
 
-At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/560sm315/artifacts) is logged and versioned.
+At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/1jowduev/artifacts) is logged and versioned.
 
 ## How to use
 

config.json

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

evaluation.txt

@@ -1 +1 @@
-{"eval_loss": 1.9889769554138184, "eval_runtime": 8.2714, "eval_samples_per_second": 20.432, "eval_steps_per_second": 2.66, "epoch": 1.0}
+{"eval_loss": 1.8749154806137085, "eval_runtime": 7.3205, "eval_samples_per_second": 21.993, "eval_steps_per_second": 2.869, "epoch": 2.0}

flax_model.msgpack

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:44ffebc9bed4a9a2d516e6fe2d55e2a84e9108938d76c1bf82c7bc9e87e0eeb3
+oid sha256:dc6c27a566d394fbdfff2c02e91b8c4f7dcbbda449ff9001dad2a4e5e9c49d15
 size 497764120

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:83e6a184300a4da7de3a0ae9368b17270bf1f0c60cb18344e094885437d4ded9
+oid sha256:b786b373617192574138bda4ac4b3640a92f885392072876141d13ed205ff93f
 size 995603825

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b7f820636f754a7aa82e3715071861e73590860152f7a49ca45aba55fe00b410
+oid sha256:7efb14a7343abd44b17d9c21ac3a67b41d36a9948a87d8429abc40754990793b
 size 510403817

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a0991fc954782244b3d68425edce12ebcd44630d9d81754c57a010a17f834cf
-size 14503
+oid sha256:c04cc128afd4b444801d7a22ed3a8e15a0e9e121067a7a197e91e35268473f22
+size 14567

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e90c182f2545f26454b003c854f4df0419ef205b274b2e4a9121c08f80493a77
+oid sha256:34ccf3854b39bd52f430cb63b3a54f30c543980a0b5913372cb9a1e99f761d9b
 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/miyagi", "tokenizer_class": "GPT2Tokenizer"}

trainer_state.json

@@ -1,8 +1,8 @@
 {
-  "best_metric": 1.9889769554138184,
-  "best_model_checkpoint": "output/miyagi/checkpoint-120",
-  "epoch": 1.0,
-  "global_step": 120,
+  "best_metric": 1.8749154806137085,
+  "best_model_checkpoint": "output/miyagi/checkpoint-242",
+  "epoch": 2.0,
+  "global_step": 242,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -158,11 +158,171 @@
       "eval_samples_per_second": 20.489,
       "eval_steps_per_second": 2.667,
       "step": 120
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 1.8863365650177002,
+      "eval_runtime": 6.9627,
+      "eval_samples_per_second": 23.123,
+      "eval_steps_per_second": 3.016,
+      "step": 121
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 3.696176693910321e-07,
+      "loss": 1.993,
+      "step": 125
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 1.8643657094774288e-06,
+      "loss": 1.8125,
+      "step": 130
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 4.482209545216786e-06,
+      "loss": 1.9934,
+      "step": 135
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 8.179093411846335e-06,
+      "loss": 1.8632,
+      "step": 140
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 1.2892802350719696e-05,
+      "loss": 2.0066,
+      "step": 145
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 1.8544009226529548e-05,
+      "loss": 2.0706,
+      "step": 150
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 2.5037609725814876e-05,
+      "loss": 1.9308,
+      "step": 155
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 3.2264322870026065e-05,
+      "loss": 1.8125,
+      "step": 160
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 4.0102530108070535e-05,
+      "loss": 1.8868,
+      "step": 165
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 4.842032203820096e-05,
+      "loss": 1.9685,
+      "step": 170
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 5.70777183149067e-05,
+      "loss": 1.9188,
+      "step": 175
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 6.592902338193754e-05,
+      "loss": 1.9786,
+      "step": 180
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 7.482527838676297e-05,
+      "loss": 1.8686,
+      "step": 185
+    },
+    {
+      "epoch": 1.57,
+      "learning_rate": 8.361676801313241e-05,
+      "loss": 1.9975,
+      "step": 190
+    },
+    {
+      "epoch": 1.61,
+      "learning_rate": 9.215554004418502e-05,
+      "loss": 1.851,
+      "step": 195
+    },
+    {
+      "epoch": 1.65,
+      "learning_rate": 0.00010029789525431117,
+      "loss": 1.8228,
+      "step": 200
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 0.0001079068057273095,
+      "loss": 1.8039,
+      "step": 205
+    },
+    {
+      "epoch": 1.74,
+      "learning_rate": 0.0001148542209028974,
+      "loss": 1.9549,
+      "step": 210
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 0.00012102322254305531,
+      "loss": 1.9539,
+      "step": 215
+    },
+    {
+      "epoch": 1.82,
+      "learning_rate": 0.000126309992352219,
+      "loss": 1.8849,
+      "step": 220
+    },
+    {
+      "epoch": 1.86,
+      "learning_rate": 0.00013062555913818553,
+      "loss": 1.9122,
+      "step": 225
+    },
+    {
+      "epoch": 1.9,
+      "learning_rate": 0.00013389729611071438,
+      "loss": 1.9664,
+      "step": 230
+    },
+    {
+      "epoch": 1.94,
+      "learning_rate": 0.00013607014311974643,
+      "loss": 1.8078,
+      "step": 235
+    },
+    {
+      "epoch": 1.98,
+      "learning_rate": 0.00013710753326415926,
+      "loss": 1.8547,
+      "step": 240
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 1.8749154806137085,
+      "eval_runtime": 7.1382,
+      "eval_samples_per_second": 22.555,
+      "eval_steps_per_second": 2.942,
+      "step": 242
     }
   ],
-  "max_steps": 120,
-  "num_train_epochs": 1,
-  "total_flos": 125158883328000.0,
+  "max_steps": 242,
+  "num_train_epochs": 2,
+  "total_flos": 252146810880000.0,
   "trial_name": null,
   "trial_params": null
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16a13486ddcf5f6cc2d8ddfca1f9d43d401ea752c8f92491f44c7ffa413e82c1
+oid sha256:3fea27806c0a8b58c971861b19a8e6a16537326283f0b22c46854ba1150e10ed
 size 2671