huggingartists

README.md

@@ -45,15 +45,15 @@ from datasets import load_dataset
 dataset = load_dataset("huggingartists/death-grips")
 ```
 
-[Explore the data](https://wandb.ai/huggingartists/huggingartists/runs/ec6to0ba/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/1z4yxb78/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 Death Grips's lyrics.
 
-Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/14p94gs8) for full transparency and reproducibility.
+Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/18v4x337) for full transparency and reproducibility.
 
-At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/14p94gs8/artifacts) is logged and versioned.
+At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/18v4x337/artifacts) is logged and versioned.
 
 ## How to use
 

config.json

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

evaluation.txt

@@ -1 +1 @@
-{"eval_loss": 3.4941582679748535, "eval_runtime": 0.5943, "eval_samples_per_second": 74.031, "eval_steps_per_second": 10.095, "epoch": 1.0}
+{"eval_loss": 3.1992340087890625, "eval_runtime": 0.5011, "eval_samples_per_second": 75.835, "eval_steps_per_second": 9.978, "epoch": 61.0}

flax_model.msgpack

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e1757221700272e752c8d7c1a8aaeb5afb46e475c9d7766873751da252b23c78
+oid sha256:93ea9acbaf03e5cd973f67cc943630d2e10e1ec2156b1a368c852eef0b80c447
 size 497764120

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:51504115416c0c0ceb5999766325d8fc015e4cfd213b87fec34e0c2f4b840ab6
+oid sha256:91885fb2d0a23add8ab65706c01695bf0d25c6bdb6fa85982f61c7a4403d7562
 size 995603825

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d2c7cc19add62d7e343e93cd67b3fc2447d313257ae21733cac467b3fd084a1
+oid sha256:45a4d5fb1bb4bc74f1d211806c05b5291969db23c26535e118f8d45dd0493b88
 size 510403817

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8aa36eb6f9781a66d2ff9dda6822a5ac1492c196faa65d6cc177e35a39f3abeb
+oid sha256:80bc2e05cd33aba954c4fa5280f46e5f77924d62e7982e05ecf36aff4194107e
 size 14503

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:789f53ac5f4078426fcc32c51995193c87b589ef511dca806dd5fcd3735b78a5
+oid sha256:2222362d80f6c4a5547283104536d5c4564191fb641a9b7f7b9e346e9a58c2ee
 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/death-grips", "tokenizer_class": "GPT2Tokenizer"}

trainer_state.json

@@ -1,8 +1,8 @@
 {
-  "best_metric": 3.4941582679748535,
-  "best_model_checkpoint": "output/death-grips/checkpoint-32",
-  "epoch": 1.0,
-  "global_step": 32,
+  "best_metric": 3.1992340087890625,
+  "best_model_checkpoint": "output/death-grips/checkpoint-66",
+  "epoch": 2.0,
+  "global_step": 66,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -50,11 +50,69 @@
       "eval_samples_per_second": 75.33,
       "eval_steps_per_second": 10.272,
       "step": 32
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 3.25174617767334,
+      "eval_runtime": 0.4993,
+      "eval_samples_per_second": 76.107,
+      "eval_steps_per_second": 10.014,
+      "step": 33
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 1.2396913677783124e-06,
+      "loss": 3.1933,
+      "step": 35
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 1.4676757700644785e-05,
+      "loss": 3.1172,
+      "step": 40
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 4.0102530108070535e-05,
+      "loss": 3.4529,
+      "step": 45
+    },
+    {
+      "epoch": 1.52,
+      "learning_rate": 7.186411942550872e-05,
+      "loss": 3.2121,
+      "step": 50
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 0.00010290000000000001,
+      "loss": 3.1379,
+      "step": 55
+    },
+    {
+      "epoch": 1.82,
+      "learning_rate": 0.000126309992352219,
+      "loss": 3.1008,
+      "step": 60
+    },
+    {
+      "epoch": 1.97,
+      "learning_rate": 0.0001368893738885136,
+      "loss": 3.1177,
+      "step": 65
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 3.1992340087890625,
+      "eval_runtime": 0.4988,
+      "eval_samples_per_second": 76.185,
+      "eval_steps_per_second": 10.024,
+      "step": 66
     }
   ],
-  "max_steps": 32,
-  "num_train_epochs": 1,
-  "total_flos": 32922796032000.0,
+  "max_steps": 2013,
+  "num_train_epochs": 61,
+  "total_flos": 66890760192000.0,
   "trial_name": null,
   "trial_params": null
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79b0711c457b001263266f6599453533724d726bf5a7988a0de95942c1d57764
+oid sha256:820c88075277a4ce2d8bfc6da26d7fd133ba368b384db802a6a4afafc3e34877
 size 2863