huggingartists

README.md

@@ -45,15 +45,15 @@ from datasets import load_dataset
 dataset = load_dataset("huggingartists/kurt-cobain")
 ```
 
-[Explore the data](https://wandb.ai/huggingartists/huggingartists/runs/1whd1v3b/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/tjfuj6tr/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 Kurt Cobain's lyrics.
 
-Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/3nzvvuyl) for full transparency and reproducibility.
+Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/3enopofm) for full transparency and reproducibility.
 
-At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/3nzvvuyl/artifacts) is logged and versioned.
+At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/3enopofm/artifacts) is logged and versioned.
 
 ## How to use
 

config.json

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

evaluation.txt

@@ -1 +1 @@
-{"eval_loss": 2.059675931930542, "eval_runtime": 3.7661, "eval_samples_per_second": 21.773, "eval_steps_per_second": 2.921, "epoch": 1.0}
+{"eval_loss": 1.8867709636688232, "eval_runtime": 3.4897, "eval_samples_per_second": 21.779, "eval_steps_per_second": 2.866, "epoch": 2.0}

flax_model.msgpack

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7cfb2fb84e95c1f4166fbc68132aab67b3e2d43bb335046b2db6d09528a0fff9
+oid sha256:92cd1a1dbcc866561e4e2c65bc53fed5096e0ce5f836a41b712f588b6374cc74
 size 497764120

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fbc63b097ef5c6b54b802015cc1fd80b5d7fb752db3f09423f2231b2fd9bf470
+oid sha256:a222bb05ea08ee5f83a19f1124fc880a18d9afb82a601e26ddfd42882683baaa
 size 995603825

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fbd5a79c6d6f4397e979deb5ed837e7a31a9444a389f1e4b7d9b629e59679130
+oid sha256:dd4e8ce7554bde500a78926cb81c5e1d2ae6a48cd1688e91bc158367b40e150c
 size 510403817

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e3669fa98bb5c4efd6c0df7cdf49d6ef6463037ace488e6ccbace1eb61273d86
+oid sha256:997987240923c558e1c237d64d5efba40e39d7bad476231adb9f6a613bbb1a21
 size 14503

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea254c15c4fd5cb1f8de5c78442f725e8358618f09aaa6308f4d0adddbd45447
+oid sha256:6ba8206d5153f46186cf77d6a4dc5a54b5948a8e7cf23f123d556cbf66dca801
 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/kurt-cobain", "tokenizer_class": "GPT2Tokenizer"}

trainer_state.json

@@ -1,8 +1,8 @@
 {
-  "best_metric": 2.059675931930542,
-  "best_model_checkpoint": "output/kurt-cobain/checkpoint-63",
-  "epoch": 1.0,
-  "global_step": 63,
+  "best_metric": 1.8867709636688232,
+  "best_model_checkpoint": "output/kurt-cobain/checkpoint-126",
+  "epoch": 2.0,
+  "global_step": 126,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -86,11 +86,97 @@
       "eval_samples_per_second": 22.522,
       "eval_steps_per_second": 3.021,
       "step": 63
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 3.408888099334633e-07,
+      "loss": 2.2316,
+      "step": 65
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 4.137086214086682e-06,
+      "loss": 2.3402,
+      "step": 70
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 1.1920020081922749e-05,
+      "loss": 2.2531,
+      "step": 75
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 2.320835154085542e-05,
+      "loss": 2.3415,
+      "step": 80
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 3.7303948905573005e-05,
+      "loss": 2.1674,
+      "step": 85
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 5.333506393059682e-05,
+      "loss": 2.2066,
+      "step": 90
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 7.031024545323179e-05,
+      "loss": 1.9122,
+      "step": 95
+    },
+    {
+      "epoch": 1.59,
+      "learning_rate": 8.71796561146101e-05,
+      "loss": 2.1474,
+      "step": 100
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 0.00010290000000000001,
+      "loss": 2.0603,
+      "step": 105
+    },
+    {
+      "epoch": 1.75,
+      "learning_rate": 0.0001164990457207046,
+      "loss": 1.8847,
+      "step": 110
+    },
+    {
+      "epoch": 1.83,
+      "learning_rate": 0.00012713575447996587,
+      "loss": 1.881,
+      "step": 115
+    },
+    {
+      "epoch": 1.9,
+      "learning_rate": 0.00013415229447692924,
+      "loss": 2.2478,
+      "step": 120
+    },
+    {
+      "epoch": 1.98,
+      "learning_rate": 0.00013711472479561806,
+      "loss": 2.2805,
+      "step": 125
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 1.8867709636688232,
+      "eval_runtime": 3.3707,
+      "eval_samples_per_second": 22.547,
+      "eval_steps_per_second": 2.967,
+      "step": 126
     }
   ],
-  "max_steps": 63,
-  "num_train_epochs": 1,
-  "total_flos": 64931069952000.0,
+  "max_steps": 126,
+  "num_train_epochs": 2,
+  "total_flos": 130646016000000.0,
   "trial_name": null,
   "trial_params": null
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:827966f81c0e881fb54a56100eb0000ea908c70ca55363e9cba79025ffe95eea
+oid sha256:07a6cfdfce155fa31773129f68bc985f3200c031e3f132dded8a6f847b060755
 size 2863