huggingartists

README.md

@@ -45,15 +45,15 @@ from datasets import load_dataset
 dataset = load_dataset("huggingartists/lil-nas-x")
 ```
 
-[Explore the data](https://wandb.ai/huggingartists/huggingartists/runs/i3cxi0c3/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/13ndcpsd/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 Lil Nas X's lyrics.
 
-Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/1qrt007n) for full transparency and reproducibility.
+Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/3p5781qk) for full transparency and reproducibility.
 
-At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/1qrt007n/artifacts) is logged and versioned.
+At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/3p5781qk/artifacts) is logged and versioned.
 
 ## How to use
 

config.json

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

evaluation.txt

@@ -1 +1 @@
-{"eval_loss": 2.9424936771392822, "eval_runtime": 1.2434, "eval_samples_per_second": 20.106, "eval_steps_per_second": 3.217, "epoch": 10.0}
+{"eval_loss": 2.6141936779022217, "eval_runtime": 1.3974, "eval_samples_per_second": 20.037, "eval_steps_per_second": 2.862, "epoch": 106.0}

flax_model.msgpack

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:20f0207e6068480b12b0f0a1e986ad0b838ed6813a6cb3025608abce843f64a6
+oid sha256:e012de5ccfc4b4c18d70aee94f8defbfc1e50f57718ed71910a48c0e2e996780
 size 497764120

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cca5db0a9b829f45ea81c1628183f47350c94e9b0ca90c2c7284c95ad41aeee0
+oid sha256:31152ec3e7ee51f760ec20935ab2868246b309095fe64db579f8d857dc60e25f
 size 995603825

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:97c65e91bdea4a97855ae617ec185512034c6de6b74b727c5d47b4834600048e
+oid sha256:90a5d88426cc944b9b9757165686316e8e8367bafb4aa8f561c8b87fddde8c4a
 size 510403817

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dff0838f6c4266c52ad3f733c18288237e78c922be8b97cbee6dca8f0e06b0d4
+oid sha256:a4752c512c2a88beb880fae152e08c8dd448d4cc3f5a72c4d66926f865266b7a
 size 14503

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:858b0150f63e516bfdd54df0bdcc3e1de87c6a580f8d9790a43f52a335f62cca
+oid sha256:c1491e00f77c720090b01b79de27682170c480dbbeee4b54bb59d93e9dda8447
 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/lil-nas-x", "tokenizer_class": "GPT2Tokenizer"}

trainer_state.json

@@ -1,8 +1,8 @@
 {
-  "best_metric": 2.9424936771392822,
-  "best_model_checkpoint": "output/lil-nas-x/checkpoint-114",
-  "epoch": 6.0,
-  "global_step": 114,
+  "best_metric": 2.6141936779022217,
+  "best_model_checkpoint": "output/lil-nas-x/checkpoint-133",
+  "epoch": 7.0,
+  "global_step": 133,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -186,11 +186,43 @@
       "eval_samples_per_second": 22.081,
       "eval_steps_per_second": 3.533,
       "step": 114
+    },
+    {
+      "epoch": 6.05,
+      "learning_rate": 0.00013626438541342677,
+      "loss": 1.9341,
+      "step": 115
+    },
+    {
+      "epoch": 6.32,
+      "learning_rate": 0.00010612064364719856,
+      "loss": 2.1993,
+      "step": 120
+    },
+    {
+      "epoch": 6.58,
+      "learning_rate": 5.1759695582141247e-05,
+      "loss": 1.9984,
+      "step": 125
+    },
+    {
+      "epoch": 6.84,
+      "learning_rate": 8.268100667234864e-06,
+      "loss": 2.0998,
+      "step": 130
+    },
+    {
+      "epoch": 7.0,
+      "eval_loss": 2.6141936779022217,
+      "eval_runtime": 1.2675,
+      "eval_samples_per_second": 22.091,
+      "eval_steps_per_second": 3.156,
+      "step": 133
     }
   ],
-  "max_steps": 190,
-  "num_train_epochs": 10,
-  "total_flos": 116013662208000.0,
+  "max_steps": 2014,
+  "num_train_epochs": 106,
+  "total_flos": 134957334528000.0,
   "trial_name": null,
   "trial_params": null
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:567145a7fe28355135b0476020151a6d4f254152553e83298e8d9a53a3d93243
+oid sha256:fe08a4b46827a3aa1d0e4730d532a662db372dd2e4a6888c5273969cfba12e5a
 size 2671