huggingartists

README.md

@@ -45,15 +45,15 @@ from datasets import load_dataset
 dataset = load_dataset("huggingartists/the-gazette")
 ```
 
-[Explore the data](https://wandb.ai/huggingartists/huggingartists/runs/1in06o8p/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/3ck1sdfv/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 The Gazette's lyrics.
 
-Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/imffzt1z) for full transparency and reproducibility.
+Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/m1wevlws) for full transparency and reproducibility.
 
-At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/imffzt1z/artifacts) is logged and versioned.
+At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/m1wevlws/artifacts) is logged and versioned.
 
 ## How to use
 

config.json

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

flax_model.msgpack

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a0064ee8364449eae873b401e13781ea28885704a5e64dea29966eff9436880
+oid sha256:4b0a55b9a88cfc006c97ced67a2e960eed339d9fa2f503a9ca72fc5049a4a9b4
 size 497764120

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:041424f549c10466c0691914c673106c0cd7a3245b3e587210a5aeaf77492f42
+oid sha256:088ddca036c616cf924a3c31abfc7c02e28fc41869e9aec146ff68e468cc60dd
 size 995603825

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d4dc3d79af3942de48efe1cb4d7112a449e9de67e12eb7ce1bfe71d13d44133
+oid sha256:6a8c0f24236751e3b6e048e4a72eb41cd541006d398a0b7286bfce923c3667b9
 size 510403817

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ada4d26d0f4f51eec3cea87150053cd5390ffe99beea24846e73e9800641a3f3
-size 14503
+oid sha256:bad83b8d103d4ac9f3bbe85b7ddfd36cfeb31fe3ed911b1bd4a2b3b2f43b8104
+size 14567

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3759f0274d6462c99515ad4f587a39c595bfc6a862d6d53aec4d5f4c94343a76
+oid sha256:407aaf946156cc59d13c99014290915b74fee0be008a71f0976b3bc407e23501
 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/the-gazette", "tokenizer_class": "GPT2Tokenizer"}

trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.0,
-  "global_step": 17,
+  "epoch": 4.0,
+  "global_step": 68,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -24,11 +24,71 @@
       "learning_rate": 4.6324050628611986e-06,
       "loss": 4.0138,
       "step": 15
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 1.0275104488948473e-05,
+      "loss": 3.7661,
+      "step": 20
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 6.227039054081748e-05,
+      "loss": 3.7248,
+      "step": 25
+    },
+    {
+      "epoch": 1.76,
+      "learning_rate": 0.00011929601172133719,
+      "loss": 3.9344,
+      "step": 30
+    },
+    {
+      "epoch": 2.06,
+      "learning_rate": 0.00013603195463831566,
+      "loss": 3.8787,
+      "step": 35
+    },
+    {
+      "epoch": 2.35,
+      "learning_rate": 9.917765120627052e-05,
+      "loss": 3.5252,
+      "step": 40
+    },
+    {
+      "epoch": 2.65,
+      "learning_rate": 3.8022348793729525e-05,
+      "loss": 3.5674,
+      "step": 45
+    },
+    {
+      "epoch": 2.94,
+      "learning_rate": 1.1680453616843376e-06,
+      "loss": 3.4848,
+      "step": 50
+    },
+    {
+      "epoch": 3.24,
+      "learning_rate": 1.7903988278662747e-05,
+      "loss": 3.2603,
+      "step": 55
+    },
+    {
+      "epoch": 3.53,
+      "learning_rate": 7.492960945918241e-05,
+      "loss": 3.4291,
+      "step": 60
+    },
+    {
+      "epoch": 3.82,
+      "learning_rate": 0.0001269248955110515,
+      "loss": 3.4645,
+      "step": 65
     }
   ],
-  "max_steps": 17,
-  "num_train_epochs": 1,
-  "total_flos": 16853336064000.0,
+  "max_steps": 68,
+  "num_train_epochs": 4,
+  "total_flos": 67413344256000.0,
   "trial_name": null,
   "trial_params": null
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:481780d50f34750988b858ec38e71a7790325f55622dd09aa64618acc047e160
+oid sha256:520a217df91c7cf215f9d566603b63d78168cc24e306e916bf9c950908c9a8f1
 size 2671