huggingartists

README.md

@@ -45,15 +45,15 @@ from datasets import load_dataset
 dataset = load_dataset("huggingartists/the-the-pigs")
 ```
 
-[Explore the data](https://wandb.ai/huggingartists/huggingartists/runs/s5khturf/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/7yh65db9/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 ‘’Вепри’’ (The Pigs)'s lyrics.
 
-Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/2wm2oonn) for full transparency and reproducibility.
+Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/65gj1lk1) for full transparency and reproducibility.
 
-At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/2wm2oonn/artifacts) is logged and versioned.
+At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/65gj1lk1/artifacts) is logged and versioned.
 
 ## How to use
 

config.json

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

evaluation.txt

@@ -1 +1 @@
-{"eval_loss": 1.7347867488861084, "eval_runtime": 0.9361, "eval_samples_per_second": 20.297, "eval_steps_per_second": 3.205, "epoch": 20.0}
+{"eval_loss": 1.621703028678894, "eval_runtime": 1.0514, "eval_samples_per_second": 20.924, "eval_steps_per_second": 2.853, "epoch": 109.0}

flax_model.msgpack

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c02c32ea8cbf7c2e61290b1d72ca0369e968b66bb1edd7b4464b23c5092af01b
+oid sha256:8cac01e3e8e7334767c029651df67fe66fe2897cde82b9c9c859c035aa779d50
 size 497764120

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d794e2cf1e854660cf8c67241054d968e9933fc96e0ac960005808d8e19da9a
+oid sha256:efb6298c1ee9d27085b6b26eeee4bb5bd451b57bf370bbf0250eacb1122a8406
 size 995603825

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f13a43a42b8448df12dbb6b75830224c036b3bcb9c128c9833c197779081b8a6
+oid sha256:df20a48917965ea1b00db1df1514df26f7f6ba42fdaa12aa96e21f8d425f972a
 size 510403817

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:70c1257d23e86fa50a3c449eb97c44e917eeff6eada6271ca3edb44fa461f708
-size 14567
+oid sha256:b7128092bbf4a37694370d36c94bbee45377288c60216893350826a65beba17c
+size 14503

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f8eb138d3e74e4ee9a8cfdbf6948246533add92d0858995ee833af706c95c53c
+oid sha256:8f39323abdebb283bc5c2151a021734faafaf232e59d003177bb41167a1a31b6
 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-the-pigs", "tokenizer_class": "GPT2Tokenizer"}

trainer_state.json

@@ -1,8 +1,8 @@
 {
-  "best_metric": 1.7347867488861084,
-  "best_model_checkpoint": "output/the-the-pigs/checkpoint-117",
-  "epoch": 9.0,
-  "global_step": 117,
+  "best_metric": 1.621703028678894,
+  "best_model_checkpoint": "output/the-the-pigs/checkpoint-132",
+  "epoch": 11.0,
+  "global_step": 132,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -216,11 +216,45 @@
       "eval_samples_per_second": 22.327,
       "eval_steps_per_second": 3.525,
       "step": 117
+    },
+    {
+      "epoch": 10.0,
+      "learning_rate": 0.0001372,
+      "loss": 1.6342,
+      "step": 120
+    },
+    {
+      "epoch": 10.0,
+      "eval_loss": 1.6437487602233887,
+      "eval_runtime": 0.9748,
+      "eval_samples_per_second": 22.569,
+      "eval_steps_per_second": 3.078,
+      "step": 120
+    },
+    {
+      "epoch": 10.42,
+      "learning_rate": 8.635498649403298e-05,
+      "loss": 1.7365,
+      "step": 125
+    },
+    {
+      "epoch": 10.83,
+      "learning_rate": 9.190657300387535e-06,
+      "loss": 1.6443,
+      "step": 130
+    },
+    {
+      "epoch": 11.0,
+      "eval_loss": 1.621703028678894,
+      "eval_runtime": 1.0058,
+      "eval_samples_per_second": 21.873,
+      "eval_steps_per_second": 2.983,
+      "step": 132
     }
   ],
-  "max_steps": 260,
-  "num_train_epochs": 20,
-  "total_flos": 115229786112000.0,
+  "max_steps": 1308,
+  "num_train_epochs": 109,
+  "total_flos": 130384723968000.0,
   "trial_name": null,
   "trial_params": null
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:115de7483970d263e0616e850a6e0d52e43c047dc3d58f7fce41ea06d8252d5f
+oid sha256:93d3101d9dcf343ede445e4a706f3bbc279ebaf47084dfddf4e639933ea0a8c3
 size 2671