huggingartists

README.md

@@ -45,15 +45,15 @@ from datasets import load_dataset
 dataset = load_dataset("huggingartists/viktor-tsoi")
 ```
 
-[Explore the data](https://wandb.ai/huggingartists/huggingartists/runs/3dbxo21p/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/1uufz4th/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 Виктор Цой (Viktor Tsoi)'s lyrics.
 
-Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/1qe51xj0) for full transparency and reproducibility.
+Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/8mogk3d7) for full transparency and reproducibility.
 
-At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/1qe51xj0/artifacts) is logged and versioned.
+At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/8mogk3d7/artifacts) is logged and versioned.
 
 ## How to use
 

config.json

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

evaluation.txt

@@ -1 +1 @@
-{"eval_loss": 1.742375135421753, "eval_runtime": 2.6042, "eval_samples_per_second": 20.736, "eval_steps_per_second": 2.688, "epoch": 1.0}
+{"eval_loss": 1.6593416929244995, "eval_runtime": 2.657, "eval_samples_per_second": 21.453, "eval_steps_per_second": 3.011, "epoch": 2.0}

flax_model.msgpack

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:91e10663a0f3244857439b56cd04237c31b6eae728e7946713ce843d8d28e75e
+oid sha256:d49064efb266e519ece7257c9d60deebe252fb6406d169e20dadeff277f7dc37
 size 497764120

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b6393030e2096bada970db9d27e3ff22446a05a9077ef19b5fc54c55e11b45d
+oid sha256:db593a7972d8e20eed34acf31aa0d79678447e39973eff379958dc4fbba2231e
 size 995603825

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:546047b53d33d8741418a5178e3adc522fb1e0d0301daf0f8e99e986b5d9777c
+oid sha256:1c750cb8a3a0856153a37e616ee6dce7c26d113b033fd26b7f7d02ab5d7e8639
 size 510403817

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43f420abc20ff158a09ca170c7b11375c8ca382b141e051a66f1a65570d74fea
-size 14503
+oid sha256:14c00e5accc59ae7985545e12496021de015b318dd1489d964d4a6d8d6ce5297
+size 14567

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d4369506dedd54e65c6967a3362585e3aa7b5afb87732c009d3c12491c2fbd1
+oid sha256:377ca4976456890405a303851a7b4d7bfd45747ee263ed38f7554f3c6e6a1db4
 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/viktor-tsoi", "tokenizer_class": "GPT2Tokenizer"}

trainer_state.json

@@ -1,8 +1,8 @@
 {
-  "best_metric": 1.742375135421753,
-  "best_model_checkpoint": "output/viktor-tsoi/checkpoint-41",
-  "epoch": 1.0,
-  "global_step": 41,
+  "best_metric": 1.6593416929244995,
+  "best_model_checkpoint": "output/viktor-tsoi/checkpoint-82",
+  "epoch": 2.0,
+  "global_step": 82,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -62,11 +62,67 @@
       "eval_samples_per_second": 20.944,
       "eval_steps_per_second": 2.715,
       "step": 41
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 3.197007505031765e-06,
+      "loss": 1.858,
+      "step": 45
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 1.5675842264214697e-05,
+      "loss": 1.8206,
+      "step": 50
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 3.58284204500588e-05,
+      "loss": 1.7518,
+      "step": 55
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 6.0732717017669706e-05,
+      "loss": 1.744,
+      "step": 60
+    },
+    {
+      "epoch": 1.59,
+      "learning_rate": 8.677773105069102e-05,
+      "loss": 1.7542,
+      "step": 65
+    },
+    {
+      "epoch": 1.71,
+      "learning_rate": 0.00011018706319231134,
+      "loss": 1.7612,
+      "step": 70
+    },
+    {
+      "epoch": 1.83,
+      "learning_rate": 0.00012756647503932202,
+      "loss": 1.7551,
+      "step": 75
+    },
+    {
+      "epoch": 1.95,
+      "learning_rate": 0.0001363960370713319,
+      "loss": 1.7343,
+      "step": 80
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 1.6593416929244995,
+      "eval_runtime": 2.6581,
+      "eval_samples_per_second": 21.444,
+      "eval_steps_per_second": 3.01,
+      "step": 82
     }
   ],
-  "max_steps": 41,
-  "num_train_epochs": 1,
-  "total_flos": 42459955200000.0,
+  "max_steps": 82,
+  "num_train_epochs": 2,
+  "total_flos": 84397326336000.0,
   "trial_name": null,
   "trial_params": null
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b49b2cf9a36957cbbc6e44492b8b37d4e9c2e9a29bf05d217e090cc84a1dda16
+oid sha256:d4864274d1168011bbafdc53bc5f4a82d25908496ba29f580633e85995da2e5f
 size 2671