huggingartists

README.md

@@ -45,15 +45,15 @@ from datasets import load_dataset
 dataset = load_dataset("huggingartists/oxxxymiron")
 ```
 
-[Explore the data](https://wandb.ai/huggingartists/huggingartists/runs/if83r8sb/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/e254c9iz/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 Oxxxymiron's lyrics.
 
-Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/s58wdkfz) for full transparency and reproducibility.
+Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/1ggk9c4z) for full transparency and reproducibility.
 
-At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/s58wdkfz/artifacts) is logged and versioned.
+At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/1ggk9c4z/artifacts) is logged and versioned.
 
 ## How to use
 

config.json

@@ -37,7 +37,7 @@
     }
   },
   "torch_dtype": "float32",
-  "transformers_version": "4.15.0",
+  "transformers_version": "4.20.1",
   "use_cache": true,
   "vocab_size": 50257
 }

evaluation.txt

@@ -1 +1 @@
-{"eval_loss": 1.3110859394073486, "eval_runtime": 18.5351, "eval_samples_per_second": 20.825, "eval_steps_per_second": 2.644, "epoch": 26.0}
+{"eval_loss": 1.2792030572891235, "eval_runtime": 11.6667, "eval_samples_per_second": 44.057, "eval_steps_per_second": 5.571, "epoch": 27.0}

flax_model.msgpack

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bf04b5cb92f0bb037efcff6106efd6559eadeb2c169561274b38adf7974d3cbd
+oid sha256:7199341f4dd28233f5a2f7a57d1173f1de5ec3e5c9bda47eff103b938f2f53f0
 size 497764120

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:89bd3fcc9080941291eb43d62d53800524426bd1841ce2e59ad94d37b402ee47
+oid sha256:b09ade92b331627aa5e617dc79f94f4950c20fcb91cc9c206ab7b3fc6ff328ab
 size 995604017

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b078eadcf9ca889f51cd804d94e22e90d64d6befb42b2adc89663598895f61d
-size 510403817
+oid sha256:3419aa695794916220adfc7bc1a0a22a3a14811601f48076c9c4970c4e59123e
+size 510396521

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c93f956bb61c562ef5de6ecf68f0acb1e428bb13e97ddfd9eb68fef96714fcef
+oid sha256:43de655d52a19502409ebbe70eea7706f630b0bef1a4871e806cca13d3c53b94
 size 14439

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:40aa28790758cc10852db2e41872a7c552d32089589ee1f68283d1cfcd6cf1da
+oid sha256:cf6862649037771cabc79d7217ab41990edef62364ec82c3e0d0afea35db8b9b
 size 623

special_tokens_map.json

@@ -1 +1,5 @@
-{"bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "unk_token": "<|endoftext|>"}
+{
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
+}

tokenizer_config.json

@@ -1 +1,10 @@
-{"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/oxxxymiron", "tokenizer_class": "GPT2Tokenizer"}
+{
+  "add_prefix_space": false,
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1024,
+  "name_or_path": "huggingartists/oxxxymiron",
+  "special_tokens_map_file": null,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

trainer_state.json

@@ -1,8 +1,8 @@
 {
-  "best_metric": 1.3110859394073486,
-  "best_model_checkpoint": "output/oxxxymiron/checkpoint-4573",
-  "epoch": 17.0,
-  "global_step": 4573,
+  "best_metric": 1.2792030572891235,
+  "best_model_checkpoint": "output/oxxxymiron/checkpoint-4807",
+  "epoch": 19.0,
+  "global_step": 4807,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -5514,11 +5514,301 @@
       "eval_samples_per_second": 20.855,
       "eval_steps_per_second": 2.647,
       "step": 4573
+    },
+    {
+      "epoch": 18.08,
+      "learning_rate": 0.000134880848712477,
+      "loss": 1.3191,
+      "step": 4575
+    },
+    {
+      "epoch": 18.1,
+      "learning_rate": 0.00013365575351388775,
+      "loss": 1.4082,
+      "step": 4580
+    },
+    {
+      "epoch": 18.12,
+      "learning_rate": 0.00013217996375537754,
+      "loss": 1.381,
+      "step": 4585
+    },
+    {
+      "epoch": 18.14,
+      "learning_rate": 0.0001304591664429994,
+      "loss": 1.3937,
+      "step": 4590
+    },
+    {
+      "epoch": 18.16,
+      "learning_rate": 0.00012849999272775362,
+      "loss": 1.3955,
+      "step": 4595
+    },
+    {
+      "epoch": 18.18,
+      "learning_rate": 0.000126309992352219,
+      "loss": 1.3851,
+      "step": 4600
+    },
+    {
+      "epoch": 18.2,
+      "learning_rate": 0.00012389760455736593,
+      "loss": 1.3328,
+      "step": 4605
+    },
+    {
+      "epoch": 18.22,
+      "learning_rate": 0.00012127212556165209,
+      "loss": 1.3809,
+      "step": 4610
+    },
+    {
+      "epoch": 18.24,
+      "learning_rate": 0.00011844367273772787,
+      "loss": 1.2981,
+      "step": 4615
+    },
+    {
+      "epoch": 18.26,
+      "learning_rate": 0.00011542314562479984,
+      "loss": 1.4094,
+      "step": 4620
+    },
+    {
+      "epoch": 18.28,
+      "learning_rate": 0.00011222218392688052,
+      "loss": 1.4044,
+      "step": 4625
+    },
+    {
+      "epoch": 18.3,
+      "learning_rate": 0.0001088531226587985,
+      "loss": 1.4849,
+      "step": 4630
+    },
+    {
+      "epoch": 18.32,
+      "learning_rate": 0.00010532894461279404,
+      "loss": 1.4488,
+      "step": 4635
+    },
+    {
+      "epoch": 18.34,
+      "learning_rate": 0.00010166323032888931,
+      "loss": 1.4335,
+      "step": 4640
+    },
+    {
+      "epoch": 18.36,
+      "learning_rate": 9.78701057618181e-05,
+      "loss": 1.3215,
+      "step": 4645
+    },
+    {
+      "epoch": 18.38,
+      "learning_rate": 9.396418784617256e-05,
+      "loss": 1.4931,
+      "step": 4650
+    },
+    {
+      "epoch": 18.4,
+      "learning_rate": 8.996052816955526e-05,
+      "loss": 1.4301,
+      "step": 4655
+    },
+    {
+      "epoch": 18.42,
+      "learning_rate": 8.587455497076757e-05,
+      "loss": 1.3555,
+      "step": 4660
+    },
+    {
+      "epoch": 18.44,
+      "learning_rate": 8.172201368657088e-05,
+      "loss": 1.3862,
+      "step": 4665
+    },
+    {
+      "epoch": 18.46,
+      "learning_rate": 7.751890627611039e-05,
+      "loss": 1.3795,
+      "step": 4670
+    },
+    {
+      "epoch": 18.48,
+      "learning_rate": 7.328142955681618e-05,
+      "loss": 1.4168,
+      "step": 4675
+    },
+    {
+      "epoch": 18.5,
+      "learning_rate": 6.902591278942331e-05,
+      "loss": 1.4594,
+      "step": 4680
+    },
+    {
+      "epoch": 18.52,
+      "learning_rate": 6.47687547526032e-05,
+      "loss": 1.4803,
+      "step": 4685
+    },
+    {
+      "epoch": 18.54,
+      "learning_rate": 6.0526360549714816e-05,
+      "loss": 1.4239,
+      "step": 4690
+    },
+    {
+      "epoch": 18.56,
+      "learning_rate": 5.6315078391183605e-05,
+      "loss": 1.3304,
+      "step": 4695
+    },
+    {
+      "epoch": 18.58,
+      "learning_rate": 5.21511365961095e-05,
+      "loss": 1.3828,
+      "step": 4700
+    },
+    {
+      "epoch": 18.6,
+      "learning_rate": 4.80505810558948e-05,
+      "loss": 1.3273,
+      "step": 4705
+    },
+    {
+      "epoch": 18.62,
+      "learning_rate": 4.402921340084794e-05,
+      "loss": 1.3661,
+      "step": 4710
+    },
+    {
+      "epoch": 18.64,
+      "learning_rate": 4.0102530108070474e-05,
+      "loss": 1.287,
+      "step": 4715
+    },
+    {
+      "epoch": 18.66,
+      "learning_rate": 3.6285662785250574e-05,
+      "loss": 1.3865,
+      "step": 4720
+    },
+    {
+      "epoch": 18.68,
+      "learning_rate": 3.2593319860498044e-05,
+      "loss": 1.428,
+      "step": 4725
+    },
+    {
+      "epoch": 18.7,
+      "learning_rate": 2.9039729902920295e-05,
+      "loss": 1.2403,
+      "step": 4730
+    },
+    {
+      "epoch": 18.72,
+      "learning_rate": 2.5638586792340877e-05,
+      "loss": 1.4223,
+      "step": 4735
+    },
+    {
+      "epoch": 18.74,
+      "learning_rate": 2.2402996949474048e-05,
+      "loss": 1.3913,
+      "step": 4740
+    },
+    {
+      "epoch": 18.75,
+      "learning_rate": 1.9345428829881034e-05,
+      "loss": 1.3764,
+      "step": 4745
+    },
+    {
+      "epoch": 18.77,
+      "learning_rate": 1.647766487635479e-05,
+      "loss": 1.4167,
+      "step": 4750
+    },
+    {
+      "epoch": 18.79,
+      "learning_rate": 1.3810756114877466e-05,
+      "loss": 1.3081,
+      "step": 4755
+    },
+    {
+      "epoch": 18.81,
+      "learning_rate": 1.1354979569111334e-05,
+      "loss": 1.3206,
+      "step": 4760
+    },
+    {
+      "epoch": 18.83,
+      "learning_rate": 9.119798657542995e-06,
+      "loss": 1.3369,
+      "step": 4765
+    },
+    {
+      "epoch": 18.85,
+      "learning_rate": 7.113826725875128e-06,
+      "loss": 1.3328,
+      "step": 4770
+    },
+    {
+      "epoch": 18.87,
+      "learning_rate": 5.344793855206173e-06,
+      "loss": 1.4008,
+      "step": 4775
+    },
+    {
+      "epoch": 18.89,
+      "learning_rate": 3.819517073901737e-06,
+      "loss": 1.41,
+      "step": 4780
+    },
+    {
+      "epoch": 18.91,
+      "learning_rate": 2.5438740879408957e-06,
+      "loss": 1.1899,
+      "step": 4785
+    },
+    {
+      "epoch": 18.93,
+      "learning_rate": 1.522780630978951e-06,
+      "loss": 1.3401,
+      "step": 4790
+    },
+    {
+      "epoch": 18.95,
+      "learning_rate": 7.601715213983543e-07,
+      "loss": 1.3232,
+      "step": 4795
+    },
+    {
+      "epoch": 18.97,
+      "learning_rate": 2.5898549935329754e-07,
+      "loss": 1.3369,
+      "step": 4800
+    },
+    {
+      "epoch": 18.99,
+      "learning_rate": 2.1153902234608112e-08,
+      "loss": 1.4171,
+      "step": 4805
+    },
+    {
+      "epoch": 19.0,
+      "eval_loss": 1.2792030572891235,
+      "eval_runtime": 11.7078,
+      "eval_samples_per_second": 43.902,
+      "eval_steps_per_second": 5.552,
+      "step": 4807
     }
   ],
-  "max_steps": 6994,
-  "num_train_epochs": 26,
-  "total_flos": 4776548990976000.0,
+  "max_steps": 6831,
+  "num_train_epochs": 27,
+  "total_flos": 5020465102848000.0,
   "trial_name": null,
   "trial_params": null
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c111611d0270c2f70ae5a43dbcc59025e6535cde71a5fbf71689de64f457d265
-size 2991
+oid sha256:9c8a04c78ae405c90d321579f04eceaba457a750930ce8d60249e0bee7dbd178
+size 3311