huggingartists

README.md

@@ -45,15 +45,15 @@ from datasets import load_dataset
 dataset = load_dataset("huggingartists/cardi-b")
 ```
 
-[Explore the data](https://wandb.ai/huggingartists/huggingartists/runs/gyop804e/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/2794795e/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 Cardi B's lyrics.
 
-Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/2ls1zza7) for full transparency and reproducibility.
+Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/1buiv5nf) for full transparency and reproducibility.
 
-At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/2ls1zza7/artifacts) is logged and versioned.
+At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/1buiv5nf/artifacts) is logged and versioned.
 
 ## How to use
 

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "gpt2",
+  "_name_or_path": "huggingartists/cardi-b",
   "activation_function": "gelu_new",
   "architectures": [
     "GPT2LMHeadModel"
@@ -35,7 +35,7 @@
     }
   },
   "torch_dtype": "float32",
-  "transformers_version": "4.10.2",
+  "transformers_version": "4.10.3",
   "use_cache": true,
   "vocab_size": 50257
 }

evaluation.txt

@@ -1 +1 @@
-{"eval_loss": 3.3664300441741943, "eval_runtime": 1.6554, "eval_samples_per_second": 42.89, "eval_steps_per_second": 5.437, "epoch": 1.0}
+{"eval_loss": 2.9845471382141113, "eval_runtime": 3.5891, "eval_samples_per_second": 21.454, "eval_steps_per_second": 2.786, "epoch": 2.0}

flax_model.msgpack

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:68dd29573f781095d9ad848fe4c8b6c2a22a1a287ec206a96c4ed108a61559c1
+oid sha256:aab7a5aa95958bd4c8c810e9b7acd8ff750da2c5eafe1cbbf3b6f40519373f40
 size 497764120

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49f94360ec805ce12fe6f0dfa4326451d8c48fda61a78c70af1e43e4ffd058d5
+oid sha256:89e6aded72e69f7bb9454c89045641fe99631a9eadc3ac776867f59a2b6ab290
 size 995603825

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:74955c53f4c610171358cb48c570ab0c10cc2b3ece76f517c6f6411aaa38644e
+oid sha256:69e9a718f89ae122d4823c99c69935afc63bdcdcdac02306b43ce41185505c77
 size 510403817

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0def2032f81512e3f8bff61f3e21073854d8d398d1be01592c54d7bfc7c874fd
-size 14503
+oid sha256:285cd8fb1eecf2a6ec93b901adfe605f19a10d2db64bcd2676529b2f8a13a1bf
+size 14439

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e450cb9c3dd5d5e299310845f6d7ab8731c0d1d1d427cd56769b403ce862ce4
+oid sha256:858b0150f63e516bfdd54df0bdcc3e1de87c6a580f8d9790a43f52a335f62cca
 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/cardi-b", "tokenizer_class": "GPT2Tokenizer"}

trainer_state.json

@@ -1,8 +1,8 @@
 {
-  "best_metric": 3.3664300441741943,
-  "best_model_checkpoint": "output/cardi-b/checkpoint-58",
-  "epoch": 1.0,
-  "global_step": 58,
+  "best_metric": 2.9845471382141113,
+  "best_model_checkpoint": "output/cardi-b/checkpoint-114",
+  "epoch": 2.0,
+  "global_step": 114,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -80,11 +80,85 @@
       "eval_samples_per_second": 44.424,
       "eval_steps_per_second": 5.631,
       "step": 58
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 9.35614586573241e-07,
+      "loss": 3.234,
+      "step": 60
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 6.5610987761461805e-06,
+      "loss": 3.3216,
+      "step": 65
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 1.6868286569304916e-05,
+      "loss": 3.2467,
+      "step": 70
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 3.1079356352801514e-05,
+      "loss": 3.3662,
+      "step": 75
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 4.8121883965283725e-05,
+      "loss": 3.3484,
+      "step": 80
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 6.670977211354408e-05,
+      "loss": 3.2623,
+      "step": 85
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 8.54403044178588e-05,
+      "loss": 3.0856,
+      "step": 90
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 0.00010290000000000001,
+      "loss": 3.2992,
+      "step": 95
+    },
+    {
+      "epoch": 1.75,
+      "learning_rate": 0.00011777128040335575,
+      "loss": 3.1025,
+      "step": 100
+    },
+    {
+      "epoch": 1.84,
+      "learning_rate": 0.00012893189933276512,
+      "loss": 3.2896,
+      "step": 105
+    },
+    {
+      "epoch": 1.93,
+      "learning_rate": 0.00013553963184824208,
+      "loss": 3.228,
+      "step": 110
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 2.9845471382141113,
+      "eval_runtime": 3.4603,
+      "eval_samples_per_second": 22.252,
+      "eval_steps_per_second": 2.89,
+      "step": 114
     }
   ],
-  "max_steps": 58,
-  "num_train_epochs": 1,
-  "total_flos": 59705229312000.0,
+  "max_steps": 114,
+  "num_train_epochs": 2,
+  "total_flos": 117581414400000.0,
   "trial_name": null,
   "trial_params": null
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a62540a61b468205c2469fc48112f0523a3e5bd744b567b166b214b48f501b94
+oid sha256:a2f61ff06cbbabd7f1d12a195eee711fc2c26b1693ce37e36414e8203238c3e3
 size 2671