huggingartists

README.md

@@ -45,15 +45,15 @@ from datasets import load_dataset
 dataset = load_dataset("huggingartists/enigma")
 ```
 
-[Explore the data](https://wandb.ai/huggingartists/huggingartists/runs/2zrl31ns/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/8bx90lw6/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 Enigma's lyrics.
 
-Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/2706pjfi) for full transparency and reproducibility.
+Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/1c1t20ji) for full transparency and reproducibility.
 
-At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/2706pjfi/artifacts) is logged and versioned.
+At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/1c1t20ji/artifacts) is logged and versioned.
 
 ## How to use
 

config.json

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

evaluation.txt

@@ -1 +1 @@
-{"eval_loss": 3.9204065799713135, "eval_runtime": 2.4219, "eval_samples_per_second": 19.819, "eval_steps_per_second": 2.477, "epoch": 1.0}
+{"eval_loss": 3.7314870357513428, "eval_runtime": 2.1159, "eval_samples_per_second": 21.267, "eval_steps_per_second": 2.836, "epoch": 2.0}

flax_model.msgpack

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:27ae1e4faca11fb0373678ac6b341924ba8c2d751bb9995dd28b4f2da30ab69a
+oid sha256:34494afe6195414f25402b1092b21a6c5d3bc09e12b82a51595fc053106f4cbe
 size 497764120

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:983bd35bd9d10f8cc6cf739042bc36fd890ca9f5f3d884a1eac45dcdfa28e7f3
+oid sha256:91ffe69c515dd6b1670059d6078d23db802e476e919c1ebe2fa2e1574f8da98a
 size 995603825

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b449540dc207e6c17fe2e6f96fe7ca39dd301ba633a439eefffe60d5c2198c8d
+oid sha256:7ff70e5e7b675aa5d6178e40f4c978b332c317fa63f44e779e416cdbd5fc2a17
 size 510403817

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4865cef34c88ebff2de8694d032cb0c22961cc9866bf669c5b15cf1c9e378740
-size 14567
+oid sha256:2b94157e2bb9ab763b1509d4627cd0a65ce3c8a5bd3742b19eeec8bba1ef0aef
+size 14503

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8989e74728331765fdc15dc13be950f4c53d6c5551f5ee94e2d269e65894c977
+oid sha256:2222362d80f6c4a5547283104536d5c4564191fb641a9b7f7b9e346e9a58c2ee
 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/enigma", "tokenizer_class": "GPT2Tokenizer"}

trainer_state.json

@@ -1,8 +1,8 @@
 {
-  "best_metric": 3.9204065799713135,
-  "best_model_checkpoint": "output/enigma/checkpoint-33",
-  "epoch": 1.0,
-  "global_step": 33,
+  "best_metric": 3.7314870357513428,
+  "best_model_checkpoint": "output/enigma/checkpoint-66",
+  "epoch": 2.0,
+  "global_step": 66,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -50,11 +50,61 @@
       "eval_samples_per_second": 20.139,
       "eval_steps_per_second": 2.517,
       "step": 33
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 1.2396913677783124e-06,
+      "loss": 3.4099,
+      "step": 35
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 1.4676757700644785e-05,
+      "loss": 3.9212,
+      "step": 40
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 4.0102530108070535e-05,
+      "loss": 3.831,
+      "step": 45
+    },
+    {
+      "epoch": 1.52,
+      "learning_rate": 7.186411942550872e-05,
+      "loss": 3.4868,
+      "step": 50
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 0.00010290000000000001,
+      "loss": 3.5598,
+      "step": 55
+    },
+    {
+      "epoch": 1.82,
+      "learning_rate": 0.000126309992352219,
+      "loss": 3.6865,
+      "step": 60
+    },
+    {
+      "epoch": 1.97,
+      "learning_rate": 0.0001368893738885136,
+      "loss": 3.4504,
+      "step": 65
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 3.7314870357513428,
+      "eval_runtime": 1.9498,
+      "eval_samples_per_second": 23.079,
+      "eval_steps_per_second": 3.077,
+      "step": 66
     }
   ],
-  "max_steps": 33,
-  "num_train_epochs": 1,
-  "total_flos": 33837318144000.0,
+  "max_steps": 66,
+  "num_train_epochs": 2,
+  "total_flos": 68066574336000.0,
   "trial_name": null,
   "trial_params": null
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e5fc12339fb114391064e4dc6241e4a8a870fc0dae8a125fb4c0d8c60fd6d5a1
+oid sha256:23a6f855dcc08fc6611cb7b927ae059eb524cc6ac63995b001934043b86f8210
 size 2671