huggingartists

README.md

@@ -45,15 +45,15 @@ from datasets import load_dataset
 dataset = load_dataset("huggingartists/6ix9ine")
 ```
 
-[Explore the data](https://wandb.ai/huggingartists/huggingartists/runs/1ubrxjqi/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/33owzv4t/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 6ix9ine's lyrics.
 
-Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/x99noxul) for full transparency and reproducibility.
+Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/22q1oxft) for full transparency and reproducibility.
 
-At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/x99noxul/artifacts) is logged and versioned.
+At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/22q1oxft/artifacts) is logged and versioned.
 
 ## How to use
 

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "gpt2",
+  "_name_or_path": "huggingartists/6ix9ine",
   "activation_function": "gelu_new",
   "architectures": [
     "GPT2LMHeadModel"

evaluation.txt

@@ -1 +1 @@
-{"eval_loss": 3.22310209274292, "eval_runtime": 2.9511, "eval_samples_per_second": 21.009, "eval_steps_per_second": 2.711, "epoch": 1.0}
+{"eval_loss": 3.0470073223114014, "eval_runtime": 2.6704, "eval_samples_per_second": 20.596, "eval_steps_per_second": 2.621, "epoch": 2.0}

flax_model.msgpack

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:21a29eb776edb4b712524c6abba8c4860f899e3635fd68ff7cc59a3d49975c8a
+oid sha256:8df15ff3bf9d8a1748a052761e63c3b2f0e766961f7279a8de10378dfaeaf585
 size 497764120

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:635c24ec0c45101d2cc83a7e5762597d78a3de8b7f6009164decc1d7593a427c
+oid sha256:fb7c973b07fc7925a7773a7a9b8e96db55101b49d6bf109cfa76b63b9f7b450e
 size 995603825

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d406ad882369a3e603cd147a311f51ecf1dc400c235f725ce5f0ad6a38a17306
+oid sha256:fd1cf3ab818bb31d83b57f1db70e0d084389c521eecdf3cbb96f980dd4a48168
 size 510403817

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:803cf259ab295010aaedc7ed0ba89a9d393a8018b1e858e6b80cb18034f8b057
+oid sha256:29d7a8e82d5104f8855899362d2c29661c48c9cc84dceb8ac5bbc637db2337f5
 size 14503

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d4369506dedd54e65c6967a3362585e3aa7b5afb87732c009d3c12491c2fbd1
+oid sha256:00dd6b6c01d14ec8bb955c14a18bd11e818291c6d3cf3ac44048cedcc0186d76
 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/6ix9ine", "tokenizer_class": "GPT2Tokenizer"}

trainer_state.json

@@ -1,72 +1,128 @@
 {
-  "best_metric": 3.22310209274292,
-  "best_model_checkpoint": "output/6ix9ine/checkpoint-41",
-  "epoch": 1.0,
-  "global_step": 41,
+  "best_metric": 3.0470073223114014,
+  "best_model_checkpoint": "output/6ix9ine/checkpoint-84",
+  "epoch": 2.0,
+  "global_step": 84,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 0.12,
-      "learning_rate": 0.0001322266681456037,
-      "loss": 3.9471,
+      "learning_rate": 4.742060843007589e-06,
+      "loss": 3.316,
       "step": 5
     },
     {
       "epoch": 0.24,
-      "learning_rate": 0.00011802778132101399,
-      "loss": 3.8762,
+      "learning_rate": 1.8312641592473922e-05,
+      "loss": 3.5414,
       "step": 10
     },
     {
-      "epoch": 0.37,
-      "learning_rate": 9.666210850995393e-05,
-      "loss": 3.5952,
+      "epoch": 0.36,
+      "learning_rate": 3.88355754965355e-05,
+      "loss": 3.3994,
       "step": 15
     },
     {
-      "epoch": 0.49,
-      "learning_rate": 7.122756753113643e-05,
-      "loss": 3.596,
+      "epoch": 0.48,
+      "learning_rate": 6.347351557997133e-05,
+      "loss": 3.2221,
       "step": 20
     },
     {
-      "epoch": 0.61,
-      "learning_rate": 4.541204214117672e-05,
-      "loss": 3.577,
+      "epoch": 0.6,
+      "learning_rate": 8.882020496458803e-05,
+      "loss": 3.2784,
       "step": 25
     },
     {
-      "epoch": 0.73,
-      "learning_rate": 2.2958656968642224e-05,
-      "loss": 3.469,
+      "epoch": 0.71,
+      "learning_rate": 0.00011137140040750911,
+      "loss": 3.376,
       "step": 30
     },
     {
-      "epoch": 0.85,
-      "learning_rate": 7.123042792471594e-06,
-      "loss": 3.3983,
+      "epoch": 0.83,
+      "learning_rate": 0.00012800934269961248,
+      "loss": 3.0065,
       "step": 35
     },
     {
-      "epoch": 0.98,
-      "learning_rate": 2.0128603879540573e-07,
-      "loss": 3.4279,
+      "epoch": 0.95,
+      "learning_rate": 0.0001364337946790438,
+      "loss": 3.118,
       "step": 40
     },
     {
       "epoch": 1.0,
-      "eval_loss": 3.22310209274292,
-      "eval_runtime": 2.9378,
-      "eval_samples_per_second": 21.104,
-      "eval_steps_per_second": 2.723,
-      "step": 41
+      "eval_loss": 3.159865617752075,
+      "eval_runtime": 2.6213,
+      "eval_samples_per_second": 20.982,
+      "eval_steps_per_second": 2.67,
+      "step": 42
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 0.0001354800547756731,
+      "loss": 3.1208,
+      "step": 45
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 0.00012527997991807724,
+      "loss": 2.8559,
+      "step": 50
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 0.00010724375598316453,
+      "loss": 2.9927,
+      "step": 55
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 8.386493606940326e-05,
+      "loss": 2.9799,
+      "step": 60
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 5.8375700540314535e-05,
+      "loss": 2.9474,
+      "step": 65
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 3.4300000000000054e-05,
+      "loss": 2.8929,
+      "step": 70
+    },
+    {
+      "epoch": 1.79,
+      "learning_rate": 1.496636030269317e-05,
+      "loss": 2.821,
+      "step": 75
+    },
+    {
+      "epoch": 1.9,
+      "learning_rate": 3.04770552307078e-06,
+      "loss": 2.7814,
+      "step": 80
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 3.0470073223114014,
+      "eval_runtime": 2.6251,
+      "eval_samples_per_second": 20.952,
+      "eval_steps_per_second": 2.667,
+      "step": 84
     }
   ],
-  "max_steps": 41,
-  "num_train_epochs": 1,
-  "total_flos": 42198663168000.0,
+  "max_steps": 84,
+  "num_train_epochs": 2,
+  "total_flos": 86226370560000.0,
   "trial_name": null,
   "trial_params": null
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:74489e50cba909b350e219cdb2c55931c833346ab293b4d186155c74b5daf6cf
+oid sha256:cd271d0572a7a3468694d79a611ddcf794549420f744198cdf5961c723dc8d78
 size 2863