huggingartists

README.md

@@ -45,15 +45,15 @@ from datasets import load_dataset
 dataset = load_dataset("huggingartists/tool")
 ```
 
-[Explore the data](https://wandb.ai/huggingartists/huggingartists/runs/3ql2lz0c/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/2i0nfbt3/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 Tool's lyrics.
 
-Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/vc1gg3ig) for full transparency and reproducibility.
+Hyperparameters and metrics are recorded in the [W&B training run](https://wandb.ai/huggingartists/huggingartists/runs/35jhzbcz) for full transparency and reproducibility.
 
-At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/vc1gg3ig/artifacts) is logged and versioned.
+At the end of training, [the final model](https://wandb.ai/huggingartists/huggingartists/runs/35jhzbcz/artifacts) is logged and versioned.
 
 ## How to use
 

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "gpt2",
+  "_name_or_path": "tool",
   "activation_function": "gelu_new",
   "architectures": [
     "GPT2LMHeadModel"
@@ -18,7 +18,9 @@
   "n_inner": null,
   "n_layer": 12,
   "n_positions": 1024,
+  "reorder_and_upcast_attn": false,
   "resid_pdrop": 0.1,
+  "scale_attn_by_inverse_layer_idx": false,
   "scale_attn_weights": true,
   "summary_activation": null,
   "summary_first_dropout": 0.1,
@@ -35,7 +37,7 @@
     }
   },
   "torch_dtype": "float32",
-  "transformers_version": "4.9.2",
+  "transformers_version": "4.16.2",
   "use_cache": true,
   "vocab_size": 50257
 }

evaluation.txt

@@ -1 +1 @@
-{"eval_loss": 2.716337203979492, "eval_runtime": 0.6909, "eval_samples_per_second": 20.264, "eval_steps_per_second": 2.895, "epoch": 4.0}
+{"eval_loss": 2.619758367538452, "eval_runtime": 0.6775, "eval_samples_per_second": 19.187, "eval_steps_per_second": 2.952, "epoch": 4.0}

flax_model.msgpack

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d190d46a017c4853022282d146db288ed5372fa45224358c599dcb848644f72
+oid sha256:8269b8328a0bf533c21e8a9cf8abb1251769e6472a5655d46e0263fa5c36c202
 size 497764120

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7aadfa0928299f84fe7da08d9f37e57a6ab6987f60699771276a8675cf63e170
+oid sha256:ffe7e75417a67202ed0582065f1a9bd973196ecaaf6283e0353d348b8b2c9ce5
 size 995603825

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a135f5da3c0ef8b9a6d9406b1d6608e8c1a91fca91cad4bcb07ae75b2ccd2f8e
+oid sha256:cda16091180e330446812bef2213ce1d274c30224756be5cc5af4152ec723633
 size 510403817

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7120a97908d485a86256aee2d3e7f6c1ef45fc650232402b60dace0f92e24635
-size 14567
+oid sha256:594209d63fbcb9f59cdfbe58a2c20b27bc86dba538eb2c90c6868cbdfcae50dc
+size 14503

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8989e74728331765fdc15dc13be950f4c53d6c5551f5ee94e2d269e65894c977
+oid sha256:46ac68174300d9f94d4de67167852595a5a6202d18703222cb9d7154becc9e21
 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/tool", "tokenizer_class": "GPT2Tokenizer"}

trainer_state.json

@@ -1,8 +1,8 @@
 {
-  "best_metric": 2.716337203979492,
-  "best_model_checkpoint": "output/tool/checkpoint-33",
-  "epoch": 3.0,
-  "global_step": 33,
+  "best_metric": 2.619758367538452,
+  "best_model_checkpoint": "output/tool/checkpoint-44",
+  "epoch": 4.0,
+  "global_step": 44,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -66,11 +66,31 @@
       "eval_samples_per_second": 22.166,
       "eval_steps_per_second": 3.167,
       "step": 33
+    },
+    {
+      "epoch": 3.18,
+      "learning_rate": 1.0890007647780947e-05,
+      "loss": 2.7361,
+      "step": 35
+    },
+    {
+      "epoch": 3.64,
+      "learning_rate": 9.709746989192932e-05,
+      "loss": 2.4185,
+      "step": 40
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 2.619758367538452,
+      "eval_runtime": 0.5572,
+      "eval_samples_per_second": 23.33,
+      "eval_steps_per_second": 3.589,
+      "step": 44
     }
   ],
   "max_steps": 44,
   "num_train_epochs": 4,
-  "total_flos": 34490548224000.0,
+  "total_flos": 45987397632000.0,
   "trial_name": null,
   "trial_params": null
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e352d83522f0bdc1377fe6e64bbdf81888764a91748c1cae15f658e7d1ddff2
-size 2671
+oid sha256:238f0800c1a375eef579856b16d2fb58efef9b9559fe5020f52fdd21d2d5f559
+size 3055