Upload 9 files

config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "finetuned_bottleself/gpt2-large_control_code_tenway_bucket_chunks_2_16_100_106_step5_two_epochs_repeatbucketid_fluencyfilter_1.0",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 1280,
+  "n_head": 20,
+  "n_inner": null,
+  "n_layer": 36,
+  "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,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 50
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.18.0.dev0",
+  "use_cache": true,
+  "vocab_size": 50257
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87b333bb7c679fbd55b9c533ded0346b6c2d641f2469f2a0cb1fe2ed6bcdc991
+size 3134054729

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "unk_token": "<|endoftext|>", "pad_token": "<|endoftext|>"}

tokenizer_config.json

@@ -0,0 +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-large", "tokenizer_class": "GPT2Tokenizer"}

trainer_state.json

@@ -0,0 +1,80 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "global_step": 4128,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.24,
+      "learning_rate": 3.7832929782082326e-05,
+      "loss": 1.8019,
+      "step": 500
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 5.920654149000606e-05,
+      "loss": 1.3315,
+      "step": 1000
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 4.974258025439128e-05,
+      "loss": 0.9419,
+      "step": 1500
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 4.0278619018776494e-05,
+      "loss": 0.6627,
+      "step": 2000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.49071434140205383,
+      "eval_runtime": 1039.783,
+      "eval_samples_per_second": 3.505,
+      "eval_steps_per_second": 0.351,
+      "step": 2064
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 3.081465778316172e-05,
+      "loss": 0.3682,
+      "step": 2500
+    },
+    {
+      "epoch": 1.45,
+      "learning_rate": 2.135069654754694e-05,
+      "loss": 0.2958,
+      "step": 3000
+    },
+    {
+      "epoch": 1.7,
+      "learning_rate": 1.1886735311932163e-05,
+      "loss": 0.2752,
+      "step": 3500
+    },
+    {
+      "epoch": 1.94,
+      "learning_rate": 2.4227740763173836e-06,
+      "loss": 0.246,
+      "step": 4000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.32644888758659363,
+      "eval_runtime": 1038.0256,
+      "eval_samples_per_second": 3.511,
+      "eval_steps_per_second": 0.352,
+      "step": 4128
+    }
+  ],
+  "max_steps": 4128,
+  "num_train_epochs": 2,
+  "total_flos": 7.01816537088e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:986f867243c2b38c07c61b6af226fa5aa0e75d82f91c076be795bca8fc3ef9bb
+size 3247