first GPT2 model with ~2M words

all_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 0.324633431085044,
+    "eval_loss": 4.011027812957764,
+    "eval_runtime": 4.2815,
+    "eval_samples": 90,
+    "eval_samples_per_second": 21.021,
+    "eval_steps_per_second": 2.803,
+    "perplexity": 55.20358037015378,
+    "train_loss": 5.383951053103885,
+    "train_runtime": 1331.1447,
+    "train_samples": 2962,
+    "train_samples_per_second": 6.675,
+    "train_steps_per_second": 1.668
+}

config.json

@@ -0,0 +1,31 @@
+{
+  "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_embd": 768,
+  "n_head": 12,
+  "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,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.29.0.dev0",
+  "use_cache": true,
+  "vocab_size": 50257
+}

eval_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 0.324633431085044,
+    "eval_loss": 4.011027812957764,
+    "eval_runtime": 4.2815,
+    "eval_samples": 90,
+    "eval_samples_per_second": 21.021,
+    "eval_steps_per_second": 2.803,
+    "perplexity": 55.20358037015378
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.29.0.dev0"
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8bf0b0af6a8962bbbbdcb71b61c21662f1bbcc0cd9c76631eae5696396c6b8eb
+size 510396521

special_tokens_map.json

@@ -0,0 +1,5 @@
+{
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
+}

tokenizer_config.json

@@ -0,0 +1,9 @@
+{
+  "add_prefix_space": false,
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1024,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "train_loss": 5.383951053103885,
+    "train_runtime": 1331.1447,
+    "train_samples": 2962,
+    "train_samples_per_second": 6.675,
+    "train_steps_per_second": 1.668
+}

trainer_state.json

@@ -0,0 +1,49 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.99797434166104,
+  "global_step": 2220,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.68,
+      "learning_rate": 3.873873873873874e-05,
+      "loss": 6.1827,
+      "step": 500
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 2.7477477477477483e-05,
+      "loss": 5.3106,
+      "step": 1000
+    },
+    {
+      "epoch": 2.03,
+      "learning_rate": 1.6216216216216218e-05,
+      "loss": 5.1566,
+      "step": 1500
+    },
+    {
+      "epoch": 2.7,
+      "learning_rate": 4.954954954954955e-06,
+      "loss": 5.057,
+      "step": 2000
+    },
+    {
+      "epoch": 3.0,
+      "step": 2220,
+      "total_flos": 4640546488320000.0,
+      "train_loss": 5.383951053103885,
+      "train_runtime": 1331.1447,
+      "train_samples_per_second": 6.675,
+      "train_steps_per_second": 1.668
+    }
+  ],
+  "max_steps": 2220,
+  "num_train_epochs": 3,
+  "total_flos": 4640546488320000.0,
+  "trial_name": null,
+  "trial_params": null
+}