new model version

checkpoint

@@ -1,3 +0,0 @@
-model_checkpoint_path: "model-1809"
-all_model_checkpoint_paths: "model-1000"
-all_model_checkpoint_paths: "model-1809"

config.json

@@ -1,5 +1,9 @@
 {
+  "_name_or_path": "gpt2-medium",
   "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
   "attn_pdrop": 0.1,
   "bos_token_id": 50256,
   "embd_pdrop": 0.1,
@@ -13,7 +17,8 @@
   "n_inner": null,
   "n_layer": 24,
   "n_positions": 1024,
-  "n_vocab": 50257,
+  "n_special": 0,
+  "predict_special_tokens": true,
   "reorder_and_upcast_attn": false,
   "resid_pdrop": 0.1,
   "scale_attn_by_inverse_layer_idx": false,
@@ -23,7 +28,14 @@
   "summary_proj_to_labels": true,
   "summary_type": "cls_index",
   "summary_use_proj": true,
-  "transformers_version": "4.22.1",
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 50
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.23.0.dev0",
   "use_cache": true,
   "vocab_size": 50257
 }

counter

@@ -1 +0,0 @@
-1809

merges.txt

@@ -1,4 +1,4 @@
-#version: 0.2
+#version: 0.2 - Trained by `huggingface/tokenizers`
 Ġ t
 Ġ a
 h e

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:82992202046d96c34a3668abc556f88103bb4d5ccffc6536ca617fc2210c8c9a
-size 1444569625
+oid sha256:8b771e607deb7759c82cdf3518edc6159296409048d879a8577c28311631bcd9
+size 1444566873

tokenizer_config.json

@@ -0,0 +1,10 @@
+{
+  "add_prefix_space": false,
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1024,
+  "name_or_path": "gpt2-medium",
+  "special_tokens_map_file": null,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

trainer_state.json

@@ -0,0 +1,22 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.05319714863283328,
+  "global_step": 500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.05,
+      "learning_rate": 4.9473348228534955e-05,
+      "loss": 2.8884,
+      "step": 500
+    }
+  ],
+  "max_steps": 46995,
+  "num_train_epochs": 5,
+  "total_flos": 928700694528000.0,
+  "trial_name": null,
+  "trial_params": null
+}