init

config.json

@@ -0,0 +1,40 @@
+{
+  "_name_or_path": "gpt2",
+  "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": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 1024,
+  "pad_token_id": 50256,
+  "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": "4.26.0",
+  "use_cache": true,
+  "vocab_size": 50257
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.26.0"
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a37c8dd9aea01164e5b3cfbf7cf2a50aa31ca2c161a50846b53ad79f181d1fc8
+size 510398013

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "pad_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
+}

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",
+  "special_tokens_map_file": null,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

trainer_state.json

@@ -0,0 +1,64 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.0,
+  "global_step": 4000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.5,
+      "learning_rate": 4.605263157894737e-05,
+      "loss": 3.9918,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 3.9473684210526316e-05,
+      "loss": 3.7733,
+      "step": 1000
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 3.289473684210527e-05,
+      "loss": 3.4872,
+      "step": 1500
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 2.6315789473684212e-05,
+      "loss": 3.4665,
+      "step": 2000
+    },
+    {
+      "epoch": 2.5,
+      "learning_rate": 1.9736842105263158e-05,
+      "loss": 3.2853,
+      "step": 2500
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 1.3157894736842106e-05,
+      "loss": 3.2903,
+      "step": 3000
+    },
+    {
+      "epoch": 3.5,
+      "learning_rate": 6.578947368421053e-06,
+      "loss": 3.1943,
+      "step": 3500
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 0.0,
+      "loss": 3.1584,
+      "step": 4000
+    }
+  ],
+  "max_steps": 4000,
+  "num_train_epochs": 4,
+  "total_flos": 1516563449856000.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a59fa65465bf21f9dcde1273729c3242605f839092c893d7ffa78c0b733ea512
+size 3451