Upload 7 files

config.json

@@ -0,0 +1,41 @@
+{
+  "_name_or_path": "openai-community/gpt2-medium",
+  "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": 1024,
+  "n_head": 16,
+  "n_inner": null,
+  "n_layer": 24,
+  "n_positions": 1024,
+  "n_special": 0,
+  "predict_special_tokens": true,
+  "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": "4.44.2",
+  "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": "4.44.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30a5a8869cc6b8be2702cb92117d28a9effd38a1d9d91f09bf15048f018aa6e7
+size 1419322880

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86be11bdb56d36be3719d63e94d396403e097213c13523f8721608aeed30e487
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8213b1e13d3852acfb7fa839c00d68cbee4b0785cd4e10adbdf208b49496677f
+size 1064

trainer_state.json

@@ -0,0 +1,61 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.859427296392711,
+  "eval_steps": 500,
+  "global_step": 10000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.46485682409817775,
+      "grad_norm": 0.7774684429168701,
+      "learning_rate": 4.024960998439938e-05,
+      "loss": 0.2221,
+      "step": 2500
+    },
+    {
+      "epoch": 0.9297136481963555,
+      "grad_norm": 0.49191537499427795,
+      "learning_rate": 2.8061622464898596e-05,
+      "loss": 0.0269,
+      "step": 5000
+    },
+    {
+      "epoch": 1.3945704722945333,
+      "grad_norm": 0.2874563932418823,
+      "learning_rate": 1.5873634945397816e-05,
+      "loss": 0.0225,
+      "step": 7500
+    },
+    {
+      "epoch": 1.859427296392711,
+      "grad_norm": 0.3235009014606476,
+      "learning_rate": 3.685647425897036e-06,
+      "loss": 0.0205,
+      "step": 10000
+    }
+  ],
+  "logging_steps": 2500,
+  "max_steps": 10756,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 2500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.857308518986547e+16,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c3014b17ac527442cce9dc9e5514f88e140f7470575dc630a73ea6041c66b1a
+size 5176