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": "4.45.1",
+  "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": "4.45.1"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f08fa80302c30ab2db5473b870a2a0be1f860a0f1bbfc6a9d27c10e38b7033b7
+size 1419322880

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:234a8325bb5a3b602a09f548ff0d0db74e3caddaa13034fe56d51908aef614b1
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22b3c4916f9e7b6fdda27e9f105e16daf01dc6e8120912243962f81a1f25cb49
+size 1064

trainer_state.json

@@ -0,0 +1,54 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 5026,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.5968961400716275,
+      "grad_norm": 0.9552611708641052,
+      "learning_rate": 3.895271763146266e-05,
+      "loss": 1.5143,
+      "step": 1500
+    },
+    {
+      "epoch": 1.193792280143255,
+      "grad_norm": 0.9094588756561279,
+      "learning_rate": 2.2381794078656652e-05,
+      "loss": 1.2757,
+      "step": 3000
+    },
+    {
+      "epoch": 1.7906884202148827,
+      "grad_norm": 0.9588974714279175,
+      "learning_rate": 5.810870525850641e-06,
+      "loss": 1.206,
+      "step": 4500
+    }
+  ],
+  "logging_steps": 1500,
+  "max_steps": 5026,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 1500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.86668839600128e+16,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69acac8ebf8ab3549d0be7e6b59ad3a70f1ff2efbd26476f3845be957825ee73
+size 5176