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:fcfa79cb15f576d12e8191b177a41456c4699d74d9e9a3cdeb71a9269bd0d6cc
+size 1431912264

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48270d1290a1fef1fd188fe2432bd41cdacf0f1e5070184e2a0b56fed34f5601
+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 +1,103 @@
+{
+  "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": 0.19896538002387584,
+      "grad_norm": 0.22902533411979675,
+      "learning_rate": 5e-05,
+      "loss": 3.7966,
+      "step": 500
+    },
+    {
+      "epoch": 0.3979307600477517,
+      "grad_norm": 0.22708623111248016,
+      "learning_rate": 4.447635881573133e-05,
+      "loss": 1.4108,
+      "step": 1000
+    },
+    {
+      "epoch": 0.5968961400716275,
+      "grad_norm": 0.20095278322696686,
+      "learning_rate": 3.895271763146266e-05,
+      "loss": 1.365,
+      "step": 1500
+    },
+    {
+      "epoch": 0.7958615200955034,
+      "grad_norm": 0.1303737759590149,
+      "learning_rate": 3.342907644719399e-05,
+      "loss": 1.3683,
+      "step": 2000
+    },
+    {
+      "epoch": 0.9948269001193792,
+      "grad_norm": 0.21030685305595398,
+      "learning_rate": 2.7905435262925323e-05,
+      "loss": 1.3898,
+      "step": 2500
+    },
+    {
+      "epoch": 1.193792280143255,
+      "grad_norm": 0.18989521265029907,
+      "learning_rate": 2.2381794078656652e-05,
+      "loss": 1.3441,
+      "step": 3000
+    },
+    {
+      "epoch": 1.392757660167131,
+      "grad_norm": 0.19548365473747253,
+      "learning_rate": 1.6858152894387984e-05,
+      "loss": 1.3469,
+      "step": 3500
+    },
+    {
+      "epoch": 1.5917230401910067,
+      "grad_norm": 0.23873193562030792,
+      "learning_rate": 1.133451171011931e-05,
+      "loss": 1.3736,
+      "step": 4000
+    },
+    {
+      "epoch": 1.7906884202148827,
+      "grad_norm": 0.2010679692029953,
+      "learning_rate": 5.810870525850641e-06,
+      "loss": 1.3847,
+      "step": 4500
+    },
+    {
+      "epoch": 1.9896538002387585,
+      "grad_norm": 0.19471381604671478,
+      "learning_rate": 2.872293415819708e-07,
+      "loss": 1.3575,
+      "step": 5000
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 5026,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.88611238559744e+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 sha256:7c47030ff993b11cf8048b55d02879fdf62c42835d7a1bc97ac583761f94cb6b
+size 5176