Add files using upload-large-folder tool

config.json

@@ -0,0 +1,39 @@
+{
+  "_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,
+  "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": "4.48.1",
+  "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": "4.48.1"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8835811a329cdeb5e32f9818994ef317e142eccee0f2c9fc23e03787e1f214db
+size 497774208

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e8094076d42fde15f8629500bb62e2c235e0173631985e595dc4009e8973232
+size 995638202

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3142eb9ef29f39c1056feaba012d70697a15cdef061694ac7929853189d9ee94
+size 13990

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7990d8cf387ee75c28002e43c4cb3ec4f5f9431ec50428fad779e5d7de1da94
+size 1064

trainer_state.json

@@ -0,0 +1,124 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 6729,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.22291573785109228,
+      "grad_norm": 1.3647773265838623,
+      "learning_rate": 5e-05,
+      "loss": 0.7791,
+      "step": 500
+    },
+    {
+      "epoch": 0.44583147570218457,
+      "grad_norm": 0.9170280694961548,
+      "learning_rate": 4.598651468935624e-05,
+      "loss": 0.1977,
+      "step": 1000
+    },
+    {
+      "epoch": 0.6687472135532768,
+      "grad_norm": 0.8765759468078613,
+      "learning_rate": 4.1973029378712475e-05,
+      "loss": 0.1697,
+      "step": 1500
+    },
+    {
+      "epoch": 0.8916629514043691,
+      "grad_norm": 0.6906009912490845,
+      "learning_rate": 3.7959544068068715e-05,
+      "loss": 0.1548,
+      "step": 2000
+    },
+    {
+      "epoch": 1.1145786892554614,
+      "grad_norm": 0.9499293565750122,
+      "learning_rate": 3.394605875742495e-05,
+      "loss": 0.1323,
+      "step": 2500
+    },
+    {
+      "epoch": 1.3374944271065536,
+      "grad_norm": 0.822642982006073,
+      "learning_rate": 2.9932573446781187e-05,
+      "loss": 0.1174,
+      "step": 3000
+    },
+    {
+      "epoch": 1.560410164957646,
+      "grad_norm": 0.757134735584259,
+      "learning_rate": 2.591908813613742e-05,
+      "loss": 0.1101,
+      "step": 3500
+    },
+    {
+      "epoch": 1.7833259028087383,
+      "grad_norm": 0.6683522462844849,
+      "learning_rate": 2.190560282549366e-05,
+      "loss": 0.1051,
+      "step": 4000
+    },
+    {
+      "epoch": 2.0062416406598307,
+      "grad_norm": 0.7783832550048828,
+      "learning_rate": 1.7892117514849896e-05,
+      "loss": 0.1017,
+      "step": 4500
+    },
+    {
+      "epoch": 2.229157378510923,
+      "grad_norm": 0.6604039669036865,
+      "learning_rate": 1.3878632204206132e-05,
+      "loss": 0.0858,
+      "step": 5000
+    },
+    {
+      "epoch": 2.452073116362015,
+      "grad_norm": 0.7059195637702942,
+      "learning_rate": 9.86514689356237e-06,
+      "loss": 0.0835,
+      "step": 5500
+    },
+    {
+      "epoch": 2.6749888542131073,
+      "grad_norm": 0.6601874232292175,
+      "learning_rate": 5.851661582918607e-06,
+      "loss": 0.0824,
+      "step": 6000
+    },
+    {
+      "epoch": 2.8979045920642,
+      "grad_norm": 0.6698402762413025,
+      "learning_rate": 1.8381762722748435e-06,
+      "loss": 0.0816,
+      "step": 6500
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 6729,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 10000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 7031368581120000.0,
+  "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 sha256:1a401f7020de415b1953e572673fe741cdcef28de582b496d9b2915560705d09
+size 5240