Upload 7 files

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": "4.37.1",
+  "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": "4.37.1"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c93ade789c627f9af698ccd021899b169a9707952d78f3952c2c6de085e8708
+size 497774208

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:95209bca370a53a124e92620ff7b93d26b049c08c6593bd2d77a61443c2b5e0e
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb8572ebaa364ccd203f27cd2f8cf84d02c67072836233db8d6d9edc539e77f6
+size 1064

trainer_state.json

@@ -0,0 +1,195 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9971803864933636,
+  "eval_steps": 500,
+  "global_step": 14500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03,
+      "learning_rate": 4.828072347156317e-05,
+      "loss": 1.3416,
+      "step": 500
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 4.656144694312634e-05,
+      "loss": 1.1277,
+      "step": 1000
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 4.4842170414689496e-05,
+      "loss": 1.0744,
+      "step": 1500
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 4.312289388625267e-05,
+      "loss": 1.034,
+      "step": 2000
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 4.140361735781583e-05,
+      "loss": 1.013,
+      "step": 2500
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 3.9684340829379003e-05,
+      "loss": 0.9948,
+      "step": 3000
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 3.796506430094217e-05,
+      "loss": 0.9951,
+      "step": 3500
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 3.624578777250533e-05,
+      "loss": 0.9735,
+      "step": 4000
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 3.45265112440685e-05,
+      "loss": 0.9796,
+      "step": 4500
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 3.280723471563166e-05,
+      "loss": 0.9688,
+      "step": 5000
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 3.108795818719483e-05,
+      "loss": 0.9511,
+      "step": 5500
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 2.9368681658757994e-05,
+      "loss": 0.9531,
+      "step": 6000
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 2.764940513032116e-05,
+      "loss": 0.9337,
+      "step": 6500
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 2.593012860188433e-05,
+      "loss": 0.9208,
+      "step": 7000
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 2.4210852073447495e-05,
+      "loss": 0.9241,
+      "step": 7500
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 2.249157554501066e-05,
+      "loss": 0.9049,
+      "step": 8000
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 2.0772299016573828e-05,
+      "loss": 0.9192,
+      "step": 8500
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 1.9053022488136992e-05,
+      "loss": 0.9219,
+      "step": 9000
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 1.733374595970016e-05,
+      "loss": 0.9034,
+      "step": 9500
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 1.5614469431263325e-05,
+      "loss": 0.9074,
+      "step": 10000
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 1.3895192902826493e-05,
+      "loss": 0.9088,
+      "step": 10500
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 1.2175916374389657e-05,
+      "loss": 0.9119,
+      "step": 11000
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 1.0456639845952824e-05,
+      "loss": 0.8996,
+      "step": 11500
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 8.73736331751599e-06,
+      "loss": 0.8881,
+      "step": 12000
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 7.018086789079156e-06,
+      "loss": 0.9013,
+      "step": 12500
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 5.298810260642322e-06,
+      "loss": 0.8916,
+      "step": 13000
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 3.5795337322054882e-06,
+      "loss": 0.8953,
+      "step": 13500
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 1.8602572037686543e-06,
+      "loss": 0.8992,
+      "step": 14000
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 1.4098067533182036e-07,
+      "loss": 0.8785,
+      "step": 14500
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 14541,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "total_flos": 3788734464000000.0,
+  "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 sha256:0c6886914ea90165c754b8e8f65313a1df042742ca726f08b39e5d9e2e2401d8
+size 4664