Upload 8 files

config.json

@@ -0,0 +1,46 @@
+{
+  "_name_or_path": "distilgpt2",
+  "_num_labels": 1,
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 6,
+  "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": "4.28.1",
+  "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": "4.28.1"
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1ac022e9caf7388e88529fd1f92656861f56b0335e2f6d3191400f12183dcae
+size 655342981

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19d9c3bf28a4f7f7bce2ec777e785073176e2492cb147b26f07672db38bcfbdd
+size 333968953

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dce587e1d1836dcc7e92c4ff2e52fd001beb0e6152dcc8ff8a055b4d2747dd57
+size 13553

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e0d1f9e6447722d8ef7e50402393e6f9dbfd047229657345d4e4d8e622f1ebf
+size 627

trainer_state.json

@@ -0,0 +1,44 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.5510204081632653,
+  "global_step": 1000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 1.6521975994110107,
+      "eval_runtime": 3389.1646,
+      "eval_samples_per_second": 0.784,
+      "eval_steps_per_second": 0.098,
+      "step": 392
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 1.1496598639455783e-05,
+      "loss": 1.8651,
+      "step": 500
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 1.5567281246185303,
+      "eval_runtime": 3435.2549,
+      "eval_samples_per_second": 0.773,
+      "eval_steps_per_second": 0.097,
+      "step": 784
+    },
+    {
+      "epoch": 2.55,
+      "learning_rate": 2.993197278911565e-06,
+      "loss": 1.6389,
+      "step": 1000
+    }
+  ],
+  "max_steps": 1176,
+  "num_train_epochs": 3,
+  "total_flos": 1019414568960000.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d31bfac8da11b0ca8a1be79fefee2a6343a9e14f7d62fd5cc9a3c717e45d082
+size 3579