Upload 13 files

checkpoint-1500/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": "4.30.2",
+  "use_cache": true,
+  "vocab_size": 50257
+}

checkpoint-1500/generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.30.2"
+}

checkpoint-1500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93daf3f28632448bfedf803d90b0055e486c1be5a4e9c7c4e3f63303f8b0510e
+size 655345093

checkpoint-1500/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50c2ba4dfe46bb669dc6e509b726f6f6937182c0cda05c415c5528c2f21bcebe
+size 327674773

checkpoint-1500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5bbda08df963d83b8d56209a7e63e90e0866f950917443f91e914d9375b796fc
+size 14575

checkpoint-1500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:002854506d23d33db8b8b83fc345f8f15f292f95637764e4365a8df1e91bacd7
+size 627

checkpoint-1500/special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "pad_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
+}

checkpoint-1500/tokenizer_config.json

@@ -0,0 +1,9 @@
+{
+  "add_prefix_space": false,
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1024,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

checkpoint-1500/trainer_state.json

@@ -0,0 +1,44 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.7472527472527473,
+  "global_step": 1500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 1.3345543345543346e-05,
+      "loss": 3.9974,
+      "step": 545
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 3.886345148086548,
+      "eval_runtime": 46.7919,
+      "eval_samples_per_second": 2490.261,
+      "eval_steps_per_second": 4.873,
+      "step": 546
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 6.691086691086692e-06,
+      "loss": 3.9508,
+      "step": 1090
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 3.8692381381988525,
+      "eval_runtime": 46.4902,
+      "eval_samples_per_second": 2506.422,
+      "eval_steps_per_second": 4.904,
+      "step": 1092
+    }
+  ],
+  "max_steps": 1638,
+  "num_train_epochs": 3,
+  "total_flos": 3133838081654784.0,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73fc4faf2151efe52359414dfc1c9323e4767c16a7c6ba807417e90be4df15d6
+size 3963