End of training

.gitignore

@@ -0,0 +1 @@
+checkpoint-*/

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 3.0,
+    "eval_loss": 3.6250336170196533,
+    "eval_runtime": 0.6213,
+    "eval_samples": 5,
+    "eval_samples_per_second": 8.048,
+    "eval_steps_per_second": 1.61,
+    "perplexity": 37.525984650160595,
+    "train_loss": 3.7773597353980657,
+    "train_runtime": 16.24,
+    "train_samples": 13,
+    "train_samples_per_second": 2.401,
+    "train_steps_per_second": 1.293
+}

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": "4.12.0.dev0",
+  "use_cache": true,
+  "vocab_size": 50257
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 3.0,
+    "eval_loss": 3.6250336170196533,
+    "eval_runtime": 0.6213,
+    "eval_samples": 5,
+    "eval_samples_per_second": 8.048,
+    "eval_steps_per_second": 1.61,
+    "perplexity": 37.525984650160595
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e20c9331fb9f23b7f3854598b965a6f2024007553e27105a9cd2ee4827b19c70
+size 333972957

runs/Oct18_17-54-28_a3a7203bab16/1634579680.6827657/events.out.tfevents.1634579680.a3a7203bab16.691.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db085f68c84e1d8d9e34119d539ff95f88cda0c36d7e334e814de1e3a404d4c8
+size 4498

runs/Oct18_17-54-28_a3a7203bab16/events.out.tfevents.1634579680.a3a7203bab16.691.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60cb573dd9eff180cf233227e8c7528ba139ae995cb4f6af8518182de5f52b72
+size 3483

runs/Oct18_17-57-29_a3a7203bab16/1634579859.4019918/events.out.tfevents.1634579859.a3a7203bab16.799.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8bf86fe3b191eb969bd73ae6bbc994d037f9de9c8652513356d366e9480e97a
+size 4498

runs/Oct18_17-57-29_a3a7203bab16/events.out.tfevents.1634579859.a3a7203bab16.799.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb6ece8ed4dbc9421c2a8204e25d489fc4d485831c6c81f31b57f02cb29cb026
+size 3482

runs/Oct18_18-18-12_a3a7203bab16/1634581102.315263/events.out.tfevents.1634581102.a3a7203bab16.889.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a003495b0b882b2e1b592fb6eda341ac9e37b44adfabe8121d29ce662fb28452
+size 4498

runs/Oct18_18-18-12_a3a7203bab16/events.out.tfevents.1634581102.a3a7203bab16.889.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8a53c6c578bb41998d2e8d1e246b546fe3edc2e80e13c94d4d61dccb89a49ea
+size 3830

runs/Oct18_18-18-12_a3a7203bab16/events.out.tfevents.1634581120.a3a7203bab16.889.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12ca27823dc27245ba5a053ce7b4461b4e0303313259ae4a161898f386c8d81c
+size 306

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1 @@
+{"unk_token": "<|endoftext|>", "bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "add_prefix_space": false, "model_max_length": 1024, "special_tokens_map_file": null, "name_or_path": "distilgpt2", "tokenizer_class": "GPT2Tokenizer"}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "train_loss": 3.7773597353980657,
+    "train_runtime": 16.24,
+    "train_samples": 13,
+    "train_samples_per_second": 2.401,
+    "train_steps_per_second": 1.293
+}

trainer_state.json

@@ -0,0 +1,25 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "global_step": 21,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 3.0,
+      "step": 21,
+      "total_flos": 10190573273088.0,
+      "train_loss": 3.7773597353980657,
+      "train_runtime": 16.24,
+      "train_samples_per_second": 2.401,
+      "train_steps_per_second": 1.293
+    }
+  ],
+  "max_steps": 21,
+  "num_train_epochs": 3,
+  "total_flos": 10190573273088.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:836135b3a5c7fcfaf5c122180482782ef5ef109201e6e8f1aa0cdf12ac26c121
+size 2799