initial commit

all_results.json

@@ -0,0 +1,23 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 3.290411949157715,
+    "eval_mem_cpu_alloc_delta": 544768,
+    "eval_mem_cpu_peaked_delta": 73728,
+    "eval_mem_gpu_alloc_delta": 0,
+    "eval_mem_gpu_peaked_delta": 2645388800,
+    "eval_runtime": 803.942,
+    "eval_samples": 28999,
+    "eval_samples_per_second": 36.071,
+    "init_mem_cpu_alloc_delta": -36622336,
+    "init_mem_cpu_peaked_delta": 1313382400,
+    "init_mem_gpu_alloc_delta": 1444470784,
+    "init_mem_gpu_peaked_delta": 0,
+    "perplexity": 26.853923828930338,
+    "train_mem_cpu_alloc_delta": 596549632,
+    "train_mem_cpu_peaked_delta": 0,
+    "train_mem_gpu_alloc_delta": 4257896960,
+    "train_mem_gpu_peaked_delta": 2961890816,
+    "train_runtime": 4429.0691,
+    "train_samples": 29667,
+    "train_samples_per_second": 1.675
+}

config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "gpt2-medium",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "gradient_checkpointing": false,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 1024,
+  "n_head": 16,
+  "n_inner": null,
+  "n_layer": 24,
+  "n_positions": 1024,
+  "n_special": 0,
+  "predict_special_tokens": true,
+  "resid_pdrop": 0.1,
+  "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
+    }
+  },
+  "transformers_version": "4.6.1",
+  "use_cache": true,
+  "vocab_size": 50257
+}

eval_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 3.290411949157715,
+    "eval_mem_cpu_alloc_delta": 544768,
+    "eval_mem_cpu_peaked_delta": 73728,
+    "eval_mem_gpu_alloc_delta": 0,
+    "eval_mem_gpu_peaked_delta": 2645388800,
+    "eval_runtime": 803.942,
+    "eval_samples": 28999,
+    "eval_samples_per_second": 36.071,
+    "perplexity": 26.853923828930338
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18c2b63395a67d42dc83d29faecc24a4bb952c971e25eaf10b631412a987f6dd
+size 186286080

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": "gpt2-medium"}

train_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 1.0,
+    "init_mem_cpu_alloc_delta": -36622336,
+    "init_mem_cpu_peaked_delta": 1313382400,
+    "init_mem_gpu_alloc_delta": 1444470784,
+    "init_mem_gpu_peaked_delta": 0,
+    "train_mem_cpu_alloc_delta": 596549632,
+    "train_mem_cpu_peaked_delta": 0,
+    "train_mem_gpu_alloc_delta": 4257896960,
+    "train_mem_gpu_peaked_delta": 2961890816,
+    "train_runtime": 4429.0691,
+    "train_samples": 29667,
+    "train_samples_per_second": 1.675
+}

trainer_state.json

@@ -0,0 +1,107 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "global_step": 7417,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.07,
+      "learning_rate": 4.6629364972360795e-05,
+      "loss": 3.4842,
+      "step": 500
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 4.325872994472159e-05,
+      "loss": 3.4358,
+      "step": 1000
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 3.988809491708238e-05,
+      "loss": 3.4252,
+      "step": 1500
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 3.6517459889443174e-05,
+      "loss": 3.3965,
+      "step": 2000
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 3.314682486180397e-05,
+      "loss": 3.3921,
+      "step": 2500
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 2.977618983416476e-05,
+      "loss": 3.3917,
+      "step": 3000
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 2.6405554806525552e-05,
+      "loss": 3.3715,
+      "step": 3500
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 2.3034919778886342e-05,
+      "loss": 3.3522,
+      "step": 4000
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 1.9664284751247135e-05,
+      "loss": 3.354,
+      "step": 4500
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 1.6293649723607928e-05,
+      "loss": 3.3391,
+      "step": 5000
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 1.2923014695968722e-05,
+      "loss": 3.3427,
+      "step": 5500
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 9.552379668329513e-06,
+      "loss": 3.3244,
+      "step": 6000
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 6.181744640690306e-06,
+      "loss": 3.3286,
+      "step": 6500
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 2.811109613051099e-06,
+      "loss": 3.3197,
+      "step": 7000
+    },
+    {
+      "epoch": 1.0,
+      "step": 7417,
+      "total_flos": 0,
+      "train_runtime": 4429.0691,
+      "train_samples_per_second": 1.675
+    }
+  ],
+  "max_steps": 7417,
+  "num_train_epochs": 1,
+  "total_flos": 0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65335bd9a139472b555eec03a8d2f07935a01874aeba36f9290882b42df305f2
+size 2188