initial commit

all_results.json

@@ -0,0 +1,23 @@
+{
+    "epoch": 3.0,
+    "eval_loss": 4.299047470092773,
+    "eval_mem_cpu_alloc_delta": -192512,
+    "eval_mem_cpu_peaked_delta": 0,
+    "eval_mem_gpu_alloc_delta": 0,
+    "eval_mem_gpu_peaked_delta": 1846225408,
+    "eval_runtime": 5.1104,
+    "eval_samples": 95,
+    "eval_samples_per_second": 18.59,
+    "init_mem_cpu_alloc_delta": -145973248,
+    "init_mem_cpu_peaked_delta": 1313857536,
+    "init_mem_gpu_alloc_delta": 1444470784,
+    "init_mem_gpu_peaked_delta": 0,
+    "perplexity": 73.629625865726,
+    "train_mem_cpu_alloc_delta": 90374144,
+    "train_mem_cpu_peaked_delta": 10436608,
+    "train_mem_gpu_alloc_delta": 4257890816,
+    "train_mem_gpu_peaked_delta": 2657059328,
+    "train_runtime": 3295.7162,
+    "train_samples": 4268,
+    "train_samples_per_second": 1.943
+}

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": 3.0,
+    "eval_loss": 4.299047470092773,
+    "eval_mem_cpu_alloc_delta": -192512,
+    "eval_mem_cpu_peaked_delta": 0,
+    "eval_mem_gpu_alloc_delta": 0,
+    "eval_mem_gpu_peaked_delta": 1846225408,
+    "eval_runtime": 5.1104,
+    "eval_samples": 95,
+    "eval_samples_per_second": 18.59,
+    "perplexity": 73.629625865726
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:062b32c2d0f94ed04d3fd1eae2cb1d6d4609bab8ba8e9fdaf5ac5c566accd4a4
+size 1444531445

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": 3.0,
+    "init_mem_cpu_alloc_delta": -145973248,
+    "init_mem_cpu_peaked_delta": 1313857536,
+    "init_mem_gpu_alloc_delta": 1444470784,
+    "init_mem_gpu_peaked_delta": 0,
+    "train_mem_cpu_alloc_delta": 90374144,
+    "train_mem_cpu_peaked_delta": 10436608,
+    "train_mem_gpu_alloc_delta": 4257890816,
+    "train_mem_gpu_peaked_delta": 2657059328,
+    "train_runtime": 3295.7162,
+    "train_samples": 4268,
+    "train_samples_per_second": 1.943
+}

trainer_state.json

@@ -0,0 +1,95 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "global_step": 6402,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.23,
+      "learning_rate": 4.609497032177445e-05,
+      "loss": 3.0016,
+      "step": 500
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 4.218994064354889e-05,
+      "loss": 2.6439,
+      "step": 1000
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 3.828491096532334e-05,
+      "loss": 2.4277,
+      "step": 1500
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 3.437988128709778e-05,
+      "loss": 2.27,
+      "step": 2000
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 3.047485160887223e-05,
+      "loss": 1.9681,
+      "step": 2500
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 2.6569821930646678e-05,
+      "loss": 1.8284,
+      "step": 3000
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 2.266479225242112e-05,
+      "loss": 1.7601,
+      "step": 3500
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 1.8759762574195563e-05,
+      "loss": 1.7051,
+      "step": 4000
+    },
+    {
+      "epoch": 2.11,
+      "learning_rate": 1.4854732895970011e-05,
+      "loss": 1.595,
+      "step": 4500
+    },
+    {
+      "epoch": 2.34,
+      "learning_rate": 1.0949703217744455e-05,
+      "loss": 1.495,
+      "step": 5000
+    },
+    {
+      "epoch": 2.58,
+      "learning_rate": 7.0446735395189e-06,
+      "loss": 1.4778,
+      "step": 5500
+    },
+    {
+      "epoch": 2.81,
+      "learning_rate": 3.1396438612933463e-06,
+      "loss": 1.4717,
+      "step": 6000
+    },
+    {
+      "epoch": 3.0,
+      "step": 6402,
+      "total_flos": 438186742382592.0,
+      "train_runtime": 3295.7162,
+      "train_samples_per_second": 1.943
+    }
+  ],
+  "max_steps": 6402,
+  "num_train_epochs": 3,
+  "total_flos": 438186742382592.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46814eb34a4a3a0ca39173093be0eebf244a2a3f6d8ce8fda98545b65bec4068
+size 2170