swiss training

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 1.0,
+    "init_mem_cpu_alloc_delta": 335895,
+    "init_mem_cpu_peaked_delta": 18306,
+    "init_mem_gpu_alloc_delta": 511148032,
+    "init_mem_gpu_peaked_delta": 0,
+    "train_mem_cpu_alloc_delta": 925294,
+    "train_mem_cpu_peaked_delta": 1247793,
+    "train_mem_gpu_alloc_delta": 1501967872,
+    "train_mem_gpu_peaked_delta": 3373839360,
+    "train_runtime": 2923.7518,
+    "train_samples": 10863,
+    "train_samples_per_second": 3.715
+}

config.json

@@ -0,0 +1,36 @@
+{
+  "_name_or_path": "gpt2",
+  "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": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 1024,
+  "resid_pdrop": 0.1,
+  "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": "4.4.0.dev0",
+  "use_cache": true,
+  "vocab_size": 50257
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e16dc707aebea8d47279d1a5190c45c1b95676b82937a1c038246dac809c64e1
+size 510406566

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"}

train_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 1.0,
+    "init_mem_cpu_alloc_delta": 335895,
+    "init_mem_cpu_peaked_delta": 18306,
+    "init_mem_gpu_alloc_delta": 511148032,
+    "init_mem_gpu_peaked_delta": 0,
+    "train_mem_cpu_alloc_delta": 925294,
+    "train_mem_cpu_peaked_delta": 1247793,
+    "train_mem_gpu_alloc_delta": 1501967872,
+    "train_mem_gpu_peaked_delta": 3373839360,
+    "train_runtime": 2923.7518,
+    "train_samples": 10863,
+    "train_samples_per_second": 3.715
+}

trainer_state.json

@@ -0,0 +1,149 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "global_step": 10863,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.05,
+      "learning_rate": 4.7698609960416095e-05,
+      "loss": 0.4597,
+      "step": 500
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 4.539721992083218e-05,
+      "loss": 0.3231,
+      "step": 1000
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 4.309582988124828e-05,
+      "loss": 0.3073,
+      "step": 1500
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 4.079443984166437e-05,
+      "loss": 0.2928,
+      "step": 2000
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 3.849304980208046e-05,
+      "loss": 0.2808,
+      "step": 2500
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 3.619165976249655e-05,
+      "loss": 0.275,
+      "step": 3000
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 3.389026972291264e-05,
+      "loss": 0.2675,
+      "step": 3500
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 3.1588879683328734e-05,
+      "loss": 0.2614,
+      "step": 4000
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 2.9287489643744827e-05,
+      "loss": 0.2584,
+      "step": 4500
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 2.6986099604160913e-05,
+      "loss": 0.2555,
+      "step": 5000
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 2.4684709564577006e-05,
+      "loss": 0.2532,
+      "step": 5500
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 2.2383319524993096e-05,
+      "loss": 0.2496,
+      "step": 6000
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 2.0081929485409186e-05,
+      "loss": 0.2483,
+      "step": 6500
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 1.778053944582528e-05,
+      "loss": 0.2457,
+      "step": 7000
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 1.547914940624137e-05,
+      "loss": 0.2454,
+      "step": 7500
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 1.317775936665746e-05,
+      "loss": 0.2441,
+      "step": 8000
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 1.0876369327073553e-05,
+      "loss": 0.2426,
+      "step": 8500
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 8.574979287489644e-06,
+      "loss": 0.2427,
+      "step": 9000
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 6.273589247905736e-06,
+      "loss": 0.2416,
+      "step": 9500
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 3.972199208321826e-06,
+      "loss": 0.2398,
+      "step": 10000
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 1.6708091687379177e-06,
+      "loss": 0.2409,
+      "step": 10500
+    },
+    {
+      "epoch": 1.0,
+      "step": 10863,
+      "total_flos": 8305395513163776.0,
+      "train_runtime": 2923.7518,
+      "train_samples_per_second": 3.715
+    }
+  ],
+  "max_steps": 10863,
+  "num_train_epochs": 1,
+  "total_flos": 8305395513163776.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:066c3cf203b9657ca83bda8c6f40c2d45272c2c90db36cb1dd6ffcf54f7bf1a5
+size 2287