Upload 12 files

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 3.0,
+    "eval_loss": 0.9489470720291138,
+    "eval_runtime": 279.8429,
+    "eval_samples": 1267,
+    "eval_samples_per_second": 4.528,
+    "eval_steps_per_second": 2.266,
+    "perplexity": 2.582988526120989,
+    "train_loss": 0.9826037574650801,
+    "train_runtime": 24274.8201,
+    "train_samples": 11364,
+    "train_samples_per_second": 1.404,
+    "train_steps_per_second": 0.702
+}

config.json

@@ -0,0 +1,37 @@
+{
+  "_name_or_path": "gpt2-large",
+  "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": 1280,
+  "n_head": 20,
+  "n_inner": null,
+  "n_layer": 36,
+  "n_positions": 1024,
+  "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": "4.8.0.dev0",
+  "use_cache": true,
+  "vocab_size": 50257
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 3.0,
+    "eval_loss": 0.9489470720291138,
+    "eval_runtime": 279.8429,
+    "eval_samples": 1267,
+    "eval_samples_per_second": 4.528,
+    "eval_steps_per_second": 2.266,
+    "perplexity": 2.582988526120989
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f1ebf861e809d4890443edb7507e737b7b74c4367755e9366a07242210c4b97
+size 3134053001

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-large", "tokenizer_class": "GPT2Tokenizer"}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "train_loss": 0.9826037574650801,
+    "train_runtime": 24274.8201,
+    "train_samples": 11364,
+    "train_samples_per_second": 1.404,
+    "train_steps_per_second": 0.702
+}

trainer_state.json

@@ -0,0 +1,229 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "global_step": 17046,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.09,
+      "learning_rate": 4.8533380265164854e-05,
+      "loss": 1.6132,
+      "step": 500
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 4.70667605303297e-05,
+      "loss": 1.2696,
+      "step": 1000
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 4.560014079549454e-05,
+      "loss": 1.1996,
+      "step": 1500
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 4.4133521060659395e-05,
+      "loss": 1.1562,
+      "step": 2000
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 4.2666901325824246e-05,
+      "loss": 1.1215,
+      "step": 2500
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 4.120028159098909e-05,
+      "loss": 1.1017,
+      "step": 3000
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 3.9733661856153936e-05,
+      "loss": 1.0863,
+      "step": 3500
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 3.826704212131879e-05,
+      "loss": 1.0715,
+      "step": 4000
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 3.680042238648363e-05,
+      "loss": 1.0573,
+      "step": 4500
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 3.533380265164848e-05,
+      "loss": 1.0442,
+      "step": 5000
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 3.386718291681333e-05,
+      "loss": 1.038,
+      "step": 5500
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 3.240056318197818e-05,
+      "loss": 0.9828,
+      "step": 6000
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 3.0933943447143024e-05,
+      "loss": 0.9562,
+      "step": 6500
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 2.9467323712307876e-05,
+      "loss": 0.9515,
+      "step": 7000
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 2.800070397747272e-05,
+      "loss": 0.9498,
+      "step": 7500
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 2.653408424263757e-05,
+      "loss": 0.9454,
+      "step": 8000
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 2.506746450780242e-05,
+      "loss": 0.9432,
+      "step": 8500
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 2.3600844772967265e-05,
+      "loss": 0.941,
+      "step": 9000
+    },
+    {
+      "epoch": 1.67,
+      "learning_rate": 2.2134225038132113e-05,
+      "loss": 0.935,
+      "step": 9500
+    },
+    {
+      "epoch": 1.76,
+      "learning_rate": 2.0667605303296964e-05,
+      "loss": 0.931,
+      "step": 10000
+    },
+    {
+      "epoch": 1.85,
+      "learning_rate": 1.920098556846181e-05,
+      "loss": 0.9285,
+      "step": 10500
+    },
+    {
+      "epoch": 1.94,
+      "learning_rate": 1.773436583362666e-05,
+      "loss": 0.9286,
+      "step": 11000
+    },
+    {
+      "epoch": 2.02,
+      "learning_rate": 1.6267746098791505e-05,
+      "loss": 0.905,
+      "step": 11500
+    },
+    {
+      "epoch": 2.11,
+      "learning_rate": 1.4801126363956355e-05,
+      "loss": 0.8564,
+      "step": 12000
+    },
+    {
+      "epoch": 2.2,
+      "learning_rate": 1.3334506629121201e-05,
+      "loss": 0.8565,
+      "step": 12500
+    },
+    {
+      "epoch": 2.29,
+      "learning_rate": 1.186788689428605e-05,
+      "loss": 0.8558,
+      "step": 13000
+    },
+    {
+      "epoch": 2.38,
+      "learning_rate": 1.0401267159450897e-05,
+      "loss": 0.8552,
+      "step": 13500
+    },
+    {
+      "epoch": 2.46,
+      "learning_rate": 8.934647424615746e-06,
+      "loss": 0.8532,
+      "step": 14000
+    },
+    {
+      "epoch": 2.55,
+      "learning_rate": 7.468027689780594e-06,
+      "loss": 0.8504,
+      "step": 14500
+    },
+    {
+      "epoch": 2.64,
+      "learning_rate": 6.001407954945442e-06,
+      "loss": 0.8485,
+      "step": 15000
+    },
+    {
+      "epoch": 2.73,
+      "learning_rate": 4.53478822011029e-06,
+      "loss": 0.8468,
+      "step": 15500
+    },
+    {
+      "epoch": 2.82,
+      "learning_rate": 3.068168485275138e-06,
+      "loss": 0.8472,
+      "step": 16000
+    },
+    {
+      "epoch": 2.9,
+      "learning_rate": 1.601548750439986e-06,
+      "loss": 0.8467,
+      "step": 16500
+    },
+    {
+      "epoch": 2.99,
+      "learning_rate": 1.34929015604834e-07,
+      "loss": 0.8469,
+      "step": 17000
+    },
+    {
+      "epoch": 3.0,
+      "step": 17046,
+      "total_flos": 1.6212930654633984e+17,
+      "train_loss": 0.9826037574650801,
+      "train_runtime": 24274.8201,
+      "train_samples_per_second": 1.404,
+      "train_steps_per_second": 0.702
+    }
+  ],
+  "max_steps": 17046,
+  "num_train_epochs": 3,
+  "total_flos": 1.6212930654633984e+17,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85553b4f1e750808c2a3a874e03fa2fb718079d617b36367bad7f76c14e4037b
+size 2607