init

config.json

@@ -0,0 +1,39 @@
+{
+  "_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,
+      "top_k":50,
+      "top_p":0.85,
+      "no_repeat_ngram_size":3
+    }
+  },
+  "transformers_version": "4.4.0.dev0",
+  "use_cache": true,
+  "vocab_size": 50261
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:acebdef50ffbd51aa7eba84a85c10d16f5ffd223212cebff2ffb47994cb5afcc
+size 995635311

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1131c66d971e666343bfea1500d8e2b64fd499f50acb19c9c1e0ed3fac1b87fb
+size 510420239

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ff339a60a0e7de8676c841e72a1a4a72ef9890e55879d85140e63458ebdf0b5
+size 623

trainer_state.json

@@ -0,0 +1,159 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.9748106591865358,
+  "global_step": 2200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.18,
+      "learning_rate": 4.765037593984963e-05,
+      "loss": 12.2573,
+      "step": 200
+    },
+    {
+      "epoch": 0.18,
+      "eval_loss": 2.7165932655334473,
+      "eval_runtime": 138.6905,
+      "eval_samples_per_second": 13.483,
+      "step": 200
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 4.295112781954887e-05,
+      "loss": 2.6565,
+      "step": 400
+    },
+    {
+      "epoch": 0.36,
+      "eval_loss": 2.7028679847717285,
+      "eval_runtime": 135.8765,
+      "eval_samples_per_second": 13.762,
+      "step": 400
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 3.825187969924812e-05,
+      "loss": 2.6054,
+      "step": 600
+    },
+    {
+      "epoch": 0.54,
+      "eval_loss": 2.677929162979126,
+      "eval_runtime": 138.76,
+      "eval_samples_per_second": 13.477,
+      "step": 600
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 3.355263157894737e-05,
+      "loss": 2.6296,
+      "step": 800
+    },
+    {
+      "epoch": 0.72,
+      "eval_loss": 2.667823553085327,
+      "eval_runtime": 138.8745,
+      "eval_samples_per_second": 13.465,
+      "step": 800
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 2.8853383458646617e-05,
+      "loss": 2.6148,
+      "step": 1000
+    },
+    {
+      "epoch": 0.9,
+      "eval_loss": 2.6645262241363525,
+      "eval_runtime": 138.612,
+      "eval_samples_per_second": 13.491,
+      "step": 1000
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 2.4154135338345866e-05,
+      "loss": 2.5843,
+      "step": 1200
+    },
+    {
+      "epoch": 1.08,
+      "eval_loss": 2.6597423553466797,
+      "eval_runtime": 138.5965,
+      "eval_samples_per_second": 13.492,
+      "step": 1200
+    },
+    {
+      "epoch": 1.26,
+      "learning_rate": 1.9454887218045115e-05,
+      "loss": 2.5548,
+      "step": 1400
+    },
+    {
+      "epoch": 1.26,
+      "eval_loss": 2.653554677963257,
+      "eval_runtime": 138.5895,
+      "eval_samples_per_second": 13.493,
+      "step": 1400
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 1.4755639097744361e-05,
+      "loss": 2.5588,
+      "step": 1600
+    },
+    {
+      "epoch": 1.44,
+      "eval_loss": 2.6523187160491943,
+      "eval_runtime": 138.5665,
+      "eval_samples_per_second": 13.495,
+      "step": 1600
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 1.005639097744361e-05,
+      "loss": 2.5814,
+      "step": 1800
+    },
+    {
+      "epoch": 1.62,
+      "eval_loss": 2.64888858795166,
+      "eval_runtime": 138.6375,
+      "eval_samples_per_second": 13.488,
+      "step": 1800
+    },
+    {
+      "epoch": 1.8,
+      "learning_rate": 5.357142857142857e-06,
+      "loss": 2.569,
+      "step": 2000
+    },
+    {
+      "epoch": 1.8,
+      "eval_loss": 2.6475982666015625,
+      "eval_runtime": 138.5945,
+      "eval_samples_per_second": 13.493,
+      "step": 2000
+    },
+    {
+      "epoch": 1.97,
+      "learning_rate": 6.578947368421053e-07,
+      "loss": 2.5401,
+      "step": 2200
+    },
+    {
+      "epoch": 1.97,
+      "eval_loss": 2.6439733505249023,
+      "eval_runtime": 138.082,
+      "eval_samples_per_second": 13.543,
+      "step": 2200
+    }
+  ],
+  "max_steps": 2228,
+  "num_train_epochs": 2,
+  "total_flos": 2.691387690319872e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f28fc4851c0fe326ff8bc868398e502a63697d53ab65c181be81540246f26330
+size 2351