Add pretrained model

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": "4.8.2",
+  "use_cache": true,
+  "vocab_size": 50257
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:edb7b6189b1f9b7cdf17a9bb4ef541da8eb06bf8311c7a788a187deb41e036c0
+size 2838754801

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4cdcd06786d1fe8eac9383e7c75cffe468c5f01d5bf5b959991b1e5a4c89e16
+size 1444581337

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf4eb303eb739fe79e1c3f0df5d480c75d04509ba5792c47b2dc0ace5fda1ba9
+size 14503

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa5a013b3dcb1c6ab5a3bcfa2f700d9971506739c74169e82ecd4f334e914162
+size 623

trainer_state.json

@@ -0,0 +1,256 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 9.465855307640297,
+  "global_step": 14000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.9993238674780257e-05,
+      "loss": 1.9928,
+      "step": 500
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 1.9986477349560515e-05,
+      "loss": 1.5804,
+      "step": 1000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 1.5350453853607178,
+      "eval_runtime": 0.0909,
+      "eval_samples_per_second": 43.998,
+      "eval_steps_per_second": 11.0,
+      "step": 1479
+    },
+    {
+      "epoch": 1.01,
+      "learning_rate": 1.997971602434077e-05,
+      "loss": 1.4417,
+      "step": 1500
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 1.997295469912103e-05,
+      "loss": 1.2966,
+      "step": 2000
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 1.9966193373901284e-05,
+      "loss": 1.2455,
+      "step": 2500
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 1.411128044128418,
+      "eval_runtime": 0.0866,
+      "eval_samples_per_second": 46.21,
+      "eval_steps_per_second": 11.552,
+      "step": 2958
+    },
+    {
+      "epoch": 2.03,
+      "learning_rate": 1.9959432048681543e-05,
+      "loss": 1.1971,
+      "step": 3000
+    },
+    {
+      "epoch": 2.37,
+      "learning_rate": 1.99526707234618e-05,
+      "loss": 1.1112,
+      "step": 3500
+    },
+    {
+      "epoch": 2.7,
+      "learning_rate": 1.9945909398242057e-05,
+      "loss": 1.0734,
+      "step": 4000
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 1.3451578617095947,
+      "eval_runtime": 0.0858,
+      "eval_samples_per_second": 46.634,
+      "eval_steps_per_second": 11.659,
+      "step": 4437
+    },
+    {
+      "epoch": 3.04,
+      "learning_rate": 1.9939148073022316e-05,
+      "loss": 1.0531,
+      "step": 4500
+    },
+    {
+      "epoch": 3.38,
+      "learning_rate": 1.993238674780257e-05,
+      "loss": 0.9843,
+      "step": 5000
+    },
+    {
+      "epoch": 3.72,
+      "learning_rate": 1.992562542258283e-05,
+      "loss": 0.9622,
+      "step": 5500
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 1.2762081623077393,
+      "eval_runtime": 0.0884,
+      "eval_samples_per_second": 45.25,
+      "eval_steps_per_second": 11.312,
+      "step": 5916
+    },
+    {
+      "epoch": 4.06,
+      "learning_rate": 1.9918864097363085e-05,
+      "loss": 0.9453,
+      "step": 6000
+    },
+    {
+      "epoch": 4.39,
+      "learning_rate": 1.9912102772143343e-05,
+      "loss": 0.8873,
+      "step": 6500
+    },
+    {
+      "epoch": 4.73,
+      "learning_rate": 1.99053414469236e-05,
+      "loss": 0.8723,
+      "step": 7000
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 1.2012463808059692,
+      "eval_runtime": 0.0849,
+      "eval_samples_per_second": 47.093,
+      "eval_steps_per_second": 11.773,
+      "step": 7395
+    },
+    {
+      "epoch": 5.07,
+      "learning_rate": 1.9898580121703857e-05,
+      "loss": 0.8676,
+      "step": 7500
+    },
+    {
+      "epoch": 5.41,
+      "learning_rate": 1.9891818796484112e-05,
+      "loss": 0.7985,
+      "step": 8000
+    },
+    {
+      "epoch": 5.75,
+      "learning_rate": 1.9885057471264367e-05,
+      "loss": 0.8085,
+      "step": 8500
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 1.1576131582260132,
+      "eval_runtime": 0.0879,
+      "eval_samples_per_second": 45.526,
+      "eval_steps_per_second": 11.381,
+      "step": 8874
+    },
+    {
+      "epoch": 6.09,
+      "learning_rate": 1.9878296146044626e-05,
+      "loss": 0.7917,
+      "step": 9000
+    },
+    {
+      "epoch": 6.42,
+      "learning_rate": 1.987153482082488e-05,
+      "loss": 0.7452,
+      "step": 9500
+    },
+    {
+      "epoch": 6.76,
+      "learning_rate": 1.986477349560514e-05,
+      "loss": 0.7447,
+      "step": 10000
+    },
+    {
+      "epoch": 7.0,
+      "eval_loss": 1.1027594804763794,
+      "eval_runtime": 0.0838,
+      "eval_samples_per_second": 47.724,
+      "eval_steps_per_second": 11.931,
+      "step": 10353
+    },
+    {
+      "epoch": 7.1,
+      "learning_rate": 1.9858012170385395e-05,
+      "loss": 0.7298,
+      "step": 10500
+    },
+    {
+      "epoch": 7.44,
+      "learning_rate": 1.9851250845165654e-05,
+      "loss": 0.681,
+      "step": 11000
+    },
+    {
+      "epoch": 7.78,
+      "learning_rate": 1.9844489519945912e-05,
+      "loss": 0.7038,
+      "step": 11500
+    },
+    {
+      "epoch": 8.0,
+      "eval_loss": 1.0498589277267456,
+      "eval_runtime": 0.086,
+      "eval_samples_per_second": 46.519,
+      "eval_steps_per_second": 11.63,
+      "step": 11832
+    },
+    {
+      "epoch": 8.11,
+      "learning_rate": 1.9837728194726168e-05,
+      "loss": 0.6726,
+      "step": 12000
+    },
+    {
+      "epoch": 8.45,
+      "learning_rate": 1.9830966869506426e-05,
+      "loss": 0.6405,
+      "step": 12500
+    },
+    {
+      "epoch": 8.79,
+      "learning_rate": 1.982420554428668e-05,
+      "loss": 0.6458,
+      "step": 13000
+    },
+    {
+      "epoch": 9.0,
+      "eval_loss": 0.9868650436401367,
+      "eval_runtime": 0.0904,
+      "eval_samples_per_second": 44.229,
+      "eval_steps_per_second": 11.057,
+      "step": 13311
+    },
+    {
+      "epoch": 9.13,
+      "learning_rate": 1.981744421906694e-05,
+      "loss": 0.6234,
+      "step": 13500
+    },
+    {
+      "epoch": 9.47,
+      "learning_rate": 1.9810682893847195e-05,
+      "loss": 0.5984,
+      "step": 14000
+    }
+  ],
+  "max_steps": 1479000,
+  "num_train_epochs": 1000,
+  "total_flos": 3.051556454321357e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4bdec74920e7088599e6f5219d6c03fb9ea65f18d464f453ed52d2f559536f2a
+size 2671