add/repub model

all_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 10.0,
+    "eval_accuracy": 0.42910256618275966,
+    "eval_loss": 3.251399040222168,
+    "eval_runtime": 155.7882,
+    "eval_samples": 20382,
+    "eval_samples_per_second": 130.832,
+    "eval_steps_per_second": 16.356,
+    "perplexity": 25.82644689174606,
+    "train_loss": 3.311987802313766,
+    "train_runtime": 196254.5716,
+    "train_samples": 1001102,
+    "train_samples_per_second": 51.01,
+    "train_steps_per_second": 2.125
+}

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,
+  "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,
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.1,
+  "scale_attn_by_inverse_layer_idx": false,
+  "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
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.19.0.dev0",
+  "use_cache": true,
+  "vocab_size": 50257
+}

eval_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 10.0,
+    "eval_accuracy": 0.42910256618275966,
+    "eval_loss": 3.251399040222168,
+    "eval_runtime": 155.7882,
+    "eval_samples": 20382,
+    "eval_samples_per_second": 130.832,
+    "eval_steps_per_second": 16.356,
+    "perplexity": 25.82644689174606
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:efd585bfbc028086241f9137e801f8c3c5ded4c7e203cfd9c294cd63beae3498
+size 510401019

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", "tokenizer_class": "GPT2Tokenizer"}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 10.0,
+    "train_loss": 3.311987802313766,
+    "train_runtime": 196254.5716,
+    "train_samples": 1001102,
+    "train_samples_per_second": 51.01,
+    "train_steps_per_second": 2.125
+}

trainer_state.json

@@ -0,0 +1,181 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 10.0,
+  "global_step": 417130,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "learning_rate": 4.999988013329178e-05,
+      "loss": 5.0345,
+      "step": 1
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 4.5e-05,
+      "loss": 3.5452,
+      "step": 41713
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.4118760802529946,
+      "eval_loss": 3.3738181591033936,
+      "eval_runtime": 157.5504,
+      "eval_samples_per_second": 129.368,
+      "eval_steps_per_second": 16.173,
+      "step": 41713
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 4e-05,
+      "loss": 3.4132,
+      "step": 83426
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.4179529258872079,
+      "eval_loss": 3.326674461364746,
+      "eval_runtime": 156.5806,
+      "eval_samples_per_second": 130.169,
+      "eval_steps_per_second": 16.273,
+      "step": 83426
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 3.5e-05,
+      "loss": 3.3573,
+      "step": 125139
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.4213834655713664,
+      "eval_loss": 3.3009300231933594,
+      "eval_runtime": 156.2147,
+      "eval_samples_per_second": 130.474,
+      "eval_steps_per_second": 16.311,
+      "step": 125139
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 3e-05,
+      "loss": 3.3196,
+      "step": 166852
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.42338731797471446,
+      "eval_loss": 3.2852749824523926,
+      "eval_runtime": 157.4446,
+      "eval_samples_per_second": 129.455,
+      "eval_steps_per_second": 16.183,
+      "step": 166852
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 2.5e-05,
+      "loss": 3.2912,
+      "step": 208565
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.42540662325952266,
+      "eval_loss": 3.2730937004089355,
+      "eval_runtime": 155.9547,
+      "eval_samples_per_second": 130.692,
+      "eval_steps_per_second": 16.338,
+      "step": 208565
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 2e-05,
+      "loss": 3.2688,
+      "step": 250278
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.42657331580976576,
+      "eval_loss": 3.265730857849121,
+      "eval_runtime": 157.36,
+      "eval_samples_per_second": 129.525,
+      "eval_steps_per_second": 16.192,
+      "step": 250278
+    },
+    {
+      "epoch": 7.0,
+      "learning_rate": 1.5e-05,
+      "loss": 3.2506,
+      "step": 291991
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.4276302929016416,
+      "eval_loss": 3.25875186920166,
+      "eval_runtime": 157.1763,
+      "eval_samples_per_second": 129.676,
+      "eval_steps_per_second": 16.211,
+      "step": 291991
+    },
+    {
+      "epoch": 8.0,
+      "learning_rate": 1e-05,
+      "loss": 3.2358,
+      "step": 333704
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.4284013916865043,
+      "eval_loss": 3.2545275688171387,
+      "eval_runtime": 155.6431,
+      "eval_samples_per_second": 130.953,
+      "eval_steps_per_second": 16.371,
+      "step": 333704
+    },
+    {
+      "epoch": 9.0,
+      "learning_rate": 5e-06,
+      "loss": 3.2237,
+      "step": 375417
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.4288819762999157,
+      "eval_loss": 3.2520158290863037,
+      "eval_runtime": 156.3518,
+      "eval_samples_per_second": 130.36,
+      "eval_steps_per_second": 16.297,
+      "step": 375417
+    },
+    {
+      "epoch": 10.0,
+      "learning_rate": 0.0,
+      "loss": 3.2144,
+      "step": 417130
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.42910256618275966,
+      "eval_loss": 3.251399040222168,
+      "eval_runtime": 154.5215,
+      "eval_samples_per_second": 131.904,
+      "eval_steps_per_second": 16.49,
+      "step": 417130
+    },
+    {
+      "epoch": 10.0,
+      "step": 417130,
+      "total_flos": 6.5394993954816e+17,
+      "train_loss": 3.311987802313766,
+      "train_runtime": 196254.5716,
+      "train_samples_per_second": 51.01,
+      "train_steps_per_second": 2.125
+    }
+  ],
+  "max_steps": 417130,
+  "num_train_epochs": 10,
+  "total_flos": 6.5394993954816e+17,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7ab9b8fafe400ca6338bee04bac62cf40e4b9eaa08d4fd3ea678157325342fa
+size 3119