Training in progress, epoch 1, checkpoint

checkpoint-248/added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<|endoftext|>": 50256
+}

checkpoint-248/config.json

@@ -0,0 +1,42 @@
+{
+  "_name_or_path": "gpt2-xl",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "do_sample": true,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "max_length": 50,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 1600,
+  "n_head": 25,
+  "n_inner": null,
+  "n_layer": 48,
+  "n_positions": 1024,
+  "output_past": true,
+  "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": "4.34.0",
+  "use_cache": true,
+  "vocab_size": 50257
+}

checkpoint-248/generation_config.json

@@ -0,0 +1,8 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "do_sample": true,
+  "eos_token_id": 50256,
+  "max_length": 50,
+  "transformers_version": "4.34.0"
+}

checkpoint-248/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb30829ec7f42022234fa915ecc0e5b8c1c81822e13c1f0a90d64f3bad9a391e
+size 12461385454

checkpoint-248/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8711f4845ce41afecd40c5cc98d5e5baa392a50a53fc9257631028c454cddb73
+size 6230637102

checkpoint-248/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:728e0c8ec9f37b24b9898d10a8492b0d3679fcc9d3bccae700724542ecb966a8
+size 14244

checkpoint-248/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9d3b0a581050be5f1b2c471b322f7b4c375c11de2cbb1adc56a4ad0c45df3ac
+size 1064

checkpoint-248/special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "pad_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
+}

checkpoint-248/tokenizer_config.json

@@ -0,0 +1,20 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "50256": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1024,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

checkpoint-248/trainer_state.json

@@ -0,0 +1,62 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 248,
+  "global_step": 248,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.2,
+      "learning_rate": 3e-05,
+      "loss": 2.8428,
+      "step": 50
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 3e-05,
+      "loss": 2.1589,
+      "step": 100
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 3e-05,
+      "loss": 2.0527,
+      "step": 150
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 3e-05,
+      "loss": 1.9823,
+      "step": 200
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.6398457059679767,
+      "eval_loss": 1.6149228811264038,
+      "eval_runtime": 17.4504,
+      "eval_samples_per_second": 28.653,
+      "eval_steps_per_second": 1.834,
+      "step": 248
+    },
+    {
+      "epoch": 1.0,
+      "eval_exact_match": 9.0,
+      "eval_f1": 13.45666666666666,
+      "eval_qa_bleu": 7.063432441196736,
+      "eval_qa_exact_match": 0.09,
+      "eval_recite_bleu": 15.344658855358656,
+      "eval_recite_exact_match": 0.0,
+      "step": 248
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 4960,
+  "num_train_epochs": 20,
+  "save_steps": 500,
+  "total_flos": 1.15393402827264e+16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-248/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:acdd81e53b27f902dc4c1896d0c5253609dec7800ac5e5d60f5a323620c45c4a
+size 4728