Training in progress, epoch 1, checkpoint

checkpoint-131/added_tokens.json

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

checkpoint-131/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-131/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-131/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c40c7f8216668320e8b2129913f2a75cd29261740e8304ed5ef39e794d97a1f
+size 12461385454

checkpoint-131/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b791f07606897d5733883699bbc100cb29d0c2db4a76de5df9b3e4f7090dd7b
+size 6230637102

checkpoint-131/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8bfe6a48cc13927f26662925c9442577e8289049bfef5719ae4e8174e0c28519
+size 14244

checkpoint-131/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db47f01886c74ba21a851df2df16fddc4065dfa635b61f55deeee88b130eaeea
+size 1064

checkpoint-131/special_tokens_map.json

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

checkpoint-131/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-131/trainer_state.json

@@ -0,0 +1,92 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 66,
+  "global_step": 131,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.11,
+      "learning_rate": 3e-05,
+      "loss": 3.7331,
+      "step": 14
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 3e-05,
+      "loss": 2.345,
+      "step": 28
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 3e-05,
+      "loss": 2.1491,
+      "step": 42
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 3e-05,
+      "loss": 2.0739,
+      "step": 56
+    },
+    {
+      "epoch": 0.5,
+      "eval_accuracy": 0.6206453178068898,
+      "eval_loss": 1.8404711484909058,
+      "eval_runtime": 11.9883,
+      "eval_samples_per_second": 25.024,
+      "eval_steps_per_second": 1.585,
+      "step": 66
+    },
+    {
+      "epoch": 0.5,
+      "eval_exact_match": 7.666666666666667,
+      "eval_f1": 10.221428571428572,
+      "eval_qa_bleu": 1.4042262195131967,
+      "eval_qa_exact_match": 0.07333333333333333,
+      "eval_recite_bleu": 8.5956480576491,
+      "eval_recite_exact_match": 0.0,
+      "step": 66
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 3e-05,
+      "loss": 1.9722,
+      "step": 70
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 3e-05,
+      "loss": 2.014,
+      "step": 84
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 3e-05,
+      "loss": 1.9812,
+      "step": 98
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 3e-05,
+      "loss": 1.9213,
+      "step": 112
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 3e-05,
+      "loss": 1.8806,
+      "step": 126
+    }
+  ],
+  "logging_steps": 14,
+  "max_steps": 1310,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "total_flos": 5898044000563200.0,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-131/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e2f5bbca2ac6551a76ff4a6e10000fae190ff8cb3817e74f2e51a104a179e48
+size 4728