Training in progress, epoch 2, checkpoint

checkpoint-2904/added_tokens.json

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

checkpoint-2904/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-2904/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-2904/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa14207fab307f9db30e67a66bd6fdf5dee589250ef65103268e801a52bf4b59
+size 12461385454

checkpoint-2904/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8fd651a566fd4018fd16901e9615e25acb716c38aa5bd518401b3e1e8f6bb25
+size 6230637102

checkpoint-2904/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3a966d6c65dbdddee8ae068ebb60738af787b8f64754b21f0f87e0e7bf9a2f6
+size 14244

checkpoint-2904/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77f4e9f17cfa712bbb2bbc11d136c64dc112ac7f877babf2ef86b41c8243639c
+size 1064

checkpoint-2904/special_tokens_map.json

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

checkpoint-2904/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-2904/trainer_state.json

@@ -0,0 +1,111 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 1452,
+  "global_step": 2904,
+  "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": 2.2721,
+      "step": 291
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 3e-05,
+      "loss": 2.0539,
+      "step": 582
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 3e-05,
+      "loss": 2.0079,
+      "step": 873
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 3e-05,
+      "loss": 1.9686,
+      "step": 1164
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.668149394347241,
+      "eval_loss": 1.5662202835083008,
+      "eval_runtime": 137.7572,
+      "eval_samples_per_second": 36.296,
+      "eval_steps_per_second": 2.272,
+      "step": 1452
+    },
+    {
+      "epoch": 1.0,
+      "eval_exact_match": 9.04,
+      "eval_f1": 13.087046780017364,
+      "eval_qa_bleu": 5.297766450359973,
+      "eval_qa_exact_match": 0.085,
+      "eval_recite_bleu": 14.716037077738477,
+      "eval_recite_exact_match": 0.0,
+      "step": 1452
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 3e-05,
+      "loss": 1.9076,
+      "step": 1455
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 3e-05,
+      "loss": 1.5211,
+      "step": 1746
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 3e-05,
+      "loss": 1.5039,
+      "step": 2037
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 3e-05,
+      "loss": 1.4834,
+      "step": 2328
+    },
+    {
+      "epoch": 1.8,
+      "learning_rate": 3e-05,
+      "loss": 1.4604,
+      "step": 2619
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.6914514131897712,
+      "eval_loss": 1.206884741783142,
+      "eval_runtime": 139.7305,
+      "eval_samples_per_second": 35.783,
+      "eval_steps_per_second": 2.24,
+      "step": 2904
+    },
+    {
+      "epoch": 2.0,
+      "eval_exact_match": 11.64,
+      "eval_f1": 16.917593370997537,
+      "eval_qa_bleu": 7.627957176996819,
+      "eval_qa_exact_match": 0.1106,
+      "eval_recite_bleu": 18.356743056908567,
+      "eval_recite_exact_match": 0.0,
+      "step": 2904
+    }
+  ],
+  "logging_steps": 291,
+  "max_steps": 29040,
+  "num_train_epochs": 20,
+  "save_steps": 500,
+  "total_flos": 1.326566236237824e+17,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-2904/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d993d1b3c496d84dac3774165ea3fdf800c76280a435c891943344990df3011
+size 4728