Training in progress, epoch 1, checkpoint

checkpoint-56/added_tokens.json

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

checkpoint-56/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-56/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-56/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:624ad7cb5a55ed3d908aa94ad8c04bc4238d7ed78d04e9a8b432665608bb0d17
+size 12461385454

checkpoint-56/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88675366c236726998242da0776f76b194e94f1a510a3ebc1f65e4176908faa4
+size 6230637102

checkpoint-56/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b9387d4e40eb73db345e8351ca744eb6af5443bec3381b382000fca3f9015cc
+size 14244

checkpoint-56/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8d23a8d533e4044d404c3867715711e71802a5adf225f4c1473f95c1c71209e
+size 1064

checkpoint-56/special_tokens_map.json

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

checkpoint-56/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-56/trainer_state.json

@@ -0,0 +1,105 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 28,
+  "global_step": 56,
+  "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": 3.5167,
+      "step": 6
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 3e-05,
+      "loss": 2.7034,
+      "step": 12
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 3e-05,
+      "loss": 2.5409,
+      "step": 18
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 3e-05,
+      "loss": 2.4931,
+      "step": 24
+    },
+    {
+      "epoch": 0.5,
+      "eval_accuracy": 0.5748751060189339,
+      "eval_loss": 2.390355348587036,
+      "eval_runtime": 25.7729,
+      "eval_samples_per_second": 34.261,
+      "eval_steps_per_second": 2.173,
+      "step": 28
+    },
+    {
+      "epoch": 0.5,
+      "eval_bleu": 2.6290615444017718,
+      "eval_exact_match": 0.0,
+      "eval_prefix_exact_match": 0.0,
+      "step": 28
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 3e-05,
+      "loss": 2.4944,
+      "step": 30
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 3e-05,
+      "loss": 2.4832,
+      "step": 36
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 3e-05,
+      "loss": 2.4336,
+      "step": 42
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 3e-05,
+      "loss": 2.5101,
+      "step": 48
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 3e-05,
+      "loss": 2.4699,
+      "step": 54
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.6049526162776446,
+      "eval_loss": 2.101423740386963,
+      "eval_runtime": 23.9781,
+      "eval_samples_per_second": 36.825,
+      "eval_steps_per_second": 2.335,
+      "step": 56
+    },
+    {
+      "epoch": 1.0,
+      "eval_bleu": 2.731416805620766,
+      "eval_exact_match": 0.0,
+      "eval_prefix_exact_match": 0.0,
+      "step": 56
+    }
+  ],
+  "logging_steps": 6,
+  "max_steps": 560,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "total_flos": 1360515013171200.0,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-56/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b959b77797bfa32386725e4d78839c39c28940487e69e41fb564f8bb31a78b3
+size 4664