Upload 16 files

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "[PAD]": 50257
+}

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "train_loss": 0.2880971112828346,
+    "train_runtime": 590.0609,
+    "train_samples": 10068,
+    "train_samples_per_second": 17.063,
+    "train_steps_per_second": 0.532
+}

config.json

@@ -0,0 +1,75 @@
+{
+  "_name_or_path": "EleutherAI/gpt-neo-1.3B",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPTNeoForCausalLM"
+  ],
+  "attention_dropout": 0,
+  "attention_layers": [
+    "global",
+    "local",
+    "global",
+    "local",
+    "global",
+    "local",
+    "global",
+    "local",
+    "global",
+    "local",
+    "global",
+    "local",
+    "global",
+    "local",
+    "global",
+    "local",
+    "global",
+    "local",
+    "global",
+    "local",
+    "global",
+    "local",
+    "global",
+    "local"
+  ],
+  "attention_types": [
+    [
+      [
+        "global",
+        "local"
+      ],
+      12
+    ]
+  ],
+  "bos_token_id": 50256,
+  "classifier_dropout": 0.1,
+  "embed_dropout": 0,
+  "eos_token_id": 50256,
+  "gradient_checkpointing": false,
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": null,
+  "layer_norm_epsilon": 1e-05,
+  "max_position_embeddings": 2048,
+  "model_type": "gpt_neo",
+  "num_heads": 16,
+  "num_layers": 24,
+  "resid_dropout": 0,
+  "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,
+      "temperature": 0.9
+    }
+  },
+  "tokenizer_class": "GPT2Tokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.0.dev0",
+  "use_cache": true,
+  "vocab_size": 50258,
+  "window_size": 256
+}

generated_predictions_eval_greedy_5.txt

@@ -0,0 +1,12 @@
+I'm not myself today. I'm in a deep conversation with someone. It's like a virtual therapy session. How do you handle stress?
+No, it's a Thai restaurant. Thai food is delicious! What's your favorite Thai dish?
+ok, I'll do that. If you need more help, I'm here to lend a hand
+games on TV are so entertaining. I'm ready to watch the next one with you. What's on your mind today?
+That's cool! I'm heading to Tokyo with my friend for a relaxing break. How about you?
+That's cool! I'm not a fan of hot water. It's drying. What about you?
+Absolutely! I'm here to make our boss happy. What's on your mind today?
+Absolutely! I'm a fan of the alto range. It's a beautiful sound. What's your favorite part of the choir?
+Nice shirt! I got it from a college campus. It's a symbol of positivity and achievement. How about you?
+How about you?
+No, I just wanted to let you know that it's over!
+Oh, I'm into indie and rock. It's my jam.

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.38.0.dev0"
+}

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a69b1d7e0378817957f36af48c7194e34db215dbd023836488cdb37d0a4980b
+size 4993802376

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ce0d271b0dc1dcf7905427ce3143afd8e138c5600b0f77fdfd30cd10525e5f9
+size 268543784

model.safetensors.index.json

@@ -0,0 +1,323 @@
+{
+  "metadata": {
+    "total_size": 5262311424
+  },
+  "weight_map": {
+    "transformer.h.0.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.0.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.0.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.0.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.0.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.0.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.0.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.0.ln_2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.0.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.0.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.0.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.0.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.0.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.1.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.1.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.1.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.1.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.1.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.1.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.1.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.1.ln_2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.1.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.1.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.1.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.1.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.1.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.10.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.10.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.10.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.10.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.10.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.10.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.10.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.10.ln_2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.10.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.10.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.10.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.10.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.10.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.11.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.11.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.11.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.11.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.11.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.11.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.11.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.11.ln_2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.11.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.11.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.11.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.11.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.11.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.12.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.12.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.12.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.12.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.12.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.12.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.12.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.12.ln_2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.12.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.12.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.12.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.12.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.12.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.13.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.13.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.13.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.13.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.13.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.13.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.13.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.13.ln_2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.13.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.13.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.13.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.13.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.13.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.14.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.14.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.14.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.14.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.14.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.14.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.14.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.14.ln_2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.14.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.14.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.14.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.14.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.14.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.15.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.15.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.15.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.15.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.15.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.15.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.15.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.15.ln_2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.15.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.15.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.15.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.15.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.15.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.16.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.16.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.16.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.16.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.16.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.16.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.16.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.16.ln_2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.16.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.16.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.16.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.16.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.16.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.17.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.17.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.17.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.17.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.17.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.17.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.17.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.17.ln_2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.17.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.17.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.17.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.17.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.17.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.18.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.18.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.18.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.18.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.18.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.18.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.18.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.18.ln_2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.18.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.18.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.18.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.18.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.18.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.19.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.19.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.19.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.19.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.19.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.19.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.19.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.19.ln_2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.19.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.19.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.19.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.19.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.19.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.2.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.2.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.2.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.2.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.2.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.2.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.2.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.2.ln_2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.2.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.2.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.2.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.2.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.2.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.20.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.20.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.20.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.20.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.20.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.20.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.20.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.20.ln_2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.20.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.20.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.20.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.20.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.20.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.21.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.21.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.21.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.21.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.21.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.21.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.21.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.21.ln_2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.21.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.21.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.21.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.21.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.21.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.22.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.22.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.22.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.22.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.22.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.22.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.22.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.22.ln_2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.22.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.22.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.22.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.22.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.22.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.23.attn.attention.k_proj.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.23.attn.attention.out_proj.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.23.attn.attention.out_proj.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.23.attn.attention.q_proj.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.23.attn.attention.v_proj.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.23.ln_1.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.23.ln_1.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.23.ln_2.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.23.ln_2.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.23.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.23.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.23.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.23.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.3.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.3.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.3.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.3.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.3.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.3.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.3.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.3.ln_2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.3.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.3.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.3.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.3.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.3.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.4.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.4.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.4.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.4.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.4.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.4.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.4.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.4.ln_2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.4.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.4.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.4.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.4.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.4.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.5.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.5.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.5.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.5.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.5.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.5.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.5.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.5.ln_2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.5.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.5.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.5.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.5.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.5.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.6.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.6.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.6.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.6.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.6.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.6.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.6.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.6.ln_2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.6.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.6.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.6.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.6.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.6.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.7.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.7.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.7.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.7.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.7.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.7.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.7.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.7.ln_2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.7.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.7.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.7.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.7.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.7.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.8.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.8.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.8.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.8.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.8.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.8.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.8.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.8.ln_2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.8.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.8.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.8.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.8.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.8.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.9.attn.attention.k_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.9.attn.attention.out_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.9.attn.attention.out_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.9.attn.attention.q_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.9.attn.attention.v_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.9.ln_1.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.9.ln_1.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.9.ln_2.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.9.ln_2.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.9.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.9.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.9.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.9.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "transformer.ln_f.bias": "model-00002-of-00002.safetensors",
+    "transformer.ln_f.weight": "model-00002-of-00002.safetensors",
+    "transformer.wpe.weight": "model-00001-of-00002.safetensors",
+    "transformer.wte.weight": "model-00001-of-00002.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,30 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "50256": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50257": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "model_max_length": 2048,
+  "pad_token": "[PAD]",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "train_loss": 0.2880971112828346,
+    "train_runtime": 590.0609,
+    "train_samples": 10068,
+    "train_samples_per_second": 17.063,
+    "train_steps_per_second": 0.532
+}

trainer_state.json

@@ -0,0 +1,79 @@
+{
+  "best_metric": 5.144372463226318,
+  "best_model_checkpoint": "./output_dir/checkpoint-314",
+  "epoch": 0.9976171564733916,
+  "eval_steps": 50.0,
+  "global_step": 314,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.16,
+      "learning_rate": 8.471337579617836e-05,
+      "loss": 0.881,
+      "step": 50
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 6.878980891719745e-05,
+      "loss": 0.244,
+      "step": 100
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 5.286624203821656e-05,
+      "loss": 0.1884,
+      "step": 150
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 3.694267515923567e-05,
+      "loss": 0.1744,
+      "step": 200
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 2.1019108280254778e-05,
+      "loss": 0.1615,
+      "step": 250
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 5.095541401273886e-06,
+      "loss": 0.1235,
+      "step": 300
+    },
+    {
+      "epoch": 1.0,
+      "eval_bleu-1": 82.7612,
+      "eval_bleu-2": 79.8854,
+      "eval_bleu-3": 79.4646,
+      "eval_bleu-4": 79.2979,
+      "eval_gen_len": 122.3333,
+      "eval_loss": 5.144372463226318,
+      "eval_runtime": 4.327,
+      "eval_samples_per_second": 2.773,
+      "eval_steps_per_second": 0.693,
+      "step": 314
+    },
+    {
+      "epoch": 1.0,
+      "step": 314,
+      "total_flos": 1.8650968363106304e+16,
+      "train_loss": 0.2880971112828346,
+      "train_runtime": 590.0609,
+      "train_samples_per_second": 17.063,
+      "train_steps_per_second": 0.532
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 314,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "total_flos": 1.8650968363106304e+16,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9dc6831fb59222079663499dc0092e04dda45b98c045e78eaf6e4030af02c78
+size 5048