Upload experiments/2022-11-05-273b9dce0e50fad6fa8b725ac92e9f951cbba613877a10428c0dbf3c200b8d13 with huggingface_hub

experiments/2022-11-05-273b9dce0e50fad6fa8b725ac92e9f951cbba613877a10428c0dbf3c200b8d13/configs.json

@@ -0,0 +1,25 @@
+{
+    "output_dir": "./results",
+    "evaluation_strategy": "no",
+    "do_eval": false,
+    "eval_steps": 0,
+    "log_level": "error",
+    "logging_first_step": true,
+    "logging_steps": 5,
+    "logging_dir": "./logs",
+    "save_steps": 200,
+    "save_total_limit": 2,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 8,
+    "optim": "adamw_torch",
+    "gradient_accumulation_steps": 8,
+    "dataloader_drop_last": true,
+    "warmup_steps": 400,
+    "weight_decay": 0.01,
+    "learning_rate": 5e-05,
+    "fp16": true,
+    "total_gpus": 1,
+    "v_cpus": 6,
+    "total_memory_in_gb": 24048.78515625,
+    "dataset_limit": 0
+}

experiments/2022-11-05-273b9dce0e50fad6fa8b725ac92e9f951cbba613877a10428c0dbf3c200b8d13/final_checkpoint/config.json

@@ -0,0 +1,54 @@
+{
+  "_name_or_path": "EleutherAI/gpt-neo-125M",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPTNeoForCausalLM"
+  ],
+  "attention_dropout": 0,
+  "attention_layers": [
+    "global",
+    "local",
+    "global",
+    "local",
+    "global",
+    "local",
+    "global",
+    "local",
+    "global",
+    "local",
+    "global",
+    "local"
+  ],
+  "attention_types": [
+    [
+      [
+        "global",
+        "local"
+      ],
+      6
+    ]
+  ],
+  "bos_token_id": 50256,
+  "embed_dropout": 0,
+  "eos_token_id": 50256,
+  "gradient_checkpointing": false,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": null,
+  "layer_norm_epsilon": 1e-05,
+  "max_position_embeddings": 2048,
+  "model_type": "gpt_neo",
+  "num_heads": 12,
+  "num_layers": 12,
+  "resid_dropout": 0,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.23.1",
+  "use_cache": true,
+  "vocab_size": 50259,
+  "window_size": 256
+}

experiments/2022-11-05-273b9dce0e50fad6fa8b725ac92e9f951cbba613877a10428c0dbf3c200b8d13/final_checkpoint/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a6bbc41b5b38da4d26742decfbc2205af3eddfb559e640f451d740408a390bd
+size 551191249

experiments/2022-11-05-273b9dce0e50fad6fa8b725ac92e9f951cbba613877a10428c0dbf3c200b8d13/logs/1667604497.985131/events.out.tfevents.1667604497.recd68n2rbwktkbnt.2943.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d874424d6d09c79d93229a51822b0de75a206f2439680aef9150f5994ccee69b
+size 5413

experiments/2022-11-05-273b9dce0e50fad6fa8b725ac92e9f951cbba613877a10428c0dbf3c200b8d13/logs/events.out.tfevents.1667604497.recd68n2rbwktkbnt.2943.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f20660ebda82f793e8c2b50856ade5e5dba0dfbf6a2f29606ee27603f1f5ae32
+size 291940