Upload 13 files

config.json

@@ -0,0 +1,67 @@
+{
+  "_name_or_path": "xhyi/PT_GPTNEO350_ATG",
+  "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,
+  "embed_dropout": 0,
+  "eos_token_id": 50256,
+  "gradient_checkpointing": false,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": null,
+  "layer_norm_epsilon": 1e-05,
+  "max_position_embeddings": 2048,
+  "model_friendly_id": "PT_GPTNEO350_ATG",
+  "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,
+  "torch_dtype": "float32",
+  "transformers_version": "4.26.1",
+  "use_cache": true,
+  "vocab_size": 50257,
+  "window_size": 256
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.26.1"
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9b5d5244828db453e79362cd07d85407c1a71005c6f9ae761d5f180ac044994
+size 2846582951

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:741853918f96b7e59e30450b2431a75591689e83e95a5ff5f531d7ee45040642
+size 1523982267

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b28f20ef47398713e45ab1f85861dd70d99d92ea820a2650aeed1676c5f7abb
+size 14657

scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f58dda2c6320bb19195c760f00bb5bca022706e89e21c8030cbe2bbdac9f7ba6
+size 559

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e348d96ff49850a215be7eaf648eb6189f9c3a84f424f840f20f2d888cc3f4f
+size 623

special_tokens_map.json

@@ -0,0 +1,27 @@
+{
+  "additional_special_tokens": [
+    "<|endoftext|>"
+  ],
+  "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": "<|endoftext|>",
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,34 @@
+{
+  "add_prefix_space": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "errors": "replace",
+  "model_max_length": 1000000000000000019884624838656,
+  "name_or_path": "xhyi/PT_GPTNEO350_ATG",
+  "pad_token": "<|endoftext|>",
+  "special_tokens_map_file": "/root/.cache/huggingface/hub/models--xhyi--PT_GPTNEO350_ATG/snapshots/56ab08aaa6802d0f830d42c352d5d536be72811d/special_tokens_map.json",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "verbose": false
+}

trainer_state.json

@@ -0,0 +1,124 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.792332268370607,
+  "global_step": 9000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.27,
+      "learning_rate": 4.734291799787008e-05,
+      "loss": 2.0534,
+      "step": 500
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 4.468051118210863e-05,
+      "loss": 1.9997,
+      "step": 1000
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 4.20234291799787e-05,
+      "loss": 1.9542,
+      "step": 1500
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 3.93716719914803e-05,
+      "loss": 1.8679,
+      "step": 2000
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 3.670926517571886e-05,
+      "loss": 1.5918,
+      "step": 2500
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 3.4046858359957404e-05,
+      "loss": 1.6202,
+      "step": 3000
+    },
+    {
+      "epoch": 1.86,
+      "learning_rate": 3.138445154419595e-05,
+      "loss": 1.594,
+      "step": 3500
+    },
+    {
+      "epoch": 2.13,
+      "learning_rate": 2.8722044728434505e-05,
+      "loss": 1.4514,
+      "step": 4000
+    },
+    {
+      "epoch": 2.4,
+      "learning_rate": 2.6059637912673056e-05,
+      "loss": 1.3178,
+      "step": 4500
+    },
+    {
+      "epoch": 2.66,
+      "learning_rate": 2.339723109691161e-05,
+      "loss": 1.3151,
+      "step": 5000
+    },
+    {
+      "epoch": 2.93,
+      "learning_rate": 2.073482428115016e-05,
+      "loss": 1.318,
+      "step": 5500
+    },
+    {
+      "epoch": 3.19,
+      "learning_rate": 1.8072417465388714e-05,
+      "loss": 1.1319,
+      "step": 6000
+    },
+    {
+      "epoch": 3.46,
+      "learning_rate": 1.5410010649627264e-05,
+      "loss": 1.0901,
+      "step": 6500
+    },
+    {
+      "epoch": 3.73,
+      "learning_rate": 1.2747603833865815e-05,
+      "loss": 1.084,
+      "step": 7000
+    },
+    {
+      "epoch": 3.99,
+      "learning_rate": 1.0085197018104367e-05,
+      "loss": 1.0844,
+      "step": 7500
+    },
+    {
+      "epoch": 4.26,
+      "learning_rate": 7.422790202342918e-06,
+      "loss": 0.9108,
+      "step": 8000
+    },
+    {
+      "epoch": 4.53,
+      "learning_rate": 4.76038338658147e-06,
+      "loss": 0.9162,
+      "step": 8500
+    },
+    {
+      "epoch": 4.79,
+      "learning_rate": 2.0979765708200215e-06,
+      "loss": 0.9125,
+      "step": 9000
+    }
+  ],
+  "max_steps": 9390,
+  "num_train_epochs": 5,
+  "total_flos": 2.61046324887552e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca6a8e98ccb03799974833f144d28c8808865b5d7aae30f3cd4aacf0c2b6a22a
+size 3503