Upload 12 files

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": "4.26.1",
+  "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 sha256:4552969416b69a176eecc0ebb2b1c50cb7910a18e1caa60af57e0650bcdcae9d
+size 1001689455

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22380bedc99d1a67116aa244d435a72391127abfa87c6d803bc509616b42a75f
+size 551189991

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:316a28030dee0e8b77cf59bb21904f3269d5671ab19ea6aeeab385c811010384
+size 14657

scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fbba12a5918bb0aa079648dc23e9d433f5fc0e85f27115a5ebbc3b3a803f3efd
+size 559

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dfe515f64c81dc9ab458a35092d864e86e5c64d64e0ecfac54a60b2e45f95be5
+size 623

tokenizer_config.json

@@ -0,0 +1,34 @@
+{
+  "add_bos_token": false,
+  "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": 2048,
+  "name_or_path": "EleutherAI/gpt-neo-125M",
+  "pad_token": null,
+  "special_tokens_map_file": null,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": 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": 4.7337593184238556e-05,
+      "loss": 2.3421,
+      "step": 500
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 4.468051118210863e-05,
+      "loss": 2.2764,
+      "step": 1000
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 4.201810436634718e-05,
+      "loss": 2.2325,
+      "step": 1500
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 3.935569755058573e-05,
+      "loss": 2.1843,
+      "step": 2000
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 3.669329073482428e-05,
+      "loss": 2.0173,
+      "step": 2500
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 3.403088391906283e-05,
+      "loss": 2.0383,
+      "step": 3000
+    },
+    {
+      "epoch": 1.86,
+      "learning_rate": 3.136847710330139e-05,
+      "loss": 2.0066,
+      "step": 3500
+    },
+    {
+      "epoch": 2.13,
+      "learning_rate": 2.8706070287539938e-05,
+      "loss": 1.9359,
+      "step": 4000
+    },
+    {
+      "epoch": 2.4,
+      "learning_rate": 2.604366347177849e-05,
+      "loss": 1.8781,
+      "step": 4500
+    },
+    {
+      "epoch": 2.66,
+      "learning_rate": 2.3386581469648563e-05,
+      "loss": 1.8675,
+      "step": 5000
+    },
+    {
+      "epoch": 2.93,
+      "learning_rate": 2.0724174653887117e-05,
+      "loss": 1.8704,
+      "step": 5500
+    },
+    {
+      "epoch": 3.19,
+      "learning_rate": 1.8061767838125668e-05,
+      "loss": 1.7724,
+      "step": 6000
+    },
+    {
+      "epoch": 3.46,
+      "learning_rate": 1.5399361022364218e-05,
+      "loss": 1.7745,
+      "step": 6500
+    },
+    {
+      "epoch": 3.73,
+      "learning_rate": 1.2736954206602768e-05,
+      "loss": 1.7645,
+      "step": 7000
+    },
+    {
+      "epoch": 3.99,
+      "learning_rate": 1.0079872204472844e-05,
+      "loss": 1.763,
+      "step": 7500
+    },
+    {
+      "epoch": 4.26,
+      "learning_rate": 7.417465388711395e-06,
+      "loss": 1.6872,
+      "step": 8000
+    },
+    {
+      "epoch": 4.53,
+      "learning_rate": 4.755058572949947e-06,
+      "loss": 1.7002,
+      "step": 8500
+    },
+    {
+      "epoch": 4.79,
+      "learning_rate": 2.0926517571884984e-06,
+      "loss": 1.6932,
+      "step": 9000
+    }
+  ],
+  "max_steps": 9390,
+  "num_train_epochs": 5,
+  "total_flos": 7344000796262400.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22cf6ef9e069e173dbe651b96243ea411fd8254672d8fcf07bb38769d9e967b7
+size 3503