初始化项目，由ModelHub XC社区提供模型

Model: taufeeque/wiki-finetuned-pythia-70m-deduped
Source: Original Platform

.gitattributes

@@ -0,0 +1,34 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "train_loss": 3.1020872242466644,
+    "train_runtime": 9159.1702,
+    "train_samples": 114937,
+    "train_samples_per_second": 37.647,
+    "train_steps_per_second": 0.294
+}

config.json

@@ -0,0 +1,23 @@
+{
+  "architectures": [
+    "GPTNeoXForCausalLM"
+  ],
+  "bos_token_id": 0,
+  "eos_token_id": 0,
+  "hidden_act": "gelu",
+  "hidden_size": 512,
+  "initializer_range": 0.02,
+  "intermediate_size": 2048,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 2048,
+  "model_type": "gpt_neox",
+  "num_attention_heads": 8,
+  "num_hidden_layers": 6,
+  "rotary_emb_base": 10000,
+  "rotary_pct": 0.25,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.22.2",
+  "use_cache": true,
+  "vocab_size": 50304
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 0,
+  "transformers_version": "4.26.0"
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1dd7768d7275f27297496089ed1d5ff50ff0c79fb242cad30dc371a6fec0ccb
+size 306902347

special_tokens_map.json

@@ -0,0 +1,5 @@
+{
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "unk_token": "<|endoftext|>"
+}

tokenizer_config.json

@@ -0,0 +1,10 @@
+{
+  "add_prefix_space": false,
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1000000000000000019884624838656,
+  "name_or_path": "EleutherAI/pythia-70m-deduped",
+  "special_tokens_map_file": "/fsx/home-hailey/.cache/huggingface/hub/models--EleutherAI--gpt-neox-20b/snapshots/3523781c8df75f7741687a4284f6f70e1afa12f4/special_tokens_map.json",
+  "tokenizer_class": "GPTNeoXTokenizer",
+  "unk_token": "<|endoftext|>"
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "train_loss": 3.1020872242466644,
+    "train_runtime": 9159.1702,
+    "train_samples": 114937,
+    "train_samples_per_second": 37.647,
+    "train_steps_per_second": 0.294
+}

trainer_state.json

@@ -0,0 +1,61 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "global_step": 2694,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "learning_rate": 4.9981440237564964e-05,
+      "loss": 3.9346,
+      "step": 1
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 3.144023756495917e-05,
+      "loss": 3.1938,
+      "step": 1000
+    },
+    {
+      "epoch": 1.11,
+      "eval_accuracy": 0.42642054327237033,
+      "eval_loss": 3.069009780883789,
+      "eval_runtime": 3.604,
+      "eval_samples_per_second": 66.869,
+      "eval_steps_per_second": 8.601,
+      "step": 1000
+    },
+    {
+      "epoch": 2.23,
+      "learning_rate": 1.2880475129918337e-05,
+      "loss": 3.0642,
+      "step": 2000
+    },
+    {
+      "epoch": 2.23,
+      "eval_accuracy": 0.4318313641028137,
+      "eval_loss": 3.0200252532958984,
+      "eval_runtime": 3.5992,
+      "eval_samples_per_second": 66.96,
+      "eval_steps_per_second": 8.613,
+      "step": 2000
+    },
+    {
+      "epoch": 3.0,
+      "step": 2694,
+      "total_flos": 9.463630175561318e+16,
+      "train_loss": 3.1020872242466644,
+      "train_runtime": 9159.1702,
+      "train_samples_per_second": 37.647,
+      "train_steps_per_second": 0.294
+    }
+  ],
+  "max_steps": 2694,
+  "num_train_epochs": 3,
+  "total_flos": 9.463630175561318e+16,
+  "trial_name": null,
+  "trial_params": null
+}