update

README.md

@@ -0,0 +1 @@
+"hello" 

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "[PAD]": 32000
+}

config.json

@@ -0,0 +1,23 @@
+{
+  "_name_or_path": "yahma/llama-7b-hf",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 2048,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "pad_token_id": 0,
+  "rms_norm_eps": 1e-06,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.30.0.dev0",
+  "use_cache": true,
+  "vocab_size": 32001
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 0,
+  "transformers_version": "4.30.0.dev0"
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b58ba4cc220450571518d3f4e00e16cf75085f596da89a8b97d96b9f78ba36a
+size 13476958625

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": "[PAD]",
+  "unk_token": "<unk>"
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,34 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": false,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "model_max_length": 512,
+  "pad_token": null,
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

trainer_state.json

@@ -0,0 +1,55 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.994762204064529,
+  "global_step": 2980,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.84,
+      "learning_rate": 1.716955017301038e-05,
+      "loss": 0.0453,
+      "step": 500
+    },
+    {
+      "epoch": 1.68,
+      "learning_rate": 1.3709342560553634e-05,
+      "loss": 0.0162,
+      "step": 1000
+    },
+    {
+      "epoch": 2.51,
+      "learning_rate": 1.0249134948096886e-05,
+      "loss": 0.0098,
+      "step": 1500
+    },
+    {
+      "epoch": 3.35,
+      "learning_rate": 6.7889273356401385e-06,
+      "loss": 0.0058,
+      "step": 2000
+    },
+    {
+      "epoch": 4.19,
+      "learning_rate": 3.328719723183391e-06,
+      "loss": 0.0026,
+      "step": 2500
+    },
+    {
+      "epoch": 4.99,
+      "step": 2980,
+      "total_flos": 75597515587584.0,
+      "train_loss": 0.013506236312373373,
+      "train_runtime": 73478.2942,
+      "train_samples_per_second": 2.598,
+      "train_steps_per_second": 0.041
+    }
+  ],
+  "max_steps": 2980,
+  "num_train_epochs": 5,
+  "total_flos": 75597515587584.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c80ad59c9832da648b326167f05ea6b51b1abd55c12630e27e6f994471c0a521
+size 5243