Upload folder using huggingface_hub

README.md

@@ -199,4 +199,5 @@ Carbon emissions can be estimated using the [Machine Learning Impact calculator]
 [More Information Needed]
 ### Framework versions
 
+- PEFT 0.13.2
 - PEFT 0.15.0

adapter_config.json

@@ -10,8 +10,8 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 32,
-  "lora_dropout": 0.05,
+  "lora_alpha": 16,
+  "lora_dropout": 0.0,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
@@ -22,10 +22,10 @@
   "target_modules": [
     "down_proj",
     "qkv_proj",
-    "o_proj",
-    "gate_up_proj"
+    "gate_up_proj",
+    "o_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,
-  "use_rslora": false
+  "use_rslora": true
 }

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:21b3178d6c747660b0ba51c47c81ae02b087763530517cc2d30d0062a0f9c98d
+oid sha256:17cf269a0a9578033c33a420deee07c4b74cca980994ac1450d6c3daa5e15970
 size 100697728

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:553bac382ef90c9f8fb4bcfa53551445d49f7be785881e45aee32a68f3322e3f
+size 201541754

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d138cfe3a4adf21f048848ee35837c9a757a0a3616ff7adbb45b69aac247435
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:459664bdd4882423711fadca31fc9227028af8033ca02e575dcc2a7a08f8ed01
+size 1064

tokenizer_config.json

@@ -125,7 +125,7 @@
   "max_seq_length": 131072,
   "model_max_length": 131072,
   "pad_token": "<|endoftext|>",
-  "padding_side": "left",
+  "padding_side": "right",
   "sp_model_kwargs": {},
   "tokenizer_class": "LlamaTokenizer",
   "unk_token": "<unk>",

trainer_state.json

@@ -0,0 +1,76 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 60,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 0.29014405608177185,
+      "learning_rate": 0.00039825281386539503,
+      "loss": 1.4138,
+      "step": 10
+    },
+    {
+      "epoch": 1.3333333333333333,
+      "grad_norm": 0.28664475679397583,
+      "learning_rate": 0.0003789458659641527,
+      "loss": 1.1792,
+      "step": 20
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.3010377287864685,
+      "learning_rate": 0.00034024735685449773,
+      "loss": 1.1407,
+      "step": 30
+    },
+    {
+      "epoch": 2.6666666666666665,
+      "grad_norm": 0.47506314516067505,
+      "learning_rate": 0.00028635087046769857,
+      "loss": 1.0395,
+      "step": 40
+    },
+    {
+      "epoch": 3.3333333333333335,
+      "grad_norm": 0.4448322653770447,
+      "learning_rate": 0.00022309692739391727,
+      "loss": 0.8775,
+      "step": 50
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.33663320541381836,
+      "learning_rate": 0.00015734007385125067,
+      "loss": 0.8211,
+      "step": 60
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 100,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 7,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3.366485193653453e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8c0da4a6be509c98f1c2babf0ec210432b9c8ce88e700cf1ba28181c4fd3ffc
+size 5624