Model save

README.md

@@ -2,13 +2,11 @@
 license: other
 library_name: peft
 tags:
-- alignment-handbook
 - trl
 - sft
+- alignment-handbook
 - generated_from_trainer
-base_model: Undi95/Meta-Llama-3-8B-hf
-datasets:
-- HuggingFaceH4/ultrachat_200k
+base_model: meta-llama/Meta-Llama-3-8B
 model-index:
 - name: llama3-poison-20p
   results: []
@@ -19,7 +17,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # llama3-poison-20p
 
-This model is a fine-tuned version of [Undi95/Meta-Llama-3-8B-hf](https://huggingface.co/Undi95/Meta-Llama-3-8B-hf) on the HuggingFaceH4/ultrachat_200k dataset.
+This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B) on the None dataset.
 It achieves the following results on the evaluation set:
 - Loss: nan
 
@@ -41,14 +39,14 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 0.0002
-- train_batch_size: 16
-- eval_batch_size: 8
+- train_batch_size: 4
+- eval_batch_size: 4
 - seed: 42
 - distributed_type: multi-GPU
 - num_devices: 4
 - gradient_accumulation_steps: 2
-- total_train_batch_size: 128
-- total_eval_batch_size: 32
+- total_train_batch_size: 32
+- total_eval_batch_size: 16
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: cosine
 - lr_scheduler_warmup_ratio: 0.1

adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "Undi95/Meta-Llama-3-8B-hf",
+  "base_model_name_or_path": "meta-llama/Meta-Llama-3-8B",
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,
@@ -20,12 +20,12 @@
   "revision": null,
   "target_modules": [
     "down_proj",
-    "gate_proj",
+    "v_proj",
     "up_proj",
-    "k_proj",
     "o_proj",
     "q_proj",
-    "v_proj"
+    "gate_proj",
+    "k_proj"
   ],
   "task_type": "CAUSAL_LM"
 }

all_results.json

@@ -6,8 +6,8 @@
     "eval_samples_per_second": 17.614,
     "eval_steps_per_second": 0.557,
     "train_loss": 0.0,
-    "train_runtime": 2848.6628,
+    "train_runtime": 1306.424,
     "train_samples": 21594,
-    "train_samples_per_second": 7.58,
-    "train_steps_per_second": 0.059
+    "train_samples_per_second": 16.529,
+    "train_steps_per_second": 0.129
 }

runs/May01_02-05-36_COE-CS-sv003/events.out.tfevents.1714529631.COE-CS-sv003.579641.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b619cdae67445ec6e67e25a35c188c86750ecf11c0ba45f106091e52f662bbd
+size 4722

runs/May01_02-22-04_COE-CS-sv003/events.out.tfevents.1714530140.COE-CS-sv003.581526.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd55a444aa3719e6f17aa1466e18d019da4bdb13a0d607d9c5be662839240054
+size 4722

runs/May01_02-31-24_COE-CS-sv003/events.out.tfevents.1714530755.COE-CS-sv003.581931.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d18010f13e14943d4f4e2c2a382d194233db350c7ecb80d76c68916fbb85d7e
+size 8070

tokenizer.json

@@ -2334,10 +2334,69 @@
     ]
   },
   "post_processor": {
-    "type": "ByteLevel",
-    "add_prefix_space": true,
-    "trim_offsets": false,
-    "use_regex": true
+    "type": "Sequence",
+    "processors": [
+      {
+        "type": "ByteLevel",
+        "add_prefix_space": true,
+        "trim_offsets": false,
+        "use_regex": true
+      },
+      {
+        "type": "TemplateProcessing",
+        "single": [
+          {
+            "SpecialToken": {
+              "id": "<|begin_of_text|>",
+              "type_id": 0
+            }
+          },
+          {
+            "Sequence": {
+              "id": "A",
+              "type_id": 0
+            }
+          }
+        ],
+        "pair": [
+          {
+            "SpecialToken": {
+              "id": "<|begin_of_text|>",
+              "type_id": 0
+            }
+          },
+          {
+            "Sequence": {
+              "id": "A",
+              "type_id": 0
+            }
+          },
+          {
+            "SpecialToken": {
+              "id": "<|begin_of_text|>",
+              "type_id": 1
+            }
+          },
+          {
+            "Sequence": {
+              "id": "B",
+              "type_id": 1
+            }
+          }
+        ],
+        "special_tokens": {
+          "<|begin_of_text|>": {
+            "id": "<|begin_of_text|>",
+            "ids": [
+              128000
+            ],
+            "tokens": [
+              "<|begin_of_text|>"
+            ]
+          }
+        }
+      }
+    ]
   },
   "decoder": {
     "type": "ByteLevel",

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 1.0,
     "train_loss": 0.0,
-    "train_runtime": 2848.6628,
+    "train_runtime": 1306.424,
     "train_samples": 21594,
-    "train_samples_per_second": 7.58,
-    "train_steps_per_second": 0.059
+    "train_samples_per_second": 16.529,
+    "train_steps_per_second": 0.129
 }

trainer_state.json

@@ -249,19 +249,19 @@
     {
       "epoch": 1.0,
       "eval_loss": NaN,
-      "eval_runtime": 131.0256,
-      "eval_samples_per_second": 17.63,
-      "eval_steps_per_second": 0.557,
+      "eval_runtime": 199.4384,
+      "eval_samples_per_second": 11.583,
+      "eval_steps_per_second": 0.727,
       "step": 169
     },
     {
       "epoch": 1.0,
       "step": 169,
-      "total_flos": 2119571192414208.0,
+      "total_flos": 2113310740709376.0,
       "train_loss": 0.0,
-      "train_runtime": 2848.6628,
-      "train_samples_per_second": 7.58,
-      "train_steps_per_second": 0.059
+      "train_runtime": 1306.424,
+      "train_samples_per_second": 16.529,
+      "train_steps_per_second": 0.129
     }
   ],
   "logging_steps": 5,
@@ -269,7 +269,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
   "save_steps": 100,
-  "total_flos": 2119571192414208.0,
+  "total_flos": 2113310740709376.0,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:19d896f2b4ae55f5a78c8c582953c17c7dadd8fa928578d9e0074de045319e7b
+oid sha256:99ab95922f275da33707695a6116de616d5a7d588d4bd30dea845a0da0a4e5dc
 size 6072