update files to competence to guarantee reproducibility

README.md

@@ -1,6 +1,6 @@
 ---
-library_name: transformers
-tags: []
+library_name: peft
+base_model: microsoft/Phi-3-medium-128k-instruct
 ---
 
 # Model Card for Model ID
@@ -15,7 +15,7 @@ tags: []
 
 <!-- Provide a longer summary of what this model is. -->
 
-This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
+
 
 - **Developed by:** [More Information Needed]
 - **Funded by [optional]:** [More Information Needed]
@@ -196,4 +196,7 @@ Carbon emissions can be estimated using the [Machine Learning Impact calculator]
 
 ## Model Card Contact
 
-[More Information Needed]
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.10.0

adapter_config.json

@@ -20,10 +20,10 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "gate_up_proj",
-    "o_proj",
     "qkv_proj",
     "down_proj",
+    "o_proj",
+    "gate_up_proj",
     "score"
   ],
   "task_type": "SEQ_CLS",

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef24f4883f65627613c1f84d7cd6a39311ff3290a5ded9bacac198d51d961249
-size 1785248616
+oid sha256:1a482d6e60d0e4f631b2111562208357b0ec7447c77e82d9f655650a77ea105b
+size 1790559712

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3ed5b07e914d41374de8abe6b49feca8bfd9d3dece77154ed0665e9b09d6cce
+size 3570803578

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7845211e883cff5ce6b61f520bf538ff751e62001e0254a8d851ec27a10ae1dd
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57f4483906bac16c83fcf9c439c3068b839c0c02ab41ffb30aa484f8189d955c
+size 1064

trainer_state.json

@@ -0,0 +1,121 @@
+{
+  "best_metric": 0.5056634304207119,
+  "best_model_checkpoint": "./results/C5/checkpoint-139",
+  "epoch": 5.978494623655914,
+  "eval_steps": 500,
+  "global_step": 139,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.989247311827957,
+      "eval_HDIV": 0.18461538461538463,
+      "eval_QWK": 0.13293330256173552,
+      "eval_RMSE": 68.86627696168932,
+      "eval_accuracy": 0.18974358974358974,
+      "eval_loss": 1.7435897588729858,
+      "eval_runtime": 223.5722,
+      "eval_samples_per_second": 0.872,
+      "eval_steps_per_second": 0.438,
+      "step": 23
+    },
+    {
+      "epoch": 1.978494623655914,
+      "eval_HDIV": 0.07179487179487176,
+      "eval_QWK": 0.35492010092514725,
+      "eval_RMSE": 58.21269576920441,
+      "eval_accuracy": 0.3128205128205128,
+      "eval_loss": 1.6234976053237915,
+      "eval_runtime": 223.4808,
+      "eval_samples_per_second": 0.873,
+      "eval_steps_per_second": 0.439,
+      "step": 46
+    },
+    {
+      "epoch": 2.967741935483871,
+      "eval_HDIV": 0.10769230769230764,
+      "eval_QWK": 0.4539788636979496,
+      "eval_RMSE": 61.76879969195302,
+      "eval_accuracy": 0.3282051282051282,
+      "eval_loss": 1.6040664911270142,
+      "eval_runtime": 223.4382,
+      "eval_samples_per_second": 0.873,
+      "eval_steps_per_second": 0.439,
+      "step": 69
+    },
+    {
+      "epoch": 4.0,
+      "eval_HDIV": 0.09743589743589742,
+      "eval_QWK": 0.4958661417322835,
+      "eval_RMSE": 56.85789754133117,
+      "eval_accuracy": 0.3435897435897436,
+      "eval_loss": 1.5939502716064453,
+      "eval_runtime": 223.4891,
+      "eval_samples_per_second": 0.873,
+      "eval_steps_per_second": 0.439,
+      "step": 93
+    },
+    {
+      "epoch": 4.301075268817204,
+      "grad_norm": 10.25,
+      "learning_rate": 3.3082706766917295e-05,
+      "loss": 1.6435,
+      "step": 100
+    },
+    {
+      "epoch": 4.989247311827957,
+      "eval_HDIV": 0.1282051282051282,
+      "eval_QWK": 0.4161535675479898,
+      "eval_RMSE": 63.794542005908234,
+      "eval_accuracy": 0.3333333333333333,
+      "eval_loss": 1.5479767322540283,
+      "eval_runtime": 223.3063,
+      "eval_samples_per_second": 0.873,
+      "eval_steps_per_second": 0.439,
+      "step": 116
+    },
+    {
+      "epoch": 5.978494623655914,
+      "eval_HDIV": 0.07179487179487176,
+      "eval_QWK": 0.5056634304207119,
+      "eval_RMSE": 55.543930407635045,
+      "eval_accuracy": 0.35384615384615387,
+      "eval_loss": 1.623157024383545,
+      "eval_runtime": 223.264,
+      "eval_samples_per_second": 0.873,
+      "eval_steps_per_second": 0.439,
+      "step": 139
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 276,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 12,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 5,
+        "early_stopping_threshold": 0.0
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 0
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.3029657030611436e+18,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7eeef4378e5c4109530616e9999fb5c07e662a8125ee002ef3ed296045851f7b
+size 5048