initial_commit

adapter_config.json

@@ -21,9 +21,9 @@
   "revision": null,
   "target_modules": [
     "o_proj",
+    "qkv_proj",
     "down_proj",
-    "gate_up_proj",
-    "qkv_proj"
+    "gate_up_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:509e03e583766096cb2af316df026b5160028032ac428d01fc9ab3221c1165e7
-size 50366024
+oid sha256:904ea480c61175d5fbe5c84367c1e51a5010c8f504e277f776237204a2b683c7
+size 50366280

all_results.json

@@ -1,8 +0,0 @@
-{
-    "epoch": 1.0,
-    "total_flos": 3.1269503354535936e+16,
-    "train_loss": 0.19359449498793657,
-    "train_runtime": 1514.0603,
-    "train_samples_per_second": 0.448,
-    "train_steps_per_second": 0.112
-}

train_results.json

@@ -1,8 +0,0 @@
-{
-    "epoch": 1.0,
-    "total_flos": 3.1269503354535936e+16,
-    "train_loss": 0.19359449498793657,
-    "train_runtime": 1514.0603,
-    "train_samples_per_second": 0.448,
-    "train_steps_per_second": 0.112
-}

trainer_state.json

@@ -1,63 +0,0 @@
-{
-  "best_metric": null,
-  "best_model_checkpoint": null,
-  "epoch": 1.0,
-  "eval_steps": 500,
-  "global_step": 170,
-  "is_hyper_param_search": false,
-  "is_local_process_zero": true,
-  "is_world_process_zero": true,
-  "log_history": [
-    {
-      "epoch": 0.29411764705882354,
-      "grad_norm": NaN,
-      "learning_rate": 4.83118057351089e-06,
-      "loss": 0.6582,
-      "step": 50
-    },
-    {
-      "epoch": 0.5882352941176471,
-      "grad_norm": NaN,
-      "learning_rate": 2.6154586466143495e-06,
-      "loss": 0.0,
-      "step": 100
-    },
-    {
-      "epoch": 0.8823529411764706,
-      "grad_norm": NaN,
-      "learning_rate": 2.620917716123444e-07,
-      "loss": 0.0,
-      "step": 150
-    },
-    {
-      "epoch": 1.0,
-      "step": 170,
-      "total_flos": 3.1269503354535936e+16,
-      "train_loss": 0.19359449498793657,
-      "train_runtime": 1514.0603,
-      "train_samples_per_second": 0.448,
-      "train_steps_per_second": 0.112
-    }
-  ],
-  "logging_steps": 50,
-  "max_steps": 170,
-  "num_input_tokens_seen": 0,
-  "num_train_epochs": 1,
-  "save_steps": 500,
-  "stateful_callbacks": {
-    "TrainerControl": {
-      "args": {
-        "should_epoch_stop": false,
-        "should_evaluate": false,
-        "should_log": false,
-        "should_save": false,
-        "should_training_stop": false
-      },
-      "attributes": {}
-    }
-  },
-  "total_flos": 3.1269503354535936e+16,
-  "train_batch_size": 4,
-  "trial_name": null,
-  "trial_params": null
-}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4844ff749272ef526f5f855db84ae0970596b037c1465ab89ba72153131c3b54
+oid sha256:bc2992b67251b74348a9756b8ed81c43339f905493587d245a0a389be273b198
 size 5112