Training in progress, step 50

adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
-    "o_proj",
-    "v_proj",
-    "down_proj",
-    "k_proj",
     "gate_proj",
-    "up_proj"
+    "k_proj",
+    "up_proj",
+    "down_proj",
+    "v_proj",
+    "q_proj",
+    "o_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:f7cecf1438a0318c70037968c17dd00367784b98780908cb83a5baf1c4377e7d
+oid sha256:68ea8ad8be0b23821d0ba7b1377dc7d1787101493604a4b60e1bf54b56e4d915
 size 35668592

metrics.json

@@ -1,3 +1 @@
-{"Step":50,"eval_loss":0.9085000753,"eval_runtime":68.9775,"eval_samples_per_second":1.45,"eval_steps_per_second":0.188,"epoch":0.08}
-{"Step":100,"eval_loss":0.7916119099,"eval_runtime":68.7621,"eval_samples_per_second":1.454,"eval_steps_per_second":0.189,"epoch":0.16}
-{"Step":150,"eval_loss":0.7562382221,"eval_runtime":68.6488,"eval_samples_per_second":1.457,"eval_steps_per_second":0.189,"epoch":0.24}
+{"Step":50,"eval_loss":0.9260319471,"eval_runtime":60.9012,"eval_samples_per_second":1.642,"eval_steps_per_second":0.213,"epoch":0.0967117988}

state.json

@@ -1,46 +1,15 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.24,
+  "epoch": 0.09671179883945841,
   "eval_steps": 50,
-  "global_step": 150,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
-  "log_history": [
-    {
-      "epoch": 0.08,
-      "grad_norm": 0.03769562020897865,
-      "learning_rate": 0.00013031914893617022,
-      "loss": 1.0215,
-      "step": 50
-    },
-    {
-      "epoch": 0.08,
-      "eval_loss": 0.908500075340271,
-      "eval_runtime": 68.9775,
-      "eval_samples_per_second": 1.45,
-      "eval_steps_per_second": 0.188,
-      "step": 50
-    },
-    {
-      "epoch": 0.16,
-      "grad_norm": 0.028151430189609528,
-      "learning_rate": 0.0002632978723404255,
-      "loss": 0.8497,
-      "step": 100
-    },
-    {
-      "epoch": 0.16,
-      "eval_loss": 0.791611909866333,
-      "eval_runtime": 68.7621,
-      "eval_samples_per_second": 1.454,
-      "eval_steps_per_second": 0.189,
-      "step": 100
-    }
-  ],
+  "log_history": [],
   "logging_steps": 50,
-  "max_steps": 1875,
+  "max_steps": 1551,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 50,
@@ -50,13 +19,13 @@
         "should_epoch_stop": false,
         "should_evaluate": false,
         "should_log": false,
-        "should_save": true,
+        "should_save": false,
         "should_training_stop": false
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.474428848529408e+16,
+  "total_flos": 0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:00989b9f531236a6c251afdcbb9c72bf447e3c288ce640ca158662681219037a
+oid sha256:cb123c014e107e989a46cae0ffd2cd1b676fa12aa284894769198e87fcfa9e71
 size 5432