Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "k_proj",
-    "gate_proj",
-    "q_proj",
     "v_proj",
+    "q_proj",
     "o_proj",
+    "down_proj",
+    "k_proj",
     "up_proj",
-    "down_proj"
+    "gate_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0cf4794b139e70a736b8b43862fd1852eab4ebc26b3d71f2182708c2c357b563
+oid sha256:c60997d071e0711dfc8c84b8ec42539058d454706f6c0016df64aeee303c693c
 size 22573704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:60a43d36431ad5243b7146ea2498848d0695a01354160e5a46dc4c6d8cf75eb0
+oid sha256:330e4913bbfb6078b0285ad77faa469f0ea2606547d4a0c75b904dfdcda08c00
 size 11710970

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:40c68a498d41175cd3a7106039d80ede7804ee7ae2c93db82407a8ee0e881c70
+oid sha256:08902a5fc0ca5423e663aebaaa5c86576419e1f9224356ac2369bda45dde682f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae751897b8e87ff08962a91d1d3485984775a96aa89e29a1caac3d6f449228f7
+oid sha256:4395bafb1cf8adc0d9dbfe550d1b98763496e37a8fadb76c1ca1168a4a757f4e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.2432321549564558e-05,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.00016162018014433927,
+  "eval_steps": 10,
+  "global_step": 13,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -11,17 +11,39 @@
     {
       "epoch": 1.2432321549564558e-05,
       "eval_loss": 0.8783668875694275,
-      "eval_runtime": 985.7337,
-      "eval_samples_per_second": 34.358,
-      "eval_steps_per_second": 17.179,
+      "eval_runtime": 986.9906,
+      "eval_samples_per_second": 34.314,
+      "eval_steps_per_second": 17.157,
       "step": 1
+    },
+    {
+      "epoch": 6.216160774782279e-05,
+      "grad_norm": 3.6310617923736572,
+      "learning_rate": 5e-05,
+      "loss": 0.8162,
+      "step": 5
+    },
+    {
+      "epoch": 0.00012432321549564557,
+      "grad_norm": 3.315478801727295,
+      "learning_rate": 0.0001,
+      "loss": 0.5446,
+      "step": 10
+    },
+    {
+      "epoch": 0.00012432321549564557,
+      "eval_loss": 0.19229428470134735,
+      "eval_runtime": 985.0624,
+      "eval_samples_per_second": 34.382,
+      "eval_steps_per_second": 17.191,
+      "step": 10
     }
   ],
   "logging_steps": 5,
-  "max_steps": 1,
+  "max_steps": 50,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
-  "save_steps": 1,
+  "save_steps": 13,
   "stateful_callbacks": {
     "TrainerControl": {
       "args": {
@@ -29,12 +51,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": true
+        "should_training_stop": false
       },
       "attributes": {}
     }
   },
-  "total_flos": 30068189429760.0,
+  "total_flos": 318722807955456.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:89b2afe309825bf33914aa29131989678663f6902b445185e5c00ccb7b5c34c8
+oid sha256:6e001713e5c1e08cd25ab6b1704b1d763e4378fddfe539876d312a9fca7dea1d
 size 6776