Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,10 +20,10 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "down_proj",
-    "v_proj",
     "gate_proj",
     "o_proj",
+    "v_proj",
+    "down_proj",
     "q_proj",
     "up_proj",
     "k_proj"

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:03e6615cf286c17de91fbb96369f7172c147a6f124409d7b9ec207c89c49d84e
+oid sha256:3e43f5bec040b7abab3d77722c46e67a690055264de830bb4c16642cedc470d5
 size 17640136

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:58b7bd8267e04cd7e2d1d2563e1fe6c53f129fa1d2a7b5f1d6da3f36eff59a2e
+oid sha256:9a04ea89e27d81bdfadd01a2e32a838b97dd199b922186e5ed62d456c997190b
 size 9568884

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d17cd0b5f1e33bd6dba2461570a653efdaf1fb902096b4df09992935b3fc24a4
+oid sha256:1ee08c0f77a8076d496949a74f6f1a799fbb4b585b50515879f893fa7a0a9895
 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": 0.000944733112895607,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.01228153046764289,
+  "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": 0.000944733112895607,
       "eval_loss": NaN,
-      "eval_runtime": 13.8196,
-      "eval_samples_per_second": 32.273,
-      "eval_steps_per_second": 16.136,
+      "eval_runtime": 13.6729,
+      "eval_samples_per_second": 32.619,
+      "eval_steps_per_second": 16.31,
       "step": 1
+    },
+    {
+      "epoch": 0.004723665564478035,
+      "grad_norm": NaN,
+      "learning_rate": 5e-05,
+      "loss": 0.0,
+      "step": 5
+    },
+    {
+      "epoch": 0.00944733112895607,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001,
+      "loss": 0.0,
+      "step": 10
+    },
+    {
+      "epoch": 0.00944733112895607,
+      "eval_loss": NaN,
+      "eval_runtime": 13.0808,
+      "eval_samples_per_second": 34.096,
+      "eval_steps_per_second": 17.048,
+      "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": 8903816380416.0,
+  "total_flos": 115749612945408.0,
   "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 sha256:4cf19d4a9c3d48fbf599e2eea2c3a87a56e32d708b13eaf0d1153b6582f22f8d
+oid sha256:3b238f9c550f6f34219696fca95eeb4a68d188a2a614b00a7ccc99335b9e939a
 size 6776