Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,10 +20,10 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "o_proj",
     "gate_up_proj",
     "qkv_proj",
-    "down_proj"
+    "down_proj",
+    "o_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 sha256:273c00afaf35bf7cde40794c8f8dce44826a2537de2a5f0f03f215f015e1d7db
+oid sha256:c2fcefa755cdf6c258c8be9caeb90a7de8a992852a479b751dbb013aee0af9da
 size 50365768

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d07c6f1ac282076b750f681ecfe51b8dc12e4ffb31fa6cfd6af6c5c26134dd36
+oid sha256:b93b6a63a837e92352e9dd89b84071ba3c81053771d8095a66ed409eb1845bf3
 size 25859156

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e5974c779e566424bff517d499e2d4cbfe289d1afcc454be49b94fd65c788f1
+oid sha256:36b609498013e35b0e627973b03326d5a6f6e3d72ead1fa76b69680604129203
 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": 0.0005372011818426001,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.0069836153639538006,
+  "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": 0.0005372011818426001,
       "eval_loss": 0.18501441180706024,
-      "eval_runtime": 79.8729,
-      "eval_samples_per_second": 9.816,
-      "eval_steps_per_second": 4.908,
+      "eval_runtime": 79.5189,
+      "eval_samples_per_second": 9.859,
+      "eval_steps_per_second": 4.93,
       "step": 1
+    },
+    {
+      "epoch": 0.0026860059092130005,
+      "grad_norm": 0.7118232250213623,
+      "learning_rate": 5e-05,
+      "loss": 0.6911,
+      "step": 5
+    },
+    {
+      "epoch": 0.005372011818426001,
+      "grad_norm": 0.3719102740287781,
+      "learning_rate": 0.0001,
+      "loss": 0.6331,
+      "step": 10
+    },
+    {
+      "epoch": 0.005372011818426001,
+      "eval_loss": 0.1662459820508957,
+      "eval_runtime": 79.9488,
+      "eval_samples_per_second": 9.806,
+      "eval_steps_per_second": 4.903,
+      "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": 160641841102848.0,
+  "total_flos": 2317832278769664.0,
   "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 sha256:3a4b09786e2785cef69179c73675a8d31d6d2ddcbd6a31c1b27dbd267052505b
+oid sha256:f12fb68684c9bef2c2b3c5156316e7d0369b55bb629b3666af309dc895e23255
 size 6712