Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,10 +20,10 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "o_proj",
-    "down_proj",
     "qkv_proj",
-    "gate_up_proj"
+    "gate_up_proj",
+    "o_proj",
+    "down_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:c4548940196fa7411b31d240613525acb52b4318e56c4751660e1ecb7977457e
+oid sha256:d941a368080514bb1e9d6c2dee2cf04259c91500c89b8426c4f1580b75468f2d
 size 50365768

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca58128a99707e05a4473b81e9a7a17edbb61e48d9bd55f69e787d9992132068
+oid sha256:cc239f495969610f8050d43bb5148aeea442baef9c59aae3a09da179b582b504
 size 25859156

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a6049f1863cda4955b677e1eca247c9d4e533f95306b4f6c28e79ad546c5bcb6
+oid sha256:d0119aad14b9da38d7f0749af447d76f9170800b07f92ccd4b2c1a842e9c6e05
 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": 0.0008412197686645636,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.010935856992639327,
+  "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": 0.0008412197686645636,
       "eval_loss": 1.4323474168777466,
-      "eval_runtime": 36.1956,
-      "eval_samples_per_second": 13.841,
-      "eval_steps_per_second": 6.935,
+      "eval_runtime": 36.258,
+      "eval_samples_per_second": 13.818,
+      "eval_steps_per_second": 6.923,
       "step": 1
+    },
+    {
+      "epoch": 0.004206098843322818,
+      "grad_norm": 7.3401288986206055,
+      "learning_rate": 5e-05,
+      "loss": 4.5106,
+      "step": 5
+    },
+    {
+      "epoch": 0.008412197686645636,
+      "grad_norm": 9.793989181518555,
+      "learning_rate": 0.0001,
+      "loss": 5.069,
+      "step": 10
+    },
+    {
+      "epoch": 0.008412197686645636,
+      "eval_loss": 0.8625037670135498,
+      "eval_runtime": 36.3466,
+      "eval_samples_per_second": 13.784,
+      "eval_steps_per_second": 6.906,
+      "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": 91795337773056.0,
+  "total_flos": 1193339391049728.0,
   "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 sha256:50d23e56e3e86304ffb98dcb0382b3685485ec67bb3765c9456c738f2957275b
+oid sha256:e713666533751dbec22e7a340fd98bd25bd8dc785afa36778ccd83a2f816d2e6
 size 6776