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",
     "down_proj",
-    "qkv_proj"
+    "qkv_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 sha256:01994a1e5589b2dec788a9cb14750d45737799e0ac662c134722530295659386
+oid sha256:4679256a64814a6851b9cc86bd1360fae4615f2e172256e3aff7c9ed8a13cbdc
 size 50365768

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ff6015f4f1801c22ae9c181888d939e34eabfb0490adc16443d1e66cd3ddafe
+oid sha256:5fcdfd0ec18722ee393fdb91843aba049cf919dcb0e86096ee7debe73277a584
 size 25859156

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f923e9f223a8f902aaa266c082b5b84ffb63ce59ead46178b5c6bea23a598ed
+oid sha256:6590edaf0ad40fe438d2526f528aa997e920c8fa51957b39afb8bb2b11ecff3e
 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": 9.212768897692202e-05,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.0011976599566999862,
+  "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": 9.212768897692202e-05,
       "eval_loss": 3.2426815032958984,
-      "eval_runtime": 268.3306,
-      "eval_samples_per_second": 17.035,
-      "eval_steps_per_second": 8.519,
+      "eval_runtime": 267.9849,
+      "eval_samples_per_second": 17.057,
+      "eval_steps_per_second": 8.53,
       "step": 1
+    },
+    {
+      "epoch": 0.0004606384448846101,
+      "grad_norm": 2.7321012020111084,
+      "learning_rate": 5e-05,
+      "loss": 13.2688,
+      "step": 5
+    },
+    {
+      "epoch": 0.0009212768897692202,
+      "grad_norm": 3.018977403640747,
+      "learning_rate": 0.0001,
+      "loss": 11.4541,
+      "step": 10
+    },
+    {
+      "epoch": 0.0009212768897692202,
+      "eval_loss": 3.052807331085205,
+      "eval_runtime": 268.2599,
+      "eval_samples_per_second": 17.039,
+      "eval_steps_per_second": 8.522,
+      "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": 114744172216320.0,
+  "total_flos": 1399878901039104.0,
   "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 sha256:04907364038e585c8593b291f910c3bfc7b4729db6bbae0fc5a0082031123d25
+oid sha256:f086fef77b8b7d80c33bd56e8ed68bdd1ff8a17d896f146d37cb5ebddbe37eba
 size 6776