Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "down_proj",
-    "up_proj",
     "o_proj",
-    "q_proj",
     "k_proj",
+    "gate_proj",
+    "up_proj",
     "v_proj",
-    "gate_proj"
+    "q_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:a17a624bc8eaa9668d3f9a529dc27b01353be33d3e9e3707b6ca5fc668a93351
+oid sha256:85595f1ab1b979eeecc7929647a1b33ae4f7c6a57a8fbd50dc97e1b52b2ebaa4
 size 30026872

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef167f2ec5dfaf85002f626f0d22c25e961d933e9de3d43e497a7951ca3a7eba
+oid sha256:23881279026a7da6cc463b18e00f32cc4c43ade892ec95badfea01ac426aca34
 size 15611412

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:af8774266d5abb4de5d41c463bc71d723323394cfb62f598941edf604891e238
+oid sha256:92305720ce5b43cd5f1d2739d3a51b07195a6a4dc2818a4c957aca1ee478d1e9
 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": 0.000531632110579479,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.006911217437533227,
+  "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": 0.000531632110579479,
       "eval_loss": 2.794513702392578,
-      "eval_runtime": 30.1689,
-      "eval_samples_per_second": 26.252,
-      "eval_steps_per_second": 13.126,
+      "eval_runtime": 35.2595,
+      "eval_samples_per_second": 22.462,
+      "eval_steps_per_second": 11.231,
       "step": 1
+    },
+    {
+      "epoch": 0.002658160552897395,
+      "grad_norm": 2.5087876319885254,
+      "learning_rate": 5e-05,
+      "loss": 2.9129,
+      "step": 5
+    },
+    {
+      "epoch": 0.00531632110579479,
+      "grad_norm": 3.172278881072998,
+      "learning_rate": 0.0001,
+      "loss": 2.5148,
+      "step": 10
+    },
+    {
+      "epoch": 0.00531632110579479,
+      "eval_loss": 2.32590651512146,
+      "eval_runtime": 26.5891,
+      "eval_samples_per_second": 29.787,
+      "eval_steps_per_second": 14.893,
+      "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": 31638725591040.0,
+  "total_flos": 411303432683520.0,
   "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:e841a20dbf7c609ec9ef01f3ef7edc315f8657c2f220a76e5e93cabdd248b1b3
+oid sha256:4d8014bdbf365b7c80c19de9c9ffd0ae1c588b167a2374fea0ff34c2127a39f0
 size 6776