Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,12 +20,12 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "down_proj",
-    "k_proj",
-    "gate_proj",
-    "o_proj",
     "up_proj",
     "v_proj",
+    "o_proj",
+    "gate_proj",
+    "k_proj",
+    "down_proj",
     "q_proj"
   ],
   "task_type": "CAUSAL_LM",

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da7a7bfa3c9e322c18f110a1dd21f7919c4e2959c2fa1b459904044f9946a0a8
+oid sha256:3decbfe26592e2f286b5bcd9c4c1af9b20ea6371df03562497196646bb1adb0e
 size 30026872

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3722569925c9a26ca6bd9d0a34b2e3cee883cb8e9cae7a6c78947c515a35018b
+oid sha256:3c900a16fad33c9fef92637cba3931a3e3ca35876802dfe04a6efac2b5308f37
 size 15611412

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:81b0fa30ce7d6caf58ef5c2227062e5ee5947fe33564486703caa8d601663ea6
+oid sha256:7a2043fcab6393039914b1ae1d41f0b06c9cc65053e1770339d2cdf1b4d4fcd1
 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": 26.5875,
-      "eval_samples_per_second": 29.788,
-      "eval_steps_per_second": 14.894,
+      "eval_runtime": 27.1784,
+      "eval_samples_per_second": 29.141,
+      "eval_steps_per_second": 14.57,
       "step": 1
+    },
+    {
+      "epoch": 0.002658160552897395,
+      "grad_norm": 2.700984477996826,
+      "learning_rate": 5e-05,
+      "loss": 2.9154,
+      "step": 5
+    },
+    {
+      "epoch": 0.00531632110579479,
+      "grad_norm": 3.27529239654541,
+      "learning_rate": 0.0001,
+      "loss": 2.508,
+      "step": 10
+    },
+    {
+      "epoch": 0.00531632110579479,
+      "eval_loss": 2.311734199523926,
+      "eval_runtime": 27.2171,
+      "eval_samples_per_second": 29.099,
+      "eval_steps_per_second": 14.55,
+      "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 sha256:91f112afae4e2301bbefc56d64d917f6205e0d3af916c3d8ee71db3d6b725c73
+oid sha256:df5e85d7753aa2393221f39eb2c23545d4497298cc6c925ff37297ba1717bff6
 size 6776