Training in progress, step 170, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fcdf10964fbea563f7585add757a1eded783fdea527b5b19c6c581195c5c3eb6
+oid sha256:a75b8b4f060b70b4acbf15e2810188aa5e77f7b80896679941436511f37eca44
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d9ce8f5d2c229bb84c86a6f32a33598b0f8c59ea40233c2dca6776e522db316
+oid sha256:f67b104ef782f97707a79c624761edded35f0157553358c6b27c9b692cd99a3e
 size 81730196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8376b1a21f60d7891b89de2e0d8b9ab5dc44b12e00ba3ecc733ed71c6230518d
+oid sha256:03056d1c4ca5ebbca3689312a90ecc3659af7e67511e12c82f70b630038ea234
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d99dc7a150ff6ed818c8735e9e9061e757b4b841b8d74bde2c9d7a2195ff136
+oid sha256:fab1f30942a5e2bb9a9e5cc3477ef48cdcd39a7b78f8a45a46db0926bdbf2b4f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.03926852743022137,
+  "epoch": 0.04363169714469041,
   "eval_steps": 17,
-  "global_step": 153,
+  "global_step": 170,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -444,6 +444,49 @@
       "eval_samples_per_second": 13.28,
       "eval_steps_per_second": 1.661,
       "step": 153
+    },
+    {
+      "epoch": 0.04003849855630414,
+      "grad_norm": 0.415403813123703,
+      "learning_rate": 1.2658926150792322e-05,
+      "loss": 2.3245,
+      "step": 156
+    },
+    {
+      "epoch": 0.04080846968238691,
+      "grad_norm": 0.37216442823410034,
+      "learning_rate": 1.1056136061894384e-05,
+      "loss": 2.2985,
+      "step": 159
+    },
+    {
+      "epoch": 0.04157844080846968,
+      "grad_norm": 0.3392238914966583,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 2.2315,
+      "step": 162
+    },
+    {
+      "epoch": 0.04234841193455245,
+      "grad_norm": 0.3757283091545105,
+      "learning_rate": 8.141676086873572e-06,
+      "loss": 2.2423,
+      "step": 165
+    },
+    {
+      "epoch": 0.04311838306063523,
+      "grad_norm": 0.3205427825450897,
+      "learning_rate": 6.837175952121306e-06,
+      "loss": 2.3192,
+      "step": 168
+    },
+    {
+      "epoch": 0.04363169714469041,
+      "eval_loss": 2.2842438220977783,
+      "eval_runtime": 494.3736,
+      "eval_samples_per_second": 13.275,
+      "eval_steps_per_second": 1.661,
+      "step": 170
     }
   ],
   "logging_steps": 3,
@@ -463,7 +506,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.2578649349750784e+17,
+  "total_flos": 2.528149496534139e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null