Training in progress, step 26, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:754e79ac0a25ca628ae7492b9f00401f90e3ca6a838be9e38633036de7652e27
+oid sha256:1b43c6db8d3f53ea7e1a54e84276982456a29d2a3f247b9ce7c3ebc85addad35
 size 59933632

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:18c530f406c1699a02ff926bcbd9fb3b5ef0482541bc62b27f97dcbc4310b6d2
+oid sha256:8e6e61a1da58f243bbc90eaedd530e5cc4b2b65f2e7884bd583348abf33859ec
 size 31822948

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c5e599ebf8c42bf4256978eb4e60b65fa52201162f66abf71b04010cf02aa5e2
+oid sha256:728673b92976f39bdf8edc770560e4ef6b61c1c501931d83ff4d3bf638d48bfb
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4395bafb1cf8adc0d9dbfe550d1b98763496e37a8fadb76c1ca1168a4a757f4e
+oid sha256:37841e69eda911caeb33edeefa0b2f140e72dcce247aeb757b2fe89c00d7887b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.003266126499591734,
+  "epoch": 0.006532252999183468,
   "eval_steps": 10,
-  "global_step": 13,
+  "global_step": 26,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -37,6 +37,35 @@
       "eval_samples_per_second": 20.659,
       "eval_steps_per_second": 10.33,
       "step": 10
+    },
+    {
+      "epoch": 0.003768607499528924,
+      "grad_norm": 2.178535223007202,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 2.4068,
+      "step": 15
+    },
+    {
+      "epoch": 0.0050248099993718985,
+      "grad_norm": 1.5113375186920166,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 1.7782,
+      "step": 20
+    },
+    {
+      "epoch": 0.0050248099993718985,
+      "eval_loss": 1.6192883253097534,
+      "eval_runtime": 80.9839,
+      "eval_samples_per_second": 20.695,
+      "eval_steps_per_second": 10.348,
+      "step": 20
+    },
+    {
+      "epoch": 0.006281012499214873,
+      "grad_norm": 1.503976583480835,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 1.5467,
+      "step": 25
     }
   ],
   "logging_steps": 5,
@@ -56,7 +85,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 891288626921472.0,
+  "total_flos": 1782577253842944.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null