Training in progress, step 26, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3929b36fa3f4584ad167eca2cb0c957cffc064cf502fa34c284076a4950ed664
+oid sha256:9ff24869e004bb06778f5a665aa7c187094da7a56bb87a63414f523e93328931
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:51f77a0dd66df3e8fb3035510c95887bc0585b607925b396cd9ff785d20b1974
+oid sha256:07148ff123d7cd6231245d96093d9bcfdb9904fa31e6ae33997b9f4f1a2cd864
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b8d3b0cd38ff8c140a46f8cd6b0fb2611ad2c4ebd59d9733c17b98b72f21091
+oid sha256:66d743f7d7f1e483fc21966690f23e79e8c531a6f00323f193d4a604fb0e9d14
 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": 0.023444544634806132,
+  "epoch": 0.046889089269612265,
   "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": 14.966,
       "eval_steps_per_second": 7.483,
       "step": 10
+    },
+    {
+      "epoch": 0.027051397655545536,
+      "grad_norm": 6.852028846740723,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 4.7056,
+      "step": 15
+    },
+    {
+      "epoch": 0.03606853020739405,
+      "grad_norm": 5.969870090484619,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 4.1946,
+      "step": 20
+    },
+    {
+      "epoch": 0.03606853020739405,
+      "eval_loss": 1.0455502271652222,
+      "eval_runtime": 15.6064,
+      "eval_samples_per_second": 14.994,
+      "eval_steps_per_second": 7.497,
+      "step": 20
+    },
+    {
+      "epoch": 0.04508566275924256,
+      "grad_norm": 6.2113494873046875,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 4.0385,
+      "step": 25
     }
   ],
   "logging_steps": 5,
@@ -56,7 +85,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2322290133958656.0,
+  "total_flos": 4644580267917312.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null