Training in progress, step 26, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:474623393d054bda57a3fb00afe0660c46ded34c58ed4143e5ac3f51d66a3e67
+oid sha256:2ad7f84e3be9654e3968416bcf77f5795cfc6663ed4ecf8d97aea719f1014ac3
 size 125040

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e114a67525756350ed32d4254f694e4e94834b57548caa333beaa569b73fef61
+oid sha256:d797564cfe36d5a8e5e2a7ef04fcc40bd270aac7d1c7bbd789d46518f4d3e82c
 size 162868

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b65d909e6c6ee30cc3f6c3c7041369a7088779e6cd2c5df217fb6454aed7be9
+oid sha256:030366ecd534e5c7d874a2dcbb20dba0fb2725644a4e3205f2b4330090ba3d65
 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": 0.04797047970479705,
+  "epoch": 0.0959409594095941,
   "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": 130.758,
       "eval_steps_per_second": 65.947,
       "step": 10
+    },
+    {
+      "epoch": 0.055350553505535055,
+      "grad_norm": 2.504798650741577,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 44.5843,
+      "step": 15
+    },
+    {
+      "epoch": 0.07380073800738007,
+      "grad_norm": 2.633497714996338,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 44.4848,
+      "step": 20
+    },
+    {
+      "epoch": 0.07380073800738007,
+      "eval_loss": 11.102351188659668,
+      "eval_runtime": 0.9003,
+      "eval_samples_per_second": 127.733,
+      "eval_steps_per_second": 64.422,
+      "step": 20
+    },
+    {
+      "epoch": 0.09225092250922509,
+      "grad_norm": 2.813123941421509,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 44.3679,
+      "step": 25
     }
   ],
   "logging_steps": 5,
@@ -56,7 +85,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 248353652736.0,
+  "total_flos": 499118505984.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null