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:c26dbdcce0564db1e75e6eb0b1c8bdda8cadf7c1cfd196a0e6e8af5c763ac618
+oid sha256:8f77962b4c1f885dd32638297d162f5fbb1ea3e4ee514cdc0141bcc71937d0e9
 size 25271744

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8e10cae68928eeb8003c596f9c890ad56a41b36e82868e4476ac09368d6a9b92
+oid sha256:db2941425babf3bba3cfff555739b500bfb55c9015620a762dcc258a2f96c7de
 size 13685516

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7827bfc587d2b093f2fbabab8eafd8d5b11c8b91fe605dbe58f63e7b6b5350c
+oid sha256:a66ada259260869481e778bff01664524ba6c2c0487bad481b74d64a06cf7bc3
 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": 0.002113305697797285,
+  "epoch": 0.00422661139559457,
   "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": 34.735,
       "eval_steps_per_second": 17.374,
       "step": 10
+    },
+    {
+      "epoch": 0.00243842965130456,
+      "grad_norm": 0.2008397877216339,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 1.6315,
+      "step": 15
+    },
+    {
+      "epoch": 0.0032512395350727465,
+      "grad_norm": 0.17129330337047577,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 1.6642,
+      "step": 20
+    },
+    {
+      "epoch": 0.0032512395350727465,
+      "eval_loss": 1.6372413635253906,
+      "eval_runtime": 74.7542,
+      "eval_samples_per_second": 34.66,
+      "eval_steps_per_second": 17.337,
+      "step": 20
+    },
+    {
+      "epoch": 0.004064049418840933,
+      "grad_norm": 0.20447033643722534,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 1.5578,
+      "step": 25
     }
   ],
   "logging_steps": 5,
@@ -56,7 +85,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 402872365744128.0,
+  "total_flos": 831323929313280.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null