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:b29f1013f41f0e0c06dec8c213eb2ce9d8af88c7fffce07a76fe784a12f3cf8b
+oid sha256:5b250f3f86e9fc4188517cc5c1c93eed89c0e7db7704f66861fc5b241becbe2a
 size 59933632

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dd06243d848f92832f8a3e527e7f47cee960b501f7e3db01eb514e798ad38604
+oid sha256:54fa12cc9eec219b1c4b82fb4e3a3c1f1af8f96339bf6dafc1dcd484b6afdce9
 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": 0.0014078405891271388,
+  "epoch": 0.0028156811782542777,
   "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": 20.437,
       "eval_steps_per_second": 10.218,
       "step": 10
+    },
+    {
+      "epoch": 0.0016244314489928524,
+      "grad_norm": 2.1008031368255615,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 1.7914,
+      "step": 15
+    },
+    {
+      "epoch": 0.0021659085986571367,
+      "grad_norm": 2.6695444583892822,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 1.6153,
+      "step": 20
+    },
+    {
+      "epoch": 0.0021659085986571367,
+      "eval_loss": 1.4342576265335083,
+      "eval_runtime": 187.0504,
+      "eval_samples_per_second": 20.786,
+      "eval_steps_per_second": 10.393,
+      "step": 20
+    },
+    {
+      "epoch": 0.002707385748321421,
+      "grad_norm": 2.947023868560791,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 1.366,
+      "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