Training in progress, step 26, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:18aa78924e67e8eff3809cb80bcfd36c2c02a48c0d478250290e6b84a5572d45
+oid sha256:b880a184c4b04bc678e53bbf358924422452dc97f75d7ae32a75c79e9015a003
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9eda4c364bd4b46d82a0bfb1012318348c8d89e095214bab303bfa99eaf80b14
+oid sha256:1afbb236dd0b36fd18bb377c5d63f3411c33a7c8cd753c0207fd10be18f3c0ad
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d04ce38a4b1ebe155394d1cb2e43ba46dcd389805a0df7f2671ac2a395b23d6c
+oid sha256:376a84af6354b555ba2fbd8c3fc92d9086d0a9dcf2c9793e8d456dbd561d4eb5
 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": 0.04757548032936871,
+  "epoch": 0.09515096065873742,
   "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": 16.539,
       "eval_steps_per_second": 8.341,
       "step": 10
+    },
+    {
+      "epoch": 0.05489478499542543,
+      "grad_norm": 2.1512739658355713,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 0.9735,
+      "step": 15
+    },
+    {
+      "epoch": 0.07319304666056725,
+      "grad_norm": 1.4982128143310547,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 0.6925,
+      "step": 20
+    },
+    {
+      "epoch": 0.07319304666056725,
+      "eval_loss": 0.7363909482955933,
+      "eval_runtime": 6.9844,
+      "eval_samples_per_second": 16.465,
+      "eval_steps_per_second": 8.304,
+      "step": 20
+    },
+    {
+      "epoch": 0.09149130832570906,
+      "grad_norm": 0.9344391822814941,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 0.7451,
+      "step": 25
     }
   ],
   "logging_steps": 5,
@@ -56,7 +85,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2142169800376320.0,
+  "total_flos": 4284339600752640.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null