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:b0525a7724bc160a70baeb0e7333eac9b654ff50a7c18e5e1eecbddcd5e9badb
+oid sha256:d6b803c46a19a7d6d161fdaca065c16fb3570285c05d72f7359c2b0cef4e185a
 size 125040

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:30d210fa7e89f5c6871ddd0b19ccacfb0e12070f7db5a1efb6579b1d99f5305f
+oid sha256:f9ed7b08b52e85267318a417f479d249bd0384e9f9e2b0b9ce87c741d89c74fc
 size 162868

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a38e8a836923abb82b8cc9c01aa2e85798ae88c87203128021c0d28b374f9d7d
+oid sha256:913a7368968d4008e86629febfbb08ed71c049260fa617734b65bfe139c8dfd8
 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": 0.0015997046699070942,
+  "epoch": 0.0031994093398141884,
   "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": 164.54,
       "eval_steps_per_second": 82.27,
       "step": 10
+    },
+    {
+      "epoch": 0.0018458130806620317,
+      "grad_norm": 0.9184021949768066,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 44.4177,
+      "step": 15
+    },
+    {
+      "epoch": 0.0024610841075493753,
+      "grad_norm": 1.0864630937576294,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 44.3678,
+      "step": 20
+    },
+    {
+      "epoch": 0.0024610841075493753,
+      "eval_loss": 11.091269493103027,
+      "eval_runtime": 20.9913,
+      "eval_samples_per_second": 163.02,
+      "eval_steps_per_second": 81.51,
+      "step": 20
+    },
+    {
+      "epoch": 0.0030763551344367194,
+      "grad_norm": 1.3032631874084473,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 44.3418,
+      "step": 25
     }
   ],
   "logging_steps": 5,
@@ -56,7 +85,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 173606436864.0,
+  "total_flos": 330334470144.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null