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:eb72553886d5a34b7e86ee350fc261e3921408e0849b326f96d637d866fa74e5
+oid sha256:9c044ad24f64811e7e9d002c8785c4a10cf1c78ad84f3ce3da3566724ddc990f
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5390b689c25e5dd48b5dfb83f352934ec035836e2e6300d303bb627d60150b5b
+oid sha256:2e160377d93be8152262233694e21b044fd901605fe9c2d7398acb65dec2e1fb
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f2a3d0f18704952f5e489fd373140093b1ec2232d5123df9941b8b0ec34244b4
+oid sha256:8b570b00f34d984a8ff70fdd1635ce7dfd6c51893e39ea8378d8527c6c675850
 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": 0.007389512576381981,
+  "epoch": 0.014779025152763962,
   "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": 13.525,
       "eval_steps_per_second": 6.772,
       "step": 10
+    },
+    {
+      "epoch": 0.008526360665056132,
+      "grad_norm": 0.7104833722114563,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 1.8415,
+      "step": 15
+    },
+    {
+      "epoch": 0.011368480886741509,
+      "grad_norm": 0.6715155243873596,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 1.3906,
+      "step": 20
+    },
+    {
+      "epoch": 0.011368480886741509,
+      "eval_loss": 1.5854151248931885,
+      "eval_runtime": 54.9652,
+      "eval_samples_per_second": 13.481,
+      "eval_steps_per_second": 6.75,
+      "step": 20
+    },
+    {
+      "epoch": 0.014210601108426887,
+      "grad_norm": 0.6591376662254333,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 1.7109,
+      "step": 25
     }
   ],
   "logging_steps": 5,
@@ -56,7 +85,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2677712250470400.0,
+  "total_flos": 5314228927856640.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null