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:cbe214c6aaf6fed97284f88da304bdde2b4e5c801787fad0f68994be4f58112f
+oid sha256:8d7d3ea1e097e035a423006a65fb5ea733859c16d8b4a7b16d9f525decd73f6a
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:822aae55e393e64e4071c08b34aae48fcb17bf111fd374a1ae0280a8a85a66fe
+oid sha256:3df3ded4d29b49102fae0ae3a449a5024f7ca0c73636f8769ee21e020273c29c
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ef568c15d3a92fad74ef5f86ffe7330da3a1446a29e6310725eb6a237745116
+oid sha256:0b65f1a0fab783030b9678af169570889794fb3146a39ba3945282029a965db4
 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": 0.00022732041687067216,
+  "epoch": 0.0004546408337413443,
   "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": 7.495,
       "eval_steps_per_second": 3.747,
       "step": 10
+    },
+    {
+      "epoch": 0.00026229278869692945,
+      "grad_norm": 6.702174663543701,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 3.4858,
+      "step": 15
+    },
+    {
+      "epoch": 0.00034972371826257255,
+      "grad_norm": 8.694743156433105,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 2.7742,
+      "step": 20
+    },
+    {
+      "epoch": 0.00034972371826257255,
+      "eval_loss": 2.695681095123291,
+      "eval_runtime": 3204.8183,
+      "eval_samples_per_second": 7.514,
+      "eval_steps_per_second": 3.757,
+      "step": 20
+    },
+    {
+      "epoch": 0.0004371546478282157,
+      "grad_norm": 5.783470153808594,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 2.3363,
+      "step": 25
     }
   ],
   "logging_steps": 5,
@@ -56,7 +85,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3514172071477248.0,
+  "total_flos": 6935865930547200.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null