Training in progress, step 45, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:518eeb37dc41a36ebad929aecc555b3b20b2d55ee872c04b7ce10ab80ff8262f
+oid sha256:5e61aa843e4037b8ee53d96d3783033834bdf2cf8de150565235aab74aed225e
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ef4da850d3b4d589bb7bd634eca0700249327960725229871425b601815c93e
+oid sha256:dd54e2017c67a410abb48b02b3e58f3ee4d89a5c1dd8da26dd2b19c0b0a86820
 size 85723284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:41542bf364e876cca9839cdc695a83541c313b7d3530ba38b92062734dc74977
+oid sha256:14719ed3112f3e5b130f8afa264745103a34f5c0bb6a80b06bc68acfa79da1b2
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b09cef78339a08679f2a6cf4a4b56eca3094fb6b859867afd839be3db1415460
+oid sha256:0896677f34f08366c4c71a3f69133212afc490296ec7ee225b8aefde1f38f24c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.9473684210526315,
+  "epoch": 1.1842105263157894,
   "eval_steps": 9,
-  "global_step": 36,
+  "global_step": 45,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -131,6 +131,35 @@
       "eval_samples_per_second": 14.038,
       "eval_steps_per_second": 1.755,
       "step": 36
+    },
+    {
+      "epoch": 1.0263157894736843,
+      "grad_norm": 6.43715238571167,
+      "learning_rate": 7.649596321166024e-05,
+      "loss": 3.1494,
+      "step": 39
+    },
+    {
+      "epoch": 1.1052631578947367,
+      "grad_norm": 8.016036033630371,
+      "learning_rate": 7.191855733945387e-05,
+      "loss": 2.5075,
+      "step": 42
+    },
+    {
+      "epoch": 1.1842105263157894,
+      "grad_norm": 6.886407375335693,
+      "learning_rate": 6.710100716628344e-05,
+      "loss": 2.4376,
+      "step": 45
+    },
+    {
+      "epoch": 1.1842105263157894,
+      "eval_loss": 0.7812040448188782,
+      "eval_runtime": 4.5624,
+      "eval_samples_per_second": 14.028,
+      "eval_steps_per_second": 1.753,
+      "step": 45
     }
   ],
   "logging_steps": 3,
@@ -150,7 +179,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.062538188711526e+16,
+  "total_flos": 6.297410785089946e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null