Training in progress, step 45, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2990810779cbc06206cd62e3f42a923a4c6b5709cd9a1ec81e95930ab447bfdd
+oid sha256:40bf16924b22f9a55ccf3a973d9a23635329ce82e7066cf58401f66a6c45fdb5
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d2ec8a9130a303611186036c2b1dcb82ef44cf8cad7530685170d9e288f41d9e
+oid sha256:14c46842d1376197be77eefcc9231fcf7dc73fe7ea0dd7e6affcf0f746eafa54
 size 85723284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d74b05f2720b311440022765a28fc8006a7374957aaca6aca1b5e6bc5db4cbaa
+oid sha256:a15f8b7e107d1944aa714244b7981525070751630348b2f99259785cab9c85cb
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc389ed2ec8a0148b9b29024154a8f2f11c6a7454ef1d0724563562d03a46e01
+oid sha256:9776c8df8be516beee92201f32f4a3f5d90539bf47f8ef27e1636cdc132a851e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.010973936899862825,
+  "epoch": 0.013717421124828532,
   "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": 13.891,
       "eval_steps_per_second": 1.737,
       "step": 36
+    },
+    {
+      "epoch": 0.01188843164151806,
+      "grad_norm": 4.425464630126953,
+      "learning_rate": 3.824798160583012e-05,
+      "loss": 5.1745,
+      "step": 39
+    },
+    {
+      "epoch": 0.012802926383173296,
+      "grad_norm": 3.689208745956421,
+      "learning_rate": 3.5959278669726935e-05,
+      "loss": 4.9595,
+      "step": 42
+    },
+    {
+      "epoch": 0.013717421124828532,
+      "grad_norm": 4.085570812225342,
+      "learning_rate": 3.355050358314172e-05,
+      "loss": 5.382,
+      "step": 45
+    },
+    {
+      "epoch": 0.013717421124828532,
+      "eval_loss": 1.3172868490219116,
+      "eval_runtime": 397.5764,
+      "eval_samples_per_second": 13.897,
+      "eval_steps_per_second": 1.738,
+      "step": 45
     }
   ],
   "logging_steps": 3,
@@ -150,7 +179,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.062538188711526e+16,
+  "total_flos": 6.328172735889408e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null