Training in progress, step 45, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f4ef18667cb45fc42a9bd8331414640f5fef275137ef4fdde8a461d57fc4257
+oid sha256:8a1019f64c8b0eead118129c935f4115736c38cd10518de1788c926aadce9bc4
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16caa162391e5d2cd2758fafe671b8da923fb0c5d6b9b102fe7ebabe09ac3e3d
+oid sha256:8f900bf56433149b0488645dbcdbffa1945104d5372cd826591675ecda329d2d
 size 43122580

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:b09cef78339a08679f2a6cf4a4b56eca3094fb6b859867afd839be3db1415460
+oid sha256:0896677f34f08366c4c71a3f69133212afc490296ec7ee225b8aefde1f38f24c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0415464512406232,
+  "epoch": 0.05193306405077899,
   "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": 13.959,
       "eval_steps_per_second": 1.75,
       "step": 36
+    },
+    {
+      "epoch": 0.04500865551067513,
+      "grad_norm": 4.240529537200928,
+      "learning_rate": 7.649596321166024e-05,
+      "loss": 7.9651,
+      "step": 39
+    },
+    {
+      "epoch": 0.048470859780727064,
+      "grad_norm": 4.575836658477783,
+      "learning_rate": 7.191855733945387e-05,
+      "loss": 7.7481,
+      "step": 42
+    },
+    {
+      "epoch": 0.05193306405077899,
+      "grad_norm": 4.351076126098633,
+      "learning_rate": 6.710100716628344e-05,
+      "loss": 7.9443,
+      "step": 45
+    },
+    {
+      "epoch": 0.05193306405077899,
+      "eval_loss": 1.9247784614562988,
+      "eval_runtime": 104.5498,
+      "eval_samples_per_second": 13.965,
+      "eval_steps_per_second": 1.75,
+      "step": 45
     }
   ],
   "logging_steps": 3,
@@ -150,7 +179,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.04769478173655e+16,
+  "total_flos": 6.309618477170688e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null