Training in progress, step 81, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e6247673fbb13d32a81bff2d80b19b59edad902a4e88a7e900df9794a39b0da
+oid sha256:15abefa67a14818f3e0d3d9f5e641bec8c109e1f83be5dfe8271ac0f626c9a8a
 size 72396376

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:30e35d30aaa973be10cf314a0ba1b99916d0547fe6ca30fd780a200110e9cb2c
+oid sha256:34dbeb7b04207119cff9fe0cdbd03f36ef68c5fd32ddae91bb2dcdadc4860989
 size 37134420

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d60207f033c3688522020da43c4c7c18a66d95617d4c8a64c7cbf2e7ecb93ac9
+oid sha256:bd3c8778f78fc6ec9d991fdcfb271264180badfb60aa8044c4b1f7eca4abe20a
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d899e046e5eb8fee9b81979db8db7b88d6dc92f30a13d049b906f3a3be1dfc0f
+oid sha256:bec84b33191b76a1f66109f05ca2863b65ba9c0ae66be6a4921ad95ad9f1a38e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.7024390243902439,
+  "epoch": 0.7902439024390244,
   "eval_steps": 9,
-  "global_step": 72,
+  "global_step": 81,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -247,6 +247,35 @@
       "eval_samples_per_second": 35.456,
       "eval_steps_per_second": 4.509,
       "step": 72
+    },
+    {
+      "epoch": 0.7317073170731707,
+      "grad_norm": 0.2799305021762848,
+      "learning_rate": 8.930309757836517e-06,
+      "loss": 2.6651,
+      "step": 75
+    },
+    {
+      "epoch": 0.7609756097560976,
+      "grad_norm": 0.24884013831615448,
+      "learning_rate": 7.016504991533726e-06,
+      "loss": 3.0048,
+      "step": 78
+    },
+    {
+      "epoch": 0.7902439024390244,
+      "grad_norm": 0.3715744614601135,
+      "learning_rate": 5.299731159831953e-06,
+      "loss": 2.8045,
+      "step": 81
+    },
+    {
+      "epoch": 0.7902439024390244,
+      "eval_loss": 2.8328237533569336,
+      "eval_runtime": 4.8668,
+      "eval_samples_per_second": 35.547,
+      "eval_steps_per_second": 4.52,
+      "step": 81
     }
   ],
   "logging_steps": 3,
@@ -266,7 +295,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.449800134708429e+16,
+  "total_flos": 2.7460177980555264e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null