Training in progress, step 1600, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:41ea76cfeff3db5ec080f6dac2bd1015632c1bf724ab862beb0032adf75f2848
+oid sha256:aa5544e8b843bb22fe057445b7a7d9249cad55a71318c53cbdc55a20896f65b4
 size 83945744

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d6b273936a4f9bb25afd3dcc095bcc3dbb97c2cbf55103a2aae493471237620e
+oid sha256:234f4fd259bcf99f33ee62834529e6367d52546617b6cf32a9ae5e44018385ed
 size 85729445

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2eaf64e23e07990b7534832ea49f6fb31a6f2c1c2f467496c06fc98c1b19f946
+oid sha256:49c2f3088d52418115251fd954b3c4ca35bb880e942bbc4886a3407596d2a063
 size 14645

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6aed333aef95ba59dcee33c0aacc5b43b270ef2a5b48928d9d851bc67ccf67bd
+oid sha256:9810969be7a7dac5a80de1f6ccc386ed23c334c28269980ab137cd90306211a8
 size 1465

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.6198014616966248,
-  "best_model_checkpoint": "./learnhub-checkpoints/checkpoint-1500",
-  "epoch": 1.1907927373747396,
+  "best_metric": 0.6075525879859924,
+  "best_model_checkpoint": "./learnhub-checkpoints/checkpoint-1600",
+  "epoch": 1.270165691040778,
   "eval_steps": 100,
-  "global_step": 1500,
+  "global_step": 1600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -547,6 +547,42 @@
       "eval_samples_per_second": 1.344,
       "eval_steps_per_second": 0.673,
       "step": 1500
+    },
+    {
+      "epoch": 1.210635975791249,
+      "grad_norm": 12.2265625,
+      "learning_rate": 0.00013459867967556438,
+      "loss": 3.6093,
+      "step": 1525
+    },
+    {
+      "epoch": 1.2304792142077587,
+      "grad_norm": 12.3203125,
+      "learning_rate": 0.00013258688346494548,
+      "loss": 3.8902,
+      "step": 1550
+    },
+    {
+      "epoch": 1.2503224526242682,
+      "grad_norm": 8.625,
+      "learning_rate": 0.00013056022040915335,
+      "loss": 3.7301,
+      "step": 1575
+    },
+    {
+      "epoch": 1.270165691040778,
+      "grad_norm": 12.0234375,
+      "learning_rate": 0.0001285196151159647,
+      "loss": 3.676,
+      "step": 1600
+    },
+    {
+      "epoch": 1.270165691040778,
+      "eval_loss": 0.6075525879859924,
+      "eval_runtime": 789.4497,
+      "eval_samples_per_second": 1.344,
+      "eval_steps_per_second": 0.673,
+      "step": 1600
     }
   ],
   "logging_steps": 25,
@@ -566,7 +602,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.4682274343082394e+17,
+  "total_flos": 1.567975348809892e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null