Training in progress, step 36, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b55c47a2b7a7b9aeaa173c3680233ca19ec21eb684822083cc61c8e48977c6f4
+oid sha256:518eeb37dc41a36ebad929aecc555b3b20b2d55ee872c04b7ce10ab80ff8262f
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a9c87084845a7bde79f186cf69f4586abb381161216d0d7f9170fdfa8c8ab81
+oid sha256:5ef4da850d3b4d589bb7bd634eca0700249327960725229871425b601815c93e
 size 85723284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8bf854e2224a3391d13faa8e70a45247278e5b5c6446bfa9d1cafaeebfaca359
+oid sha256:41542bf364e876cca9839cdc695a83541c313b7d3530ba38b92062734dc74977
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd4a07944f7914b974e23583756a2e0907223f4627a9b1ba247bd8f732140689
+oid sha256:b09cef78339a08679f2a6cf4a4b56eca3094fb6b859867afd839be3db1415460
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.7105263157894737,
+  "epoch": 0.9473684210526315,
   "eval_steps": 9,
-  "global_step": 27,
+  "global_step": 36,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -102,6 +102,35 @@
       "eval_samples_per_second": 14.015,
       "eval_steps_per_second": 1.752,
       "step": 27
+    },
+    {
+      "epoch": 0.7894736842105263,
+      "grad_norm": 9.123873710632324,
+      "learning_rate": 8.83022221559489e-05,
+      "loss": 3.727,
+      "step": 30
+    },
+    {
+      "epoch": 0.868421052631579,
+      "grad_norm": 9.119816780090332,
+      "learning_rate": 8.473291852294987e-05,
+      "loss": 3.2364,
+      "step": 33
+    },
+    {
+      "epoch": 0.9473684210526315,
+      "grad_norm": 9.756755828857422,
+      "learning_rate": 8.07830737662829e-05,
+      "loss": 3.4796,
+      "step": 36
+    },
+    {
+      "epoch": 0.9473684210526315,
+      "eval_loss": 0.7768706679344177,
+      "eval_runtime": 4.5592,
+      "eval_samples_per_second": 14.038,
+      "eval_steps_per_second": 1.755,
+      "step": 36
     }
   ],
   "logging_steps": 3,
@@ -121,7 +150,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.796903641533645e+16,
+  "total_flos": 5.062538188711526e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null