Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bf40113f87346c12021e945e0c266e265438183bd631d414a9b6fed46858c3f5
+oid sha256:7833b65f9775e368ae540abefe6601a13adb4876a86b9430033b2346325374ba
 size 56662952

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:95318c50056e3ae9e46870335630673bc58daacfb6dd49132438bc0057bc1bb9
+oid sha256:7626e5ff84ad5ed08221745905f62e844cd4103484193280c3a7acd5731115ec
 size 113488058

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e082fc4e6b9b8fadd83b541fdc0e698b5de384e75458be66ae44bb7606c388e
+oid sha256:46820fe379d303e4c45803e10eb9d0012220321cdf7a2c720f4ff8046cb25ef5
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
+oid sha256:a62e6ea25099651400ff4a3142a50e40bef5b52ba883be53b2fcb9d1a5b0a98c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.00029059841478564733,
+  "epoch": 0.0005811968295712947,
   "eval_steps": 5,
-  "global_step": 10,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -52,6 +52,43 @@
       "eval_samples_per_second": 27.019,
       "eval_steps_per_second": 13.51,
       "step": 10
+    },
+    {
+      "epoch": 0.0003487180977427768,
+      "grad_norm": 4.114701271057129,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 7.2808,
+      "step": 12
+    },
+    {
+      "epoch": 0.000435897622178471,
+      "grad_norm": 4.156654357910156,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 6.6025,
+      "step": 15
+    },
+    {
+      "epoch": 0.000435897622178471,
+      "eval_loss": 1.5644091367721558,
+      "eval_runtime": 537.4975,
+      "eval_samples_per_second": 26.958,
+      "eval_steps_per_second": 13.479,
+      "step": 15
+    },
+    {
+      "epoch": 0.0005230771466141652,
+      "grad_norm": 3.9214437007904053,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 6.0271,
+      "step": 18
+    },
+    {
+      "epoch": 0.0005811968295712947,
+      "eval_loss": 1.4372557401657104,
+      "eval_runtime": 535.8345,
+      "eval_samples_per_second": 27.042,
+      "eval_steps_per_second": 13.521,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -71,7 +108,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 616035463987200.0,
+  "total_flos": 1292171948851200.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null