Training in progress, step 36, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d78737a8c5017e576aa33e636aff5f03d2c8589e058c1f920084324d1f463ff
+oid sha256:97a52fe431a560d5311d9a64985f151a2fa531bd048c2b511c3f08e72ce1c838
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e0cc9f8a7409e541fb182a96e0e76bad78892039ee8aa3c2c1b1f8945a23b8d
+oid sha256:c3eaf744600874b2e195a7407e010018a21336076b2547ff5c517626a4e4b14b
 size 85723284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0dd1a7ec32b6511f98f8fdc2427d030159b8d93f82e54abc269c1f81f1b4b37d
+oid sha256:96d6a6239cb5fe4a95ca665972d36ce7105c1f8f335d5abbdaab42e4f8ab1a8e
 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": 0.020905923344947737,
+  "epoch": 0.027874564459930314,
   "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": 11.569,
       "eval_steps_per_second": 1.446,
       "step": 27
+    },
+    {
+      "epoch": 0.023228803716608595,
+      "grad_norm": 0.6742556095123291,
+      "learning_rate": 8.83022221559489e-05,
+      "loss": 0.0237,
+      "step": 30
+    },
+    {
+      "epoch": 0.025551684088269456,
+      "grad_norm": 1.4266101121902466,
+      "learning_rate": 8.473291852294987e-05,
+      "loss": 0.0166,
+      "step": 33
+    },
+    {
+      "epoch": 0.027874564459930314,
+      "grad_norm": 1.627569556236267,
+      "learning_rate": 8.07830737662829e-05,
+      "loss": 0.0115,
+      "step": 36
+    },
+    {
+      "epoch": 0.027874564459930314,
+      "eval_loss": 0.0022949930280447006,
+      "eval_runtime": 188.026,
+      "eval_samples_per_second": 11.573,
+      "eval_steps_per_second": 1.447,
+      "step": 36
     }
   ],
   "logging_steps": 3,
@@ -121,7 +150,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.064758901551923e+16,
+  "total_flos": 6.78818380555223e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null