Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:391d55d57acb750c15b465b9f558c23ad6f9e99edd97d732a364ddf782f6ed5f
+oid sha256:7058d2d28f94132f811065a11eccfe0e87ab97817242e51576d7d894b42d34c5
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e9e9bcd8e547c5fce939f0d86c8df7d6b70cb2a5c16b8245fbf41f788e8665e
+oid sha256:34a8fcd8247048abdffc77226ad646a77dc686037c052ace6e1989da6cbe9a24
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d0bfe6bce92ea49444f53b004ed4a13b63bcfc0a70e5e57d8586c0c2d90b519
+oid sha256:5bdac87cf390cb72252ff25e1e6d2db6b4f49d909074ff854f1cf9f55613c368
 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": 0.014545454545454545,
+  "epoch": 0.02909090909090909,
   "eval_steps": 8,
-  "global_step": 10,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -44,6 +44,35 @@
       "learning_rate": 0.00018,
       "loss": 0.2196,
       "step": 9
+    },
+    {
+      "epoch": 0.017454545454545455,
+      "grad_norm": 0.9977229833602905,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 0.0874,
+      "step": 12
+    },
+    {
+      "epoch": 0.02181818181818182,
+      "grad_norm": 0.52955162525177,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 0.075,
+      "step": 15
+    },
+    {
+      "epoch": 0.02327272727272727,
+      "eval_loss": 0.07141619920730591,
+      "eval_runtime": 37.4915,
+      "eval_samples_per_second": 7.735,
+      "eval_steps_per_second": 3.868,
+      "step": 16
+    },
+    {
+      "epoch": 0.02618181818181818,
+      "grad_norm": 0.4917963147163391,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 0.0604,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3709436417802240.0,
+  "total_flos": 7418872835604480.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null