Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:260ab2feaefffd044780a9824981ddd1fcd7c98839be7f4c48be01c51519f4e3
+oid sha256:f1b77689a6cde7f75bf4f99375c45b8c7688aafe58eb10d31805e35b8634d8bd
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e365bc614ecce97bb0fde8680c8e2d9873d82dc1040211f8c28cf32d42ad6b89
+oid sha256:d66125b26e495b6ea157c6181b6059f97531ce35c5aa65a1de3afcfd7fc1a950
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e808f8be761b6379f6b579470974aeba301a5195fb0cc05d669c223600735635
+oid sha256:932707f129ea69f2e2941d44be32926194674e9ebb55b53e0716f8cc16fcc097
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cda2d7da3ce8a95be6df505b84eace6ccd5aa18ffc6d1bcc9a79572045c8d78f
+oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.003352329869259135,
+  "epoch": 0.00670465973851827,
   "eval_steps": 3,
-  "global_step": 5,
+  "global_step": 10,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -58,6 +58,57 @@
       "learning_rate": 0.0001,
       "loss": 4.8356,
       "step": 5
+    },
+    {
+      "epoch": 0.004022795843110962,
+      "grad_norm": 3.3904759883880615,
+      "learning_rate": 0.00012,
+      "loss": 4.3142,
+      "step": 6
+    },
+    {
+      "epoch": 0.004022795843110962,
+      "eval_loss": 4.290420055389404,
+      "eval_runtime": 52.7807,
+      "eval_samples_per_second": 11.898,
+      "eval_steps_per_second": 5.949,
+      "step": 6
+    },
+    {
+      "epoch": 0.004693261816962789,
+      "grad_norm": 3.2405154705047607,
+      "learning_rate": 0.00014,
+      "loss": 4.1384,
+      "step": 7
+    },
+    {
+      "epoch": 0.0053637277908146165,
+      "grad_norm": 3.9647226333618164,
+      "learning_rate": 0.00016,
+      "loss": 3.543,
+      "step": 8
+    },
+    {
+      "epoch": 0.006034193764666443,
+      "grad_norm": 4.046013832092285,
+      "learning_rate": 0.00018,
+      "loss": 3.4731,
+      "step": 9
+    },
+    {
+      "epoch": 0.006034193764666443,
+      "eval_loss": 3.0233943462371826,
+      "eval_runtime": 52.9098,
+      "eval_samples_per_second": 11.869,
+      "eval_steps_per_second": 5.935,
+      "step": 9
+    },
+    {
+      "epoch": 0.00670465973851827,
+      "grad_norm": 2.753418207168579,
+      "learning_rate": 0.0002,
+      "loss": 2.7829,
+      "step": 10
     }
   ],
   "logging_steps": 1,
@@ -72,12 +123,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1849564248145920.0,
+  "total_flos": 3699128496291840.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null