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:fc207a8bd4038c692068f833fc6f9e967ba4e2bc59cf8d516cc32219394ec6d2
+oid sha256:dcd807fd7345bb1a541b7d0a81bdaf15e088d087b5360c8cf62ae18d92887c18
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:993f8e074b692e7a455d207b00d26f388597f4b75884cc4631061f4836c0ed05
+oid sha256:2954f5ba9212954b225d6e67257480904c0b68d8a9081fce18c09bc363e423d8
 size 85723284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f18766532b6e2882509ec1f9d4c5626424fb37a927a1f0bde7350de9aa0a4a72
+oid sha256:6d9dad472c625544a84029492c20e55a11e0b1a437d7c0f61ccb13f356134a19
 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": 0.0003757209145047059,
+  "epoch": 0.0007514418290094118,
   "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": 2.842,
       "step": 5
+    },
+    {
+      "epoch": 0.0004508650974056471,
+      "grad_norm": 1.4646281003952026,
+      "learning_rate": 0.00012,
+      "loss": 2.6919,
+      "step": 6
+    },
+    {
+      "epoch": 0.0004508650974056471,
+      "eval_loss": 2.8418965339660645,
+      "eval_runtime": 3637.025,
+      "eval_samples_per_second": 1.541,
+      "eval_steps_per_second": 0.77,
+      "step": 6
+    },
+    {
+      "epoch": 0.0005260092803065883,
+      "grad_norm": 0.9931614398956299,
+      "learning_rate": 0.00014,
+      "loss": 2.9339,
+      "step": 7
+    },
+    {
+      "epoch": 0.0006011534632075294,
+      "grad_norm": 1.1760421991348267,
+      "learning_rate": 0.00016,
+      "loss": 3.062,
+      "step": 8
+    },
+    {
+      "epoch": 0.0006762976461084706,
+      "grad_norm": 1.3243894577026367,
+      "learning_rate": 0.00018,
+      "loss": 2.492,
+      "step": 9
+    },
+    {
+      "epoch": 0.0006762976461084706,
+      "eval_loss": 2.708946943283081,
+      "eval_runtime": 3636.5404,
+      "eval_samples_per_second": 1.541,
+      "eval_steps_per_second": 0.771,
+      "step": 9
+    },
+    {
+      "epoch": 0.0007514418290094118,
+      "grad_norm": 1.3067790269851685,
+      "learning_rate": 0.0002,
+      "loss": 2.8701,
+      "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": 7418872835604480.0,
+  "total_flos": 1.483774567120896e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null