Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f0dbedf1232c984bf359327ce209ef349479eff37b018ea6c00075a874a48b3
+oid sha256:e39611657e5fa84b1fc7f93563d2d33586b61f094d8161ee4310b0b746675c37
 size 45118424

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:82574828ca59fd9f2c1d71ffe72c164d4025a790a840ecbb29408f10718a9846
+oid sha256:365cc799b795118e12518df535bf1fc7fdb554fb35a03234ed2975760f82aa3c
 size 90365754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:552190ca0df537dcf70aa1ed2f68db1f90c7e0a289c52e2b3d1a1f38fe81daea
+oid sha256:9fd083083ffc4ff5e9889cb3b5746ee13bdec6c321e3a20459cc07659b35732a
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a62e6ea25099651400ff4a3142a50e40bef5b52ba883be53b2fcb9d1a5b0a98c
+oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.007760962359332557,
+  "epoch": 0.011641443538998836,
   "eval_steps": 8,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -73,6 +73,42 @@
       "learning_rate": 0.00013090169943749476,
       "loss": 0.8351,
       "step": 18
+    },
+    {
+      "epoch": 0.008149010477299184,
+      "grad_norm": 2.585838794708252,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 0.9041,
+      "step": 21
+    },
+    {
+      "epoch": 0.009313154831199068,
+      "grad_norm": 2.0504302978515625,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 0.7262,
+      "step": 24
+    },
+    {
+      "epoch": 0.009313154831199068,
+      "eval_loss": 0.9423869848251343,
+      "eval_runtime": 36.8752,
+      "eval_samples_per_second": 29.424,
+      "eval_steps_per_second": 14.725,
+      "step": 24
+    },
+    {
+      "epoch": 0.010477299185098952,
+      "grad_norm": 1.880564570426941,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 0.845,
+      "step": 27
+    },
+    {
+      "epoch": 0.011641443538998836,
+      "grad_norm": 2.275709867477417,
+      "learning_rate": 0.0,
+      "loss": 0.7635,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -87,12 +123,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 967722569564160.0,
+  "total_flos": 1451583854346240.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null