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:aadb482496e5e10ee27f7374b91bcf57cb0a6f17cb32ffe2dea28163cbe97fa6
+oid sha256:8688b55dfe97cd7082e0ffda65c16956847e3a4e1f45167d8148f9fed4b993f5
 size 25192688

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3cc47c149667082447f140d84a8dc30a4829dc4e31ba1443946b3c9c304ecbd0
+oid sha256:dfa1057bbfc74155067bd9de37e6e79517b0ba955cac4b44047547cc0b2eede1
 size 50493050

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:19a32067fb5f557237726e10d4e5248eee478b9f21bf82db1c657e481f64a127
+oid sha256:0a2ba38d61cd6275d77c5204447109dd9eddc38992e480ed671e0d925609356b
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef527702b4e2147a500c0b29beb26751d245ebb60338b3910b449b6549ac4d59
+oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.07017543859649122,
+  "epoch": 0.14035087719298245,
   "eval_steps": 5,
-  "global_step": 15,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -74,6 +74,65 @@
       "eval_samples_per_second": 38.438,
       "eval_steps_per_second": 19.219,
       "step": 15
+    },
+    {
+      "epoch": 0.08421052631578947,
+      "grad_norm": 4.6222100257873535,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 12.7029,
+      "step": 18
+    },
+    {
+      "epoch": 0.0935672514619883,
+      "eval_loss": 3.0007877349853516,
+      "eval_runtime": 2.3413,
+      "eval_samples_per_second": 38.44,
+      "eval_steps_per_second": 19.22,
+      "step": 20
+    },
+    {
+      "epoch": 0.09824561403508772,
+      "grad_norm": 4.646065711975098,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 11.8156,
+      "step": 21
+    },
+    {
+      "epoch": 0.11228070175438597,
+      "grad_norm": 4.925897121429443,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 11.6899,
+      "step": 24
+    },
+    {
+      "epoch": 0.11695906432748537,
+      "eval_loss": 2.9046480655670166,
+      "eval_runtime": 2.3397,
+      "eval_samples_per_second": 38.467,
+      "eval_steps_per_second": 19.233,
+      "step": 25
+    },
+    {
+      "epoch": 0.12631578947368421,
+      "grad_norm": 4.967269420623779,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 11.4466,
+      "step": 27
+    },
+    {
+      "epoch": 0.14035087719298245,
+      "grad_norm": 4.419576644897461,
+      "learning_rate": 0.0,
+      "loss": 11.7422,
+      "step": 30
+    },
+    {
+      "epoch": 0.14035087719298245,
+      "eval_loss": 2.876509666442871,
+      "eval_runtime": 2.3422,
+      "eval_samples_per_second": 38.425,
+      "eval_steps_per_second": 19.213,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -88,12 +147,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 227528241315840.0,
+  "total_flos": 455056482631680.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null