Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43aa59b6039959e35571efed99f957fb3afce710e87f6874944df9731ed6b77d
+oid sha256:05a730c535d28e4a00b16bf54d5b5f39ecffda479b02efd9849399ae7a9211de
 size 250422888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c673e5e854dd6049a13737a6d10765a36451bd3b485c7f0fa91cb5a821ecb390
+oid sha256:64da9f1188ebc28a90f6adef25c133350f0a88f940f845fb94ab3cd90b51c2b9
 size 501168482

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7332cedcc7b3b36b7974e070bd9fa7171e6a96e191919b27b6014d872048e1e
+oid sha256:83fdd6955092c161405108c24aff329154c04f5feb7c98b00794794c0262bcda
 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": 0.006314626253058647,
+  "epoch": 0.00947193937958797,
   "eval_steps": 5,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -89,6 +89,50 @@
       "eval_samples_per_second": 5.405,
       "eval_steps_per_second": 2.703,
       "step": 20
+    },
+    {
+      "epoch": 0.006630357565711579,
+      "grad_norm": 2.1834053993225098,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 5.4897,
+      "step": 21
+    },
+    {
+      "epoch": 0.007577551503670376,
+      "grad_norm": 2.090245246887207,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 4.7943,
+      "step": 24
+    },
+    {
+      "epoch": 0.007893282816323309,
+      "eval_loss": 1.2484618425369263,
+      "eval_runtime": 247.1722,
+      "eval_samples_per_second": 5.397,
+      "eval_steps_per_second": 2.699,
+      "step": 25
+    },
+    {
+      "epoch": 0.008524745441629173,
+      "grad_norm": 2.3083226680755615,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 4.8183,
+      "step": 27
+    },
+    {
+      "epoch": 0.00947193937958797,
+      "grad_norm": 2.6077980995178223,
+      "learning_rate": 0.0,
+      "loss": 5.0171,
+      "step": 30
+    },
+    {
+      "epoch": 0.00947193937958797,
+      "eval_loss": 1.2385700941085815,
+      "eval_runtime": 247.1144,
+      "eval_samples_per_second": 5.398,
+      "eval_steps_per_second": 2.699,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -103,12 +147,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.26956599246848e+16,
+  "total_flos": 1.90434898870272e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null