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:d8a8b616667c1a068a661ec3b96dcf76bf9afaee2b988896a05b7dc852fc6044
+oid sha256:2f9ac6abd495b15a9b6ac07b9f16cc5a1f7d6fb46e32e56a6a3756ea4524c208
 size 10636352

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8107c05182d13160da72e845bde11a033ed23c692bc7ee41e523d099d16d1117
+oid sha256:dfc21a05bbfd8a4fbf4dc51e9cf780f6d5c3a56931ce67f8b1e8c5342e335e83
 size 21354682

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff60844084dfe481cc492bd9e24904bd85d4151bca06d064a9070a09e58ef214
+oid sha256:20c8e174b9d1ede71755a8ba595de72ce10142afe0c111b4dd5f079cb0ce5de2
 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": 0.002940419744918587,
+  "epoch": 0.004410629617377881,
   "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": 10.4049,
       "step": 18
+    },
+    {
+      "epoch": 0.0030874407321645164,
+      "grad_norm": 4.7215728759765625,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 9.809,
+      "step": 21
+    },
+    {
+      "epoch": 0.0035285036939023046,
+      "grad_norm": 4.4128193855285645,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 10.0285,
+      "step": 24
+    },
+    {
+      "epoch": 0.0035285036939023046,
+      "eval_loss": 2.475198984146118,
+      "eval_runtime": 32.1406,
+      "eval_samples_per_second": 89.109,
+      "eval_steps_per_second": 44.554,
+      "step": 24
+    },
+    {
+      "epoch": 0.0039695666556400925,
+      "grad_norm": 6.173066139221191,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 10.1781,
+      "step": 27
+    },
+    {
+      "epoch": 0.004410629617377881,
+      "grad_norm": 4.85377311706543,
+      "learning_rate": 0.0,
+      "loss": 10.3136,
+      "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": 99156039303168.0,
+  "total_flos": 149811841990656.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null