Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5673893b89d8c97732deef9d04244406c1515cb224d1dd61a62bcf6fd7af0d49
+oid sha256:91da71d9e37bb4e9cbfb2d5b48a63da210f72ab85153b141460c7f71c4f77cb2
 size 35237104

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc85493b021d9ab82eedf47527d126c5cbb9b02aef1b08a450ccaa7684d52810
+oid sha256:ed9fd1c2bb81f565045c49a67338a02c72bb391476ff35bef00a805be8bbce83
 size 70667778

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a15c80c6a1a9c26b418b008d0939ad7a0e6e0645a08ee728ddeac8b91873a93
+oid sha256:34dd4e61b35723543bb3f7b3e025223cd7391eac041b842ada88378b27cf03d3
 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": 0.023682652457075192,
+  "epoch": 0.035523978685612786,
   "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": 1.5686,
       "step": 18
+    },
+    {
+      "epoch": 0.02486678507992895,
+      "grad_norm": 0.9773281216621399,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 1.3848,
+      "step": 21
+    },
+    {
+      "epoch": 0.028419182948490232,
+      "grad_norm": 1.2781157493591309,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 1.4521,
+      "step": 24
+    },
+    {
+      "epoch": 0.028419182948490232,
+      "eval_loss": 1.490580677986145,
+      "eval_runtime": 8.504,
+      "eval_samples_per_second": 41.862,
+      "eval_steps_per_second": 20.931,
+      "step": 24
+    },
+    {
+      "epoch": 0.03197158081705151,
+      "grad_norm": 1.0305604934692383,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 1.663,
+      "step": 27
+    },
+    {
+      "epoch": 0.035523978685612786,
+      "grad_norm": 0.8461658954620361,
+      "learning_rate": 0.0,
+      "loss": 1.2382,
+      "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": 405536794214400.0,
+  "total_flos": 599293262561280.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null