Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:451eb27bba7caf7fdd110ed84b63b231eaf5ffc5810eed714a958a9f5f641104
+oid sha256:7a2ed3ea454bf08bc6d69d3489f33689054b6b17177a5044c30fee1cf1a32465
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:540a561bc873be092fc37506942c9231d690a3400dfec8d8d0c83e67a001bd0b
+oid sha256:50a3cf9a8311d9302b3aa3df78a3d2fdcafdecebe6e3dcb2e7aaa6c1bd859bf1
 size 320194002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b042b4d598925f64321dd5bc833bccb2097be341c30bff2b10758fdf4a3fb46
+oid sha256:77a1b7a32508c1b012313650a7a7e7fa37e522773c80f128530afa4e4f746fda
 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": 0.012334258402713537,
+  "epoch": 0.018501387604070305,
   "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": 2.8131,
       "step": 18
+    },
+    {
+      "epoch": 0.012950971322849213,
+      "grad_norm": 0.4450037479400635,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 2.6101,
+      "step": 21
+    },
+    {
+      "epoch": 0.014801110083256245,
+      "grad_norm": 0.4622777998447418,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 2.7151,
+      "step": 24
+    },
+    {
+      "epoch": 0.014801110083256245,
+      "eval_loss": 2.810142993927002,
+      "eval_runtime": 94.2087,
+      "eval_samples_per_second": 7.25,
+      "eval_steps_per_second": 3.63,
+      "step": 24
+    },
+    {
+      "epoch": 0.016651248843663275,
+      "grad_norm": 0.5054405331611633,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 2.6541,
+      "step": 27
+    },
+    {
+      "epoch": 0.018501387604070305,
+      "grad_norm": 0.3172176778316498,
+      "learning_rate": 0.0,
+      "loss": 2.6418,
+      "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": 7514769321885696.0,
+  "total_flos": 1.1272153982828544e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null