Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b27e67d5e39a70992a3cf8348bbdcdccd48bd19ffe13e199242924128b9a515
+oid sha256:60081a9bde56a86bf20bf56488e3682b480dc7f1e77548df5ffca5a805e99385
 size 25192688

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb9f6067b02489961b2cab0629b17a5931c359368ff53d79328f29ba055392b5
+oid sha256:a47859dad75526b3acc5dda044f8c44a3f8d53d7937acf89fa7d58b0eb49ed10
 size 50493050

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ec5c114caeaa47e02cc51e3b52952373aad4f6a5defda9399c24783fd07a039
+oid sha256:c85569d1686f8ba93d75e7b353f9695d92b235909b55766986026f293fb4e532
 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": 0.0011701494865969128,
+  "epoch": 0.0017552242298953691,
   "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": 22.7001,
       "step": 18
+    },
+    {
+      "epoch": 0.0012286569609267584,
+      "grad_norm": 11.67773723602295,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 24.0305,
+      "step": 21
+    },
+    {
+      "epoch": 0.0014041793839162952,
+      "grad_norm": 9.549829483032227,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 22.462,
+      "step": 24
+    },
+    {
+      "epoch": 0.0014041793839162952,
+      "eval_loss": 3.7929909229278564,
+      "eval_runtime": 531.5397,
+      "eval_samples_per_second": 40.618,
+      "eval_steps_per_second": 10.155,
+      "step": 24
+    },
+    {
+      "epoch": 0.0015797018069058323,
+      "grad_norm": 7.023437976837158,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 23.2863,
+      "step": 27
+    },
+    {
+      "epoch": 0.0017552242298953691,
+      "grad_norm": 7.868184566497803,
+      "learning_rate": 0.0,
+      "loss": 22.6354,
+      "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": 910112965263360.0,
+  "total_flos": 1365169447895040.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null