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:c08c2f07741aed4ca4737a5237a7eeb5b6cb1c2a195d2beb80c893e2b98b5b3a
+oid sha256:fa77dd8841f12055e640159c5f626ff502079c9372853359cbabc43113be29b1
 size 50358592

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9fcaa4025915407ef308e414819e4078810646d6f6747cab48f19565912f983b
+oid sha256:b475303e48d8e7417e71c219a9f45810b79fa69bb9d864995bfb37f7b49f5291
 size 100824826

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2caab57c9738a6223b66a33175b22839bf9437a089ed80e62b0e4247b5a00c6c
+oid sha256:36cb5f85a79582577f20ea967d2bfcafd3518fb3ab33875ffc6455cb3108910e
 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": 0.0003369768960215665,
+  "epoch": 0.0005054653440323498,
   "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": 8.8518,
       "step": 18
+    },
+    {
+      "epoch": 0.00035382574082264487,
+      "grad_norm": 4.0057573318481445,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 9.3115,
+      "step": 21
+    },
+    {
+      "epoch": 0.0004043722752258798,
+      "grad_norm": 4.486216068267822,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 8.6871,
+      "step": 24
+    },
+    {
+      "epoch": 0.0004043722752258798,
+      "eval_loss": 2.2304084300994873,
+      "eval_runtime": 1502.5066,
+      "eval_samples_per_second": 16.632,
+      "eval_steps_per_second": 8.316,
+      "step": 24
+    },
+    {
+      "epoch": 0.0004549188096291148,
+      "grad_norm": 3.8148226737976074,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 8.8024,
+      "step": 27
+    },
+    {
+      "epoch": 0.0005054653440323498,
+      "grad_norm": 3.9129483699798584,
+      "learning_rate": 0.0,
+      "loss": 8.5131,
+      "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": 1200474229309440.0,
+  "total_flos": 1800711343964160.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null