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:a4804ed404b31ac1c7fedfc15fa4a73fb01d71d966c6df0319323c2bc01838cd
+oid sha256:6f9d14e4f0889989d10fd462a4e79e4d0698131cb8ad50d2d66ca724f716ac8a
 size 100697728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d20c307d05e44d705c48e46ee48b0946f6c5b3e7de1e701ff60b4328b30a3637
+oid sha256:9bb420a3c51fd75c1e3e87757f9a8e2b2fc470078055a32c9b67b542e4385cfb
 size 201541754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb23d5213816a8bcc8dd2e62952143731b9464c60d41359298ba1eb4c0519327
+oid sha256:ca6beb2d65a0523c2c3348eb8cc789e6c519be8b0f9b7ff0283a871518bdcb47
 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": 0.011487650775416428,
+  "epoch": 0.01723147616312464,
   "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": 14.5678,
       "step": 18
+    },
+    {
+      "epoch": 0.012062033314187249,
+      "grad_norm": 1.3764376640319824,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 14.2232,
+      "step": 21
+    },
+    {
+      "epoch": 0.013785180930499713,
+      "grad_norm": 1.5241773128509521,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 16.4105,
+      "step": 24
+    },
+    {
+      "epoch": 0.013785180930499713,
+      "eval_loss": 3.5820188522338867,
+      "eval_runtime": 46.1988,
+      "eval_samples_per_second": 15.888,
+      "eval_steps_per_second": 7.944,
+      "step": 24
+    },
+    {
+      "epoch": 0.015508328546812177,
+      "grad_norm": 0.9712653756141663,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 15.2987,
+      "step": 27
+    },
+    {
+      "epoch": 0.01723147616312464,
+      "grad_norm": 0.9049797654151917,
+      "learning_rate": 0.0,
+      "loss": 13.7824,
+      "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": 3776287592153088.0,
+  "total_flos": 5618379100520448.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null