Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:764d1a51b50a4222f3efa56f983bbbbf7b6108efa642b5271ad3ea45d396493f
+oid sha256:7cb6098f848bd2e6c01d2651024b352c6b77153eaeb87d3df1a39a9c2d4b8359
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:18be2e82ba4c9af05d64fe849281dfa3f91c21a27a3dc329b7ed7fba818c215a
+oid sha256:3f11cf1711ea5a25ff134be4da8c0a78fef241e34ea31f83c433a6773ba71fcd
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:50e59e2d1a05f0e293c56fa96d2faf2d4759fe61e974b50396fc3dd56bba8fd6
+oid sha256:dbc97c6ab2cbb7ab2f8aa98761d78e0b19e0b8f8bd6ac1d4adbcbb392dcdae9c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:22e67cb47ff12ababb2db5752a0059510ef75c13ebd9ed242d32d1eb2ba8aa08
+oid sha256:204b783eee4578e262211ed4342a25463d72b9f2b43a34a1fb0c83abcbfcca96
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.020804438280166437,
+  "epoch": 0.031206657420249653,
   "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": 0.0001963525491562421,
       "loss": 1.9871,
       "step": 18
+    },
+    {
+      "epoch": 0.021844660194174758,
+      "grad_norm": 1.726994514465332,
+      "learning_rate": 0.00012653483024396533,
+      "loss": 1.794,
+      "step": 21
+    },
+    {
+      "epoch": 0.024965325936199722,
+      "grad_norm": 2.83248233795166,
+      "learning_rate": 6.183221215612904e-05,
+      "loss": 1.9046,
+      "step": 24
+    },
+    {
+      "epoch": 0.024965325936199722,
+      "eval_loss": 1.781469702720642,
+      "eval_runtime": 25.8621,
+      "eval_samples_per_second": 11.755,
+      "eval_steps_per_second": 5.877,
+      "step": 24
+    },
+    {
+      "epoch": 0.02808599167822469,
+      "grad_norm": 1.6368578672409058,
+      "learning_rate": 1.634902137174483e-05,
+      "loss": 1.7777,
+      "step": 27
+    },
+    {
+      "epoch": 0.031206657420249653,
+      "grad_norm": 1.621636986732483,
+      "learning_rate": 0.0,
+      "loss": 1.8576,
+      "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": 5564154626703360.0,
+  "total_flos": 8346231940055040.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null