Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7833b65f9775e368ae540abefe6601a13adb4876a86b9430033b2346325374ba
+oid sha256:6cd50b6aa66e145a44f49828b56cfb711351f60606b38843ccc7c4597813edac
 size 56662952

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7626e5ff84ad5ed08221745905f62e844cd4103484193280c3a7acd5731115ec
+oid sha256:5a9f093244d9daf2d7b71e6270fed6eb83e3e5704f86c257ad4268b0e8f90f22
 size 113488058

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46820fe379d303e4c45803e10eb9d0012220321cdf7a2c720f4ff8046cb25ef5
+oid sha256:8fb8864135386fe95d0e7510b8556fae6c9dab0763d99dd4e8d959600a5144cf
 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": 0.0005811968295712947,
+  "epoch": 0.000871795244356942,
   "eval_steps": 5,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -89,6 +89,50 @@
       "eval_samples_per_second": 27.042,
       "eval_steps_per_second": 13.521,
       "step": 20
+    },
+    {
+      "epoch": 0.0006102566710498594,
+      "grad_norm": 3.9005424976348877,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 5.7874,
+      "step": 21
+    },
+    {
+      "epoch": 0.0006974361954855536,
+      "grad_norm": 3.8502655029296875,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 6.005,
+      "step": 24
+    },
+    {
+      "epoch": 0.0007264960369641184,
+      "eval_loss": 1.3938194513320923,
+      "eval_runtime": 537.5193,
+      "eval_samples_per_second": 26.957,
+      "eval_steps_per_second": 13.479,
+      "step": 25
+    },
+    {
+      "epoch": 0.0007846157199212478,
+      "grad_norm": 3.130795955657959,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 5.8796,
+      "step": 27
+    },
+    {
+      "epoch": 0.000871795244356942,
+      "grad_norm": 4.091054439544678,
+      "learning_rate": 0.0,
+      "loss": 5.2588,
+      "step": 30
+    },
+    {
+      "epoch": 0.000871795244356942,
+      "eval_loss": 1.3867002725601196,
+      "eval_runtime": 536.044,
+      "eval_samples_per_second": 27.031,
+      "eval_steps_per_second": 13.516,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -103,12 +147,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1292171948851200.0,
+  "total_flos": 1953283178496000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null