Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:17d78747828a747890a12763c1dc2f0fa19c6ea5a637542a3f3b96390ddc9439
+oid sha256:a9d63c42bf945a017a9cb6167ba1a3dacd6b157dad222e9f7bb72daa313b3e8d
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d5a642cb4a6ad8ecc74996700b1cce044c354d4bf2e42979ee883811b67e545a
+oid sha256:0ba96e89dbf6ed45979bbfc2176f5d25a63b2295615fc0ac15e16ba68f1384f0
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b3b79fae93cf203787b2922d5e898c5e5e5ae6258c347aaf3006155d5b66b3cc
+oid sha256:91d90d3b268bd0466e2451b4d352df63ba8c30163315670c92c13b5a1883079c
 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": 0.0022491495403300626,
+  "epoch": 0.003373724310495094,
   "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": 0.0475,
       "step": 18
+    },
+    {
+      "epoch": 0.002361607017346566,
+      "grad_norm": 0.2808378040790558,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 0.0315,
+      "step": 21
+    },
+    {
+      "epoch": 0.0026989794483960753,
+      "grad_norm": 0.34844180941581726,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 0.0352,
+      "step": 24
+    },
+    {
+      "epoch": 0.0026989794483960753,
+      "eval_loss": 0.029852185398340225,
+      "eval_runtime": 786.1536,
+      "eval_samples_per_second": 4.764,
+      "eval_steps_per_second": 2.382,
+      "step": 24
+    },
+    {
+      "epoch": 0.0030363518794455846,
+      "grad_norm": 0.27075034379959106,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 0.0229,
+      "step": 27
+    },
+    {
+      "epoch": 0.003373724310495094,
+      "grad_norm": 0.7711063623428345,
+      "learning_rate": 0.0,
+      "loss": 0.0375,
+      "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": 1.1777460626522112e+16,
+  "total_flos": 1.7434351163670528e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null