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:e8566e2aa24edc6571b4a670b790c3e37e208abff24d10b7c9343bc0dd605cab
+oid sha256:8576a5cdd10c0227ef82fbdc2d7aa5b2eceab438a267afea32d9ffa49fe5f653
 size 13587864

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:65d5843215f9da8dc2b66d5784786298df50a5f282321e3fd1d4a4a30c8d4313
+oid sha256:b3252af66689177027cb95802201d770a05a9ca5bff35c50b5e67b3d1b71d2d8
 size 27273018

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:719f8b8e001cc38acdda01d52ac711810ccd1dd2a86c66c4ff94a115205737e7
+oid sha256:d7f85e6c7cbaa9f0130dc8dfcc4b1f342515c1f16d6579e197c6eae2e40183d9
 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": 0.001970734591318914,
+  "epoch": 0.002956101886978371,
   "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": 1.7603,
       "step": 18
+    },
+    {
+      "epoch": 0.00206927132088486,
+      "grad_norm": 0.4918995797634125,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 1.8481,
+      "step": 21
+    },
+    {
+      "epoch": 0.002364881509582697,
+      "grad_norm": 0.4786415100097656,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 1.8574,
+      "step": 24
+    },
+    {
+      "epoch": 0.002364881509582697,
+      "eval_loss": 1.9388502836227417,
+      "eval_runtime": 58.9473,
+      "eval_samples_per_second": 72.488,
+      "eval_steps_per_second": 36.253,
+      "step": 24
+    },
+    {
+      "epoch": 0.002660491698280534,
+      "grad_norm": 0.49968457221984863,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 1.8016,
+      "step": 27
+    },
+    {
+      "epoch": 0.002956101886978371,
+      "grad_norm": 0.35181719064712524,
+      "learning_rate": 0.0,
+      "loss": 1.7519,
+      "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": 185695271387136.0,
+  "total_flos": 279410641993728.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null