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:f200b863b77a7b44afa41f050d1120188090f91cf081c7c8ed6e05ff4df7e2e5
+oid sha256:2c733ae1682e45ee9a6d829a62c450d5c0ff1eabd3f4b64003429472a49c76f5
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:65a04cdb565393266487dd144d8f7e260e270e96ad14ce67958b7460c64ffaa6
+oid sha256:ba38a45905bcc3512554743f14776f29cb3672d870e5be124e140f6c05209de6
 size 320194002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:70aad4b3ac51dddc7d9c6e648201db746c0cc853235d6c6dbd5ee81055a6b8f9
+oid sha256:ed02b4aeb3e8410dd2c4c54e4068088b8d98f2761539b98f44d1b1a6438c4b75
 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": 0.0033819488480236735,
+  "epoch": 0.0050729232720355105,
   "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": 0.723,
       "step": 18
+    },
+    {
+      "epoch": 0.0035510462904248573,
+      "grad_norm": 0.3034185469150543,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 0.6186,
+      "step": 21
+    },
+    {
+      "epoch": 0.004058338617628408,
+      "grad_norm": 0.2614850103855133,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 0.6128,
+      "step": 24
+    },
+    {
+      "epoch": 0.004058338617628408,
+      "eval_loss": 0.6241685748100281,
+      "eval_runtime": 335.2606,
+      "eval_samples_per_second": 7.427,
+      "eval_steps_per_second": 3.714,
+      "step": 24
+    },
+    {
+      "epoch": 0.004565630944831959,
+      "grad_norm": 0.2510441243648529,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 0.5886,
+      "step": 27
+    },
+    {
+      "epoch": 0.0050729232720355105,
+      "grad_norm": 0.30792003870010376,
+      "learning_rate": 0.0,
+      "loss": 0.6102,
+      "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": 7351404771409920.0,
+  "total_flos": 1.0863742606639104e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null