Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f47139ab2a2a91ff6aa083a25b941f6d71e6b4a9e8ec9ee5fccad01ca201d9d0
+oid sha256:5794c85ad3250ecb8d485dd7841fda2c3c87cf38379646adb980cbbcc6b39a0a
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1094b9c7a137d8c3fa22409d5e53f202ce793bd11f6564ac9af3701b296d42af
+oid sha256:6618fd06fcfbb70715b060c31d39308937a38b390bec08655e1bafed8aafd91f
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a5f891767aaacfb795fc4c851c74f7dcf55cd20474ec59a43d271975d0645cf
+oid sha256:d36cf02c5c091e1cf6b7a556033f9afe92924f5c6d18c68aeec7f759f6f16a6c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c50dbaa792cda4a28fbbc2acb2a3e03c59530712bbc5107212d33064d193da4
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.03567345072032929,
+  "epoch": 0.0457351932311914,
   "eval_steps": 10,
-  "global_step": 39,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -88,6 +88,43 @@
       "learning_rate": 3.086582838174551e-05,
       "loss": 0.8467,
       "step": 35
+    },
+    {
+      "epoch": 0.03658815458495312,
+      "grad_norm": 1.2147860527038574,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.8548,
+      "step": 40
+    },
+    {
+      "epoch": 0.03658815458495312,
+      "eval_loss": 0.831978976726532,
+      "eval_runtime": 32.12,
+      "eval_samples_per_second": 14.352,
+      "eval_steps_per_second": 7.192,
+      "step": 40
+    },
+    {
+      "epoch": 0.04116167390807226,
+      "grad_norm": 1.188929557800293,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.8396,
+      "step": 45
+    },
+    {
+      "epoch": 0.0457351932311914,
+      "grad_norm": 1.2113749980926514,
+      "learning_rate": 0.0,
+      "loss": 0.7299,
+      "step": 50
+    },
+    {
+      "epoch": 0.0457351932311914,
+      "eval_loss": 0.8227381706237793,
+      "eval_runtime": 32.1238,
+      "eval_samples_per_second": 14.351,
+      "eval_steps_per_second": 7.191,
+      "step": 50
     }
   ],
   "logging_steps": 5,
@@ -102,12 +139,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 7213426195562496.0,
+  "total_flos": 9247982302003200.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null