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:c554812a1bf44244b2386ce0b4f932935b649b4d1795242ae2dd54d6cdf149a2
+oid sha256:f8c3ae283b4d1487794a0adbbb492bc53cc7988ca867daea674326894b82006f
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b6d273ced916d191c48ab7ce0aeff558177b09b9fc2ca15d2460ec395a87f3f
+oid sha256:d7cb081406ccf819cd54a99f21e90dcbc39e7911026d5089fc520e975e91fb5b
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a5f891767aaacfb795fc4c851c74f7dcf55cd20474ec59a43d271975d0645cf
+oid sha256:b9b32a31b90c640b6f3edbb6f5edfd55f2a05c8f726be41404fdb7ef23099e0b
 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": 0.0329600676103951,
+  "epoch": 0.04225649693640397,
   "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": 3.4989,
       "step": 35
+    },
+    {
+      "epoch": 0.03380519754912318,
+      "grad_norm": 40.052974700927734,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 2.2159,
+      "step": 40
+    },
+    {
+      "epoch": 0.03380519754912318,
+      "eval_loss": 0.5223318934440613,
+      "eval_runtime": 32.8352,
+      "eval_samples_per_second": 15.197,
+      "eval_steps_per_second": 7.614,
+      "step": 40
+    },
+    {
+      "epoch": 0.03803084724276357,
+      "grad_norm": 45.003719329833984,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.8864,
+      "step": 45
+    },
+    {
+      "epoch": 0.04225649693640397,
+      "grad_norm": 26.609577178955078,
+      "learning_rate": 0.0,
+      "loss": 2.1229,
+      "step": 50
+    },
+    {
+      "epoch": 0.04225649693640397,
+      "eval_loss": 0.5111870765686035,
+      "eval_runtime": 32.8062,
+      "eval_samples_per_second": 15.211,
+      "eval_steps_per_second": 7.621,
+      "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": 6835537792991232.0,
+  "total_flos": 8807327540969472.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null