Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0248ba99593f0261bb8dab4d27d8eb25b3b4d340ce64b4eb4c752a6ebf0403f6
+oid sha256:f43a4a3536388522b38f0716b8b25b52117413117adefa7609734a398b779b9c
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:819718851b3a9778a3546458b89959e57fb1e495b20c5101b0306fb025b052cb
+oid sha256:f3b42ae13d6216eb075c97437f2d502dd0d39604f43d6a9fca4d963b6d6f34c8
 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": 0.024051803885291396,
+  "epoch": 0.030835646006783842,
   "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": 1.0187,
       "step": 35
+    },
+    {
+      "epoch": 0.024668516805427074,
+      "grad_norm": 2.7381200790405273,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.8861,
+      "step": 40
+    },
+    {
+      "epoch": 0.024668516805427074,
+      "eval_loss": 0.9322488307952881,
+      "eval_runtime": 46.507,
+      "eval_samples_per_second": 14.686,
+      "eval_steps_per_second": 7.354,
+      "step": 40
+    },
+    {
+      "epoch": 0.027752081406105456,
+      "grad_norm": 3.0359268188476562,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.9485,
+      "step": 45
+    },
+    {
+      "epoch": 0.030835646006783842,
+      "grad_norm": 3.2081491947174072,
+      "learning_rate": 0.0,
+      "loss": 0.8408,
+      "step": 50
+    },
+    {
+      "epoch": 0.030835646006783842,
+      "eval_loss": 0.9238138198852539,
+      "eval_runtime": 46.3957,
+      "eval_samples_per_second": 14.721,
+      "eval_steps_per_second": 7.371,
+      "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": 7213300567769088.0,
+  "total_flos": 9247821240729600.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null