Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:177c8081764743d0c2746ac077ef9c05ee3590c565624b43de20e8f80404a3c1
+oid sha256:af7e5066ae0c657b3bcc710a7a74f4b9b06bfbd97aa4e6cf651fecd39eddc482
 size 80792096

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:905220a31559f8405bc615857c06968eba06fb1f2ae1c5264518b7803134d842
+oid sha256:aab2b4221ef3889ff5816305404da75d0fff3421f44582a21a14a5f6af71e539
 size 41459700

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4abb068b35f225af8a941598a7b2e8ccd370e8e4cb68906a831ee4b6696aba9c
+oid sha256:f5c4dec116ae1db42856446a4d22ae19f3b0b6d86d7fb48f9759f6a66e718e42
 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": 0.004417886777491433,
+  "epoch": 0.005663957407040299,
   "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": 1.3513,
       "step": 35
+    },
+    {
+      "epoch": 0.0045311659256322395,
+      "grad_norm": 1.7891837358474731,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.2986,
+      "step": 40
+    },
+    {
+      "epoch": 0.0045311659256322395,
+      "eval_loss": 1.3863377571105957,
+      "eval_runtime": 238.1813,
+      "eval_samples_per_second": 15.606,
+      "eval_steps_per_second": 7.805,
+      "step": 40
+    },
+    {
+      "epoch": 0.005097561666336269,
+      "grad_norm": 1.6350563764572144,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.2097,
+      "step": 45
+    },
+    {
+      "epoch": 0.005663957407040299,
+      "grad_norm": 1.806128740310669,
+      "learning_rate": 0.0,
+      "loss": 1.3774,
+      "step": 50
+    },
+    {
+      "epoch": 0.005663957407040299,
+      "eval_loss": 1.38254714012146,
+      "eval_runtime": 239.0077,
+      "eval_samples_per_second": 15.552,
+      "eval_steps_per_second": 7.778,
+      "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": 7101241887817728.0,
+  "total_flos": 9105273340821504.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null