Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f95e6f4b5797ec34895b66dea5cfa44e7dcb59a7aca717b95f2d2e71e07d9e8
+oid sha256:37cc9695fa469181d2070ac0f3c3d4bc2fc67cfad57709ba9f5e1c5b0ca87d39
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d948bbca254dbfcf4f09d453e6f1f6f9879940501700b9ec0c623acab1f57d9c
+oid sha256:97ffc8ebd59d89659c01cda3bc45cb542111d3ea8752e0a0150a2bc8012e5a00
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c5a4d40f9c4bf65078886d54e1cfc54df5ccabb01b6dd112966b8979e806e106
+oid sha256:65941554dfccfdcf0ed28341039200adb2012eef3c09ec7b1fbc4a815a622955
 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": 0.015621870618866412,
+  "epoch": 0.02002803925495694,
   "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": 7.9119,
       "step": 35
+    },
+    {
+      "epoch": 0.016022431403965552,
+      "grad_norm": 9.923874855041504,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 7.3681,
+      "step": 40
+    },
+    {
+      "epoch": 0.016022431403965552,
+      "eval_loss": 1.8054759502410889,
+      "eval_runtime": 70.9758,
+      "eval_samples_per_second": 14.822,
+      "eval_steps_per_second": 7.411,
+      "step": 40
+    },
+    {
+      "epoch": 0.018025235329461247,
+      "grad_norm": 7.868798732757568,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 8.0851,
+      "step": 45
+    },
+    {
+      "epoch": 0.02002803925495694,
+      "grad_norm": 10.540374755859375,
+      "learning_rate": 0.0,
+      "loss": 6.4632,
+      "step": 50
+    },
+    {
+      "epoch": 0.02002803925495694,
+      "eval_loss": 1.801642894744873,
+      "eval_runtime": 69.65,
+      "eval_samples_per_second": 15.104,
+      "eval_steps_per_second": 7.552,
+      "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": 6923053606895616.0,
+  "total_flos": 8894809381011456.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null