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:c632396ab3747ad337213a7ab06fe1601491739871f84fe7eac66cbee7cf0479
+oid sha256:2135fbc134915419472d6cdd18dba113789f2604f4836bedd84c4fa1eeaa7124
 size 80792096

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e94488b9b8be610e9b597e4b7c6c441a6b9c4e8977969978d30c34c47c5cd5b3
+oid sha256:5ff748644927e8e4053d20f194d7fdfc8f6edfa1986397f534c84abd11ece0ae
 size 41459700

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea21cb1e18b4d72753d16a45c60afba61a4e160d56ea0bf70b3da10207d6c21b
+oid sha256:b2c324db5b0d89e4b583de73f5ad251898e232edf3e9abfd8cebe5d6e4c15ab2
 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": 0.0019685536178482193,
+  "epoch": 0.002523786689548999,
   "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": 1.9136,
       "step": 35
+    },
+    {
+      "epoch": 0.0020190293516391994,
+      "grad_norm": 1.9628335237503052,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 2.0374,
+      "step": 40
+    },
+    {
+      "epoch": 0.0020190293516391994,
+      "eval_loss": 2.0606985092163086,
+      "eval_runtime": 950.4954,
+      "eval_samples_per_second": 8.776,
+      "eval_steps_per_second": 4.388,
+      "step": 40
+    },
+    {
+      "epoch": 0.0022714080205940993,
+      "grad_norm": 1.3801227807998657,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 2.044,
+      "step": 45
+    },
+    {
+      "epoch": 0.002523786689548999,
+      "grad_norm": 1.8574044704437256,
+      "learning_rate": 0.0,
+      "loss": 2.1928,
+      "step": 50
+    },
+    {
+      "epoch": 0.002523786689548999,
+      "eval_loss": 2.04537034034729,
+      "eval_runtime": 947.9063,
+      "eval_samples_per_second": 8.8,
+      "eval_steps_per_second": 4.4,
+      "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": 1.2590545433001984e+16,
+  "total_flos": 1.5988685722877952e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null