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:c53b1cbb048243f3057b5df50e575a8e86f868268453f7c0e07069688a794816
+oid sha256:4aa25184417408bf8d612d541f461d352945e64f91c7598ac493ae39699d475c
 size 31064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:deb03ab1d320a33732deadb9cc7f895ca2e560e7c09b220742e67a2a4093eddc
+oid sha256:940ea360e382d0628466e07ada4733dce3fbf187c0df8456da369a9bf20e5a3e
 size 71718

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48d41985628b63b1f03308534e42f5f4fade1dc9f1a7ca147144af3b829d1153
+oid sha256:52c1e8dd4ba9ace9e6fcca937683862f29cfd6bf4fb3642d8d44c9c9a4359dc1
 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": 0.0010954671535409572,
+  "epoch": 0.0014044450686422527,
   "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": 41.5005,
       "step": 35
+    },
+    {
+      "epoch": 0.0011235560549138022,
+      "grad_norm": 0.2809828221797943,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 41.4964,
+      "step": 40
+    },
+    {
+      "epoch": 0.0011235560549138022,
+      "eval_loss": 10.374896049499512,
+      "eval_runtime": 89.844,
+      "eval_samples_per_second": 166.845,
+      "eval_steps_per_second": 83.422,
+      "step": 40
+    },
+    {
+      "epoch": 0.0012640005617780275,
+      "grad_norm": 0.2692044675350189,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 41.4948,
+      "step": 45
+    },
+    {
+      "epoch": 0.0014044450686422527,
+      "grad_norm": 0.3889637589454651,
+      "learning_rate": 0.0,
+      "loss": 41.507,
+      "step": 50
+    },
+    {
+      "epoch": 0.0014044450686422527,
+      "eval_loss": 10.374822616577148,
+      "eval_runtime": 87.3375,
+      "eval_samples_per_second": 171.633,
+      "eval_steps_per_second": 85.817,
+      "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": 1758039834624.0,
+  "total_flos": 2220006506496.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null