Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:676d9760e740d080796bf173c2661192dff60c5a526109a3b3ff07a1951d6833
+oid sha256:b86a0aa13352a9ced522131e28cb9ebad59a86dc035525f16870fe731b19e2ca
 size 15182728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c53d9a88bdbd6e929a34b89040e89aec20efe915a9860239a6026f96506f052b
+oid sha256:1e092bfdc8bb364192f16e5ac02adc084c947901c869d955e1cc6e6b76518911
 size 8075796

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a2a35d30a6cf95bceafac98d3d5f88a6f466f6fb3c086d6aa725b839a906a2a
+oid sha256:e097adad004a56c0a60e00f04459946aee68ab67d9efd4f67f973cf741bd8551
 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": 0.04529616724738676,
+  "epoch": 0.05807200929152149,
   "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": 0.7004,
       "step": 35
+    },
+    {
+      "epoch": 0.04645760743321719,
+      "grad_norm": 4.361053943634033,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.4651,
+      "step": 40
+    },
+    {
+      "epoch": 0.04645760743321719,
+      "eval_loss": 0.3752843737602234,
+      "eval_runtime": 13.7163,
+      "eval_samples_per_second": 26.465,
+      "eval_steps_per_second": 13.269,
+      "step": 40
+    },
+    {
+      "epoch": 0.05226480836236934,
+      "grad_norm": 4.349754810333252,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.2919,
+      "step": 45
+    },
+    {
+      "epoch": 0.05807200929152149,
+      "grad_norm": 3.6295876502990723,
+      "learning_rate": 0.0,
+      "loss": 0.4376,
+      "step": 50
+    },
+    {
+      "epoch": 0.05807200929152149,
+      "eval_loss": 0.3117239773273468,
+      "eval_runtime": 13.5929,
+      "eval_samples_per_second": 26.705,
+      "eval_steps_per_second": 13.389,
+      "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": 556247568875520.0,
+  "total_flos": 713531364212736.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null