Training in progress, step 5, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f676a44d9cf643be2f0e26dd3fc570f354de39f349c7cfeee4c5f2d16e4ed419
+oid sha256:4ddc5bfa86abf8c9193466d68a87000a617c796966fcfd86c208a2637cf31130
 size 17640136

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e3eb2073d5e01ab6e6d3b3c352697a58d7080144fe28db1ce07f833b7b4b0b3b
+oid sha256:355b556e2e56506208a6f78369fa20c9fec968d12098b86afb13ce3b8f513c32
 size 9568884

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b8d6b9a0e9e9502751def1097143074ef257eab24506a0f12d159e188fa21987
+oid sha256:572c5653b97399d6dc550389d4e48df5479adab7c80147f357d4d04c0f7252da
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7adb031dc938779259a07e684ea318126e92e52b40c256b93ef474d2ac57a5b
+oid sha256:2d63217b923cb177f669d6bc2174b89abdc6a56d968d279b505491b37976d9bb
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0014580580489360732,
+  "epoch": 0.0018225725611700917,
   "eval_steps": 2,
-  "global_step": 4,
+  "global_step": 5,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -59,6 +59,13 @@
       "eval_samples_per_second": 134.708,
       "eval_steps_per_second": 67.369,
       "step": 4
+    },
+    {
+      "epoch": 0.0018225725611700917,
+      "grad_norm": 3.305025815963745,
+      "learning_rate": 5e-05,
+      "loss": 2.3645,
+      "step": 5
     }
   ],
   "logging_steps": 1,
@@ -73,12 +80,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 142461062086656.0,
+  "total_flos": 178076327608320.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null