Training in progress, step 5, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:66ee07d4b1ba6340480d1487f04875bb810f623a46022020f8b8eb3b05d6b538
+oid sha256:1f8860bdc0abf12b2c37be6b393f366bcd961772ffdc9558f3d33e09a2adf564
 size 25192496

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6cb3a55cdb7ed937b6452503c0c411a42521c276366fbe0b5a7e090b279b03c9
+oid sha256:466d3373e377e7dc4e9e4b89d687d62dbd9e9d17aa770bf86124d49389c6efa8
 size 13005114

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": 0.05638766519823789,
+  "epoch": 0.07048458149779736,
   "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": 124.708,
       "eval_steps_per_second": 62.354,
       "step": 4
+    },
+    {
+      "epoch": 0.07048458149779736,
+      "grad_norm": 142.44354248046875,
+      "learning_rate": 5e-05,
+      "loss": 120.5938,
+      "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": 477715790561280.0,
+  "total_flos": 597144738201600.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null