Training in progress, step 5, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7928cc861b0c29b902b3401ba6bd3ef6b7d27d267766af35ee45f1dd7ed291cb
+oid sha256:6710df1a3fca3351b81b2d981a13c168ac9bf33300a2b8e80812f03aba419686
 size 125248064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e7bcbbffafdf73d3d2f9ebb1b88eca4f3b57af07cab98759686b5340aa2b2ae8
+oid sha256:13d76bd192252394c154e0975e75972ddbc6069f5ad700cd3ff9ecb1cdca9050
 size 64219860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6988304369cf1930141352fe7025e91f20bdfbba03640e6a295c2917f2efb5d3
+oid sha256:82cc5102a07c8294926abd0615e64839b7d89863b274a0c2dd05f224677a3519
 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": 0.06237816764132553,
+  "epoch": 0.07797270955165692,
   "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": 7.897,
       "eval_steps_per_second": 3.948,
       "step": 4
+    },
+    {
+      "epoch": 0.07797270955165692,
+      "grad_norm": 1.8220391273498535,
+      "learning_rate": 5e-05,
+      "loss": 13.5549,
+      "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": 1.005269824831488e+16,
+  "total_flos": 1.258566158647296e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null