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:fa6d6b047eeea5df5dab1d8e4c151017ab0db18412a5df67cc3cb4202bf204a2
+oid sha256:75d400c0066f3b9ccfb100c3a96e794c2e0a1cabe8d909e6708751e9b03711f3
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:460afa554cf4c2546c5515ae968d893fafb1e575550a173b263301b789337b51
+oid sha256:7b93982f479c368fd57db35f8264ca321f2ff628fdca22fd5ea0f3e4d552c3d0
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:89fa8ac371a5d659948365d7c799bf69558c73b93c260685c8661740a2c99b2c
+oid sha256:0e24d535c5c1523f0486038b5930228f33566ca520ba04d10e88741a42965211
 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": 0.004866180048661801,
+  "epoch": 0.006082725060827251,
   "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": 2.597,
       "eval_steps_per_second": 1.299,
       "step": 4
+    },
+    {
+      "epoch": 0.006082725060827251,
+      "grad_norm": 37.6766357421875,
+      "learning_rate": 5e-05,
+      "loss": 57.5199,
+      "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": 5211946034921472.0,
+  "total_flos": 6514932543651840.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null