Training in progress, step 5, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:892b2d42198993db5ab0e3fc87f2fffbb65db2c4e57ccdf362942b8c8eeb1044
+oid sha256:bf9870034814ed6a4ee1ddc03a83543de7ec472a067bd19dd336c652df97f078
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f23d3f96c11941e5df880fb82a6b54111e233bd714cbc64108145fed4c197ae
+oid sha256:009f1a43edc8d741fbce3689bb312785d1e4511e62eb352c0fd4afd41f08da7c
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:51885bfa808d7dd91dfb7a6d29e9430a88ce71253079a7b02ced5e7584658c6b
+oid sha256:de8a4016de67e16078210074b1702667ec06fdbff9c991620f23dca1be359122
 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": 0.0321285140562249,
+  "epoch": 0.040160642570281124,
   "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": 27.627,
       "eval_steps_per_second": 13.813,
       "step": 4
+    },
+    {
+      "epoch": 0.040160642570281124,
+      "grad_norm": 4.761684894561768,
+      "learning_rate": 5e-05,
+      "loss": 24.8143,
+      "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": 3868279449845760.0,
+  "total_flos": 4641935339814912.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null