Training in progress, step 5, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ed894e6074b200d15155ce88c29e8bd413fac20ab364b4223afe263a933bc28
+oid sha256:25ff6686b810260977ba0ac6ea797a14fbaee9ee3b611100165b8e1cb4d27ab6
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f2a9e28c85a4025bbf0058d3aeec2749fc6651e9556b87f959767de0ba59b5ad
+oid sha256:8470e69fa0f8ac739ce7645fab0c3d13c62ec89d2ec442152fd29ece8c6441e0
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:acb5d26b28caf34eea6fedf7adb283f5f5b80894fc1bd08bc9796d4d1c72e8f9
+oid sha256:2bc5e1dcb9806fb5bd7a9c73b9dfbe6e42232a5a91b3ff214050319fb5ca4cad
 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": 0.0022555860999506593,
+  "epoch": 0.0028194826249383236,
   "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": 23.632,
       "eval_steps_per_second": 11.82,
       "step": 4
+    },
+    {
+      "epoch": 0.0028194826249383236,
+      "grad_norm": 1.4141714572906494,
+      "learning_rate": 5e-05,
+      "loss": 20.1202,
+      "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": 3542529601437696.0,
+  "total_flos": 4519779146661888.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null