Training in progress, step 5, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b37b62ab1f119a074195409757e73cf5792b9992af587208f8bf3abb60a3a44
+oid sha256:2982a5f89cc07d5ad27c0095e5630e4764a77d4071edc6d4b45126d20ddf27d2
 size 125248064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c54523f7133f4ef754e77930dddb0f2473a6b426c3f7423cc348eb2ed355ecd9
+oid sha256:7d68b30729d922657a6eeb814ed69c91fa21f49ad7200028898c6db41d637c08
 size 64219860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:877be02e72c90068c53b4cd4ac5f76683c34f6c6e1f29413737e7203851c9d33
+oid sha256:b52214f9bd9fd90e146416d19db727ff822d3ff4dfe457467cf1dd46cfde3948
 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": 0.0006846457493126798,
+  "epoch": 0.0008558071866408498,
   "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": 8.445,
       "eval_steps_per_second": 4.223,
       "step": 4
+    },
+    {
+      "epoch": 0.0008558071866408498,
+      "grad_norm": 1.4983941316604614,
+      "learning_rate": 5e-05,
+      "loss": 19.3913,
+      "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": 1.013185335263232e+16,
+  "total_flos": 1.26648166907904e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null