Training in progress, step 5, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8417167d69420abf74f37af18127c81d42b256797dfcbfb31fe1ccfae9a87669
+oid sha256:2b29b1fbbeac56b3a46742aad5d34f3a86c459e3e3eff7ef7d0ca9aefaa99d0d
 size 50365768

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d338e01a8b0cbe93889043b8a51abad431b1bb2202634ee20b3f067ad245461
+oid sha256:76065ce529275ce0f83af7d79572057d6eed4bab10e2390172c30fd4337cbada
 size 25859156

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e276bbc7ddfaf29694fe0fb6aa02eea3c75524f34ae16bf55fe332617e85655
+oid sha256:f4c90d3448f423bb5f708e47827c4f7b4b9b76940643d04f84f2a9865c47db60
 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": 0.02323049001814882,
+  "epoch": 0.029038112522686024,
   "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": 35.329,
       "eval_steps_per_second": 17.664,
       "step": 4
+    },
+    {
+      "epoch": 0.029038112522686024,
+      "grad_norm": 7.695745944976807,
+      "learning_rate": 5e-05,
+      "loss": 26.5067,
+      "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": 2937450808737792.0,
+  "total_flos": 3671813510922240.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null