Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e9c8b48beb1b44bbe242e5765e255df81017706a129a7f2362b03dce9c26f29
+oid sha256:193fa780cea3361b822c7db1f32c859f231a066376ee1eb0a19cafc8136cbd08
 size 188784440

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da8131f23dd066c46419b6c23df1593f4a3fd8a8ba3016d8285807840a41328f
+oid sha256:f7cf53e4d0cad9736633b4ede7760e16dd1c6b2f3190c049ae93a271bd95cb65
 size 377730170

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c84ce4dc5da8a3caa5737d0f76279b5b3f287794923b6b6aca538d8a904f8d13
+oid sha256:8dcd03417cbdbb3727d449b1bf97131aa78e82f225c479e7658bc5c642c852d5
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a62e6ea25099651400ff4a3142a50e40bef5b52ba883be53b2fcb9d1a5b0a98c
+oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0035234529839242457,
+  "epoch": 0.005285179475886369,
   "eval_steps": 8,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -73,6 +73,42 @@
       "learning_rate": 0.00013090169943749476,
       "loss": 2.6688,
       "step": 18
+    },
+    {
+      "epoch": 0.003699625633120458,
+      "grad_norm": 1.4975641965866089,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 2.3158,
+      "step": 21
+    },
+    {
+      "epoch": 0.004228143580709095,
+      "grad_norm": 1.9014939069747925,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 2.6375,
+      "step": 24
+    },
+    {
+      "epoch": 0.004228143580709095,
+      "eval_loss": 0.5634551048278809,
+      "eval_runtime": 354.047,
+      "eval_samples_per_second": 6.753,
+      "eval_steps_per_second": 3.378,
+      "step": 24
+    },
+    {
+      "epoch": 0.004756661528297732,
+      "grad_norm": 1.679165244102478,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 2.4099,
+      "step": 27
+    },
+    {
+      "epoch": 0.005285179475886369,
+      "grad_norm": 1.5690745115280151,
+      "learning_rate": 0.0,
+      "loss": 2.2271,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -87,12 +123,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.71516213854208e+16,
+  "total_flos": 2.515571136528384e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null