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:d9f420576a4c38b7f0caeb00b997f2b217a984e312705919ebfcab6e750e367d
+oid sha256:d12ca86f3e3dfd0a8ef3cb54bd453a50166ee42ae58b687ef9ded8fbea14d772
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:edc6f294f92fa4887c8d62075d64c9f49026f6cf6462c37791b39122cf6ee595
+oid sha256:32a9fb25ef89daa678207930c7c4434f8094354a42c3924e110775bfda93bb4d
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aef39db986732c6dd385c8a7d12f7c9b251f0e8f2086db98fb9d7b93c185337c
+oid sha256:6038738b834ec4ea5f7815ea238a57c5d168a5783b1150ff1748656412250738
 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": 0.000842948211369264,
+  "epoch": 0.001264422317053896,
   "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": 0.9335,
       "step": 18
+    },
+    {
+      "epoch": 0.0008850956219377273,
+      "grad_norm": 0.7344328761100769,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 0.9045,
+      "step": 21
+    },
+    {
+      "epoch": 0.0010115378536431168,
+      "grad_norm": 0.6354114413261414,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 0.9577,
+      "step": 24
+    },
+    {
+      "epoch": 0.0010115378536431168,
+      "eval_loss": 0.8802497982978821,
+      "eval_runtime": 613.2531,
+      "eval_samples_per_second": 16.29,
+      "eval_steps_per_second": 8.145,
+      "step": 24
+    },
+    {
+      "epoch": 0.0011379800853485065,
+      "grad_norm": 0.5660151243209839,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 0.7753,
+      "step": 27
+    },
+    {
+      "epoch": 0.001264422317053896,
+      "grad_norm": 0.9398247599601746,
+      "learning_rate": 0.0,
+      "loss": 1.0187,
+      "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": 7882552387829760.0,
+  "total_flos": 1.2148404268302336e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null