Training in progress, step 250, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:34d14ba3169a77e7be0c0c4bf9fe35fd60c43fae3624e4853c68a6c2e958f1f7
+oid sha256:586a6bab93e3f7a333fe7aa6f068bbdafc3277667823939c8946e8a4dc086122
 size 108113968

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:051314e0d43f4b796597cb5ee492155d94ee9957a1ad80ebccee60251e07d6ff
+oid sha256:eb87abc18359836904c10609f31e5a6a7a206589dc0051db52fc75cf7ee5f244
 size 55549892

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bf8cc74578a2cc9339639ae1a1326dde9be36a9f13d56f938990af891ca51b08
+oid sha256:e3bed82ca8ec753db23c4480c558c3877f20b7f5c87964131a57d7f9d4a8b1bc
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:65558e26afbfb87dd1928966282919939bdee4084add607d42e008ed52d680cd
+oid sha256:6088f970b1f0429ad85e576795204ef9269ce142d6ce9c2595b5649efde833b6
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.007817185399648433,
+  "epoch": 0.010340192327577293,
   "eval_steps": 63,
-  "global_step": 189,
+  "global_step": 250,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -165,6 +165,55 @@
       "eval_samples_per_second": 15.272,
       "eval_steps_per_second": 7.636,
       "step": 189
+    },
+    {
+      "epoch": 0.007858546168958742,
+      "grad_norm": 1.33353590965271,
+      "learning_rate": 2.8165064990227252e-05,
+      "loss": 0.3573,
+      "step": 190
+    },
+    {
+      "epoch": 0.008272153862061834,
+      "grad_norm": 3.5792007446289062,
+      "learning_rate": 1.985863781320435e-05,
+      "loss": 0.4507,
+      "step": 200
+    },
+    {
+      "epoch": 0.008685761555164926,
+      "grad_norm": 2.147625684738159,
+      "learning_rate": 1.286812958766106e-05,
+      "loss": 0.3595,
+      "step": 210
+    },
+    {
+      "epoch": 0.009099369248268019,
+      "grad_norm": 2.4549238681793213,
+      "learning_rate": 7.308324265397836e-06,
+      "loss": 0.2863,
+      "step": 220
+    },
+    {
+      "epoch": 0.009512976941371109,
+      "grad_norm": 0.953778862953186,
+      "learning_rate": 3.270513696097055e-06,
+      "loss": 0.2952,
+      "step": 230
+    },
+    {
+      "epoch": 0.009926584634474201,
+      "grad_norm": 1.9058080911636353,
+      "learning_rate": 8.209986176753948e-07,
+      "loss": 0.515,
+      "step": 240
+    },
+    {
+      "epoch": 0.010340192327577293,
+      "grad_norm": 1.1950501203536987,
+      "learning_rate": 0.0,
+      "loss": 0.3524,
+      "step": 250
     }
   ],
   "logging_steps": 10,
@@ -179,12 +228,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2.5808849737875456e+16,
+  "total_flos": 3.381318484544717e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null