Training in progress, step 250, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c9fe04394a9e1b9b7d0ef6a5f0abc5815ebbbcde464c1b73f66316ed810a01a
+oid sha256:9884b9c786aae4699e10cf282d40cb5f1c50e6f1cb2e8bd354d1213c172521ee
 size 26008

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a6fb308683751f7a3298bba7c0e9ba7953fc690f4d1b2d7514c20d4ba10fd62
+oid sha256:370d2de3f96e560118243db6b309a03a3381afb0af56c61acf47ca87aef9121a
 size 61926

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b073eae0856d95a78bd1210e484de480f18e699d417df6566c139d5389912738
+oid sha256:e2edc0261f7034ce0d71cea4f289a97e7923584b1d4870351bbf4900337528d8
 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": 0.043548387096774194,
+  "epoch": 0.0576036866359447,
   "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": 222.85,
       "eval_steps_per_second": 111.425,
       "step": 189
+    },
+    {
+      "epoch": 0.04377880184331797,
+      "grad_norm": 0.07347025722265244,
+      "learning_rate": 2.8165064990227252e-05,
+      "loss": 11.9135,
+      "step": 190
+    },
+    {
+      "epoch": 0.04608294930875576,
+      "grad_norm": 0.059106022119522095,
+      "learning_rate": 1.985863781320435e-05,
+      "loss": 11.9135,
+      "step": 200
+    },
+    {
+      "epoch": 0.04838709677419355,
+      "grad_norm": 0.09761878848075867,
+      "learning_rate": 1.286812958766106e-05,
+      "loss": 11.9121,
+      "step": 210
+    },
+    {
+      "epoch": 0.05069124423963134,
+      "grad_norm": 0.0723123848438263,
+      "learning_rate": 7.308324265397836e-06,
+      "loss": 11.9143,
+      "step": 220
+    },
+    {
+      "epoch": 0.052995391705069124,
+      "grad_norm": 0.05200246348977089,
+      "learning_rate": 3.270513696097055e-06,
+      "loss": 11.9119,
+      "step": 230
+    },
+    {
+      "epoch": 0.055299539170506916,
+      "grad_norm": 0.06363704055547714,
+      "learning_rate": 8.209986176753948e-07,
+      "loss": 11.9129,
+      "step": 240
+    },
+    {
+      "epoch": 0.0576036866359447,
+      "grad_norm": 0.07390929013490677,
+      "learning_rate": 0.0,
+      "loss": 11.9155,
+      "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": 23327244288.0,
+  "total_flos": 30681415680.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null