Training in progress, step 250, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9043cf3cf905e559f58e8379c7995f62193457a21a059856a4e35d611d96df5e
+oid sha256:3c191e2a28d1a4216971b702265a00031ed6ef14d81fb356749e1e4aee7f395d
 size 125248064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:204e4fd97de4d376e1aa4c7d0835dbc1ca4932dbf4a7697f0faee815f6566c5c
+oid sha256:18f441c08a1e9cfcd14b6672bb68cd721bd8ee9f667cbffb2ddb3bb1adb98e51
 size 64219860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c6862b2b6fb022e891f29f43272bce00ebf06f54860baa1b7d19910269647c7
+oid sha256:44eee6976e705cf87c7b19810814819ba62f5bcc26f8c26f581a0949dea69eed
 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": 0.037422037422037424,
+  "epoch": 0.0495000495000495,
   "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": 11.897,
       "eval_steps_per_second": 5.951,
       "step": 189
+    },
+    {
+      "epoch": 0.03762003762003762,
+      "grad_norm": 1.3049726486206055,
+      "learning_rate": 2.8165064990227252e-05,
+      "loss": 3.5265,
+      "step": 190
+    },
+    {
+      "epoch": 0.0396000396000396,
+      "grad_norm": 1.4380872249603271,
+      "learning_rate": 1.985863781320435e-05,
+      "loss": 3.0763,
+      "step": 200
+    },
+    {
+      "epoch": 0.04158004158004158,
+      "grad_norm": 1.24958074092865,
+      "learning_rate": 1.286812958766106e-05,
+      "loss": 3.0707,
+      "step": 210
+    },
+    {
+      "epoch": 0.04356004356004356,
+      "grad_norm": 2.750286102294922,
+      "learning_rate": 7.308324265397836e-06,
+      "loss": 2.7011,
+      "step": 220
+    },
+    {
+      "epoch": 0.04554004554004554,
+      "grad_norm": 1.8265074491500854,
+      "learning_rate": 3.270513696097055e-06,
+      "loss": 2.7879,
+      "step": 230
+    },
+    {
+      "epoch": 0.04752004752004752,
+      "grad_norm": 1.098848581314087,
+      "learning_rate": 8.209986176753948e-07,
+      "loss": 3.438,
+      "step": 240
+    },
+    {
+      "epoch": 0.0495000495000495,
+      "grad_norm": 1.3819769620895386,
+      "learning_rate": 0.0,
+      "loss": 2.7865,
+      "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": 9.174134924771328e+16,
+  "total_flos": 1.2102892407226368e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null