Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:689e56aaf984fcdfc4b933e871b56d04cdd4fa8c7abff9a2d9129b074eb6cece
+oid sha256:69314a041afe113035260e2bd8bd73302623cf1b008362654e9c5cc6dbd69b68
 size 125248064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:32b2b81bc20055e2789ae7a34d48bbd73ee0a8a7126174c9e6451384ec13a650
+oid sha256:53a1dd6671f3e4ce251d969dc27e8c102045110232cc36644cacc9feb686eee7
 size 64219860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5bf85c58cca5aae7d759797e66cb053a57988fcfe19dedb65a2573f97c517485
+oid sha256:2b5680ac895463613d91eeb9054dc06bc19db700daeaf5c42ff7984ab49692a6
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ccc7e73cc5879da996ace4c3a10d9efe08a100111973e801d61997747e95e982
+oid sha256:e69e2b49ea642509f0c688c16fb190b7cf27dac0a18903a5e2d1467d0343d8b8
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.012313521193464362,
+  "epoch": 0.015786565632646618,
   "eval_steps": 13,
-  "global_step": 39,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -312,6 +312,83 @@
       "eval_samples_per_second": 18.102,
       "eval_steps_per_second": 9.051,
       "step": 39
+    },
+    {
+      "epoch": 0.012629252506117294,
+      "grad_norm": 2.411217212677002,
+      "learning_rate": 2.9289321881345254e-05,
+      "loss": 4.3786,
+      "step": 40
+    },
+    {
+      "epoch": 0.012944983818770227,
+      "grad_norm": 1.5729023218154907,
+      "learning_rate": 2.3959403439996907e-05,
+      "loss": 3.6625,
+      "step": 41
+    },
+    {
+      "epoch": 0.013260715131423158,
+      "grad_norm": 1.8918485641479492,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 3.5603,
+      "step": 42
+    },
+    {
+      "epoch": 0.01357644644407609,
+      "grad_norm": 2.446108818054199,
+      "learning_rate": 1.4735983564590783e-05,
+      "loss": 3.903,
+      "step": 43
+    },
+    {
+      "epoch": 0.013892177756729024,
+      "grad_norm": 2.3776514530181885,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 3.9599,
+      "step": 44
+    },
+    {
+      "epoch": 0.014207909069381956,
+      "grad_norm": 2.1264560222625732,
+      "learning_rate": 7.612046748871327e-06,
+      "loss": 4.1211,
+      "step": 45
+    },
+    {
+      "epoch": 0.014523640382034889,
+      "grad_norm": 2.0649964809417725,
+      "learning_rate": 4.8943483704846475e-06,
+      "loss": 4.0103,
+      "step": 46
+    },
+    {
+      "epoch": 0.01483937169468782,
+      "grad_norm": 2.101264238357544,
+      "learning_rate": 2.7630079602323442e-06,
+      "loss": 3.6711,
+      "step": 47
+    },
+    {
+      "epoch": 0.015155103007340753,
+      "grad_norm": 2.364389419555664,
+      "learning_rate": 1.231165940486234e-06,
+      "loss": 3.9815,
+      "step": 48
+    },
+    {
+      "epoch": 0.015470834319993685,
+      "grad_norm": 2.1921024322509766,
+      "learning_rate": 3.0826662668720364e-07,
+      "loss": 3.7505,
+      "step": 49
+    },
+    {
+      "epoch": 0.015786565632646618,
+      "grad_norm": 2.30208158493042,
+      "learning_rate": 0.0,
+      "loss": 3.8635,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -326,12 +403,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.242743039852544e+16,
+  "total_flos": 1.591027713441792e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null