Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8bc37cd1fda8dfd1b39b977dec0658a3efa655517ac13e180a02093a5408beca
+oid sha256:0f91b85724994c13c916ded879f72418c70c4ea027156be84f5cd4c92395e100
 size 108113968

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5271ff8559b10b2c4535ccd083bde78232e76af49079888202ed48428f4cdb2b
+oid sha256:a97c82ff1731a3a1ad44c164ea43fc9f01ab508470a33d190b04c875190b7c0a
 size 55549892

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f4fdcf50e4107dcde767ba8774e49b404a9d984ae9f0c993407d902c3b221015
+oid sha256:fa979fe3d2fe754200d59b353a541573a4cf51bb8e100d8ca9c0bba0b70c95b5
 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": 0.7123287671232876,
+  "epoch": 0.91324200913242,
   "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": 19.081,
       "eval_steps_per_second": 9.955,
       "step": 39
+    },
+    {
+      "epoch": 0.730593607305936,
+      "grad_norm": 0.8844136595726013,
+      "learning_rate": 2.9289321881345254e-05,
+      "loss": 2.2397,
+      "step": 40
+    },
+    {
+      "epoch": 0.7488584474885844,
+      "grad_norm": 1.3105579614639282,
+      "learning_rate": 2.3959403439996907e-05,
+      "loss": 2.3317,
+      "step": 41
+    },
+    {
+      "epoch": 0.7671232876712328,
+      "grad_norm": 0.8636834025382996,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 2.1045,
+      "step": 42
+    },
+    {
+      "epoch": 0.7853881278538812,
+      "grad_norm": 0.9835923910140991,
+      "learning_rate": 1.4735983564590783e-05,
+      "loss": 2.1794,
+      "step": 43
+    },
+    {
+      "epoch": 0.8036529680365296,
+      "grad_norm": 1.2476320266723633,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 2.2903,
+      "step": 44
+    },
+    {
+      "epoch": 0.821917808219178,
+      "grad_norm": 1.1613067388534546,
+      "learning_rate": 7.612046748871327e-06,
+      "loss": 1.8719,
+      "step": 45
+    },
+    {
+      "epoch": 0.8401826484018264,
+      "grad_norm": 1.899326205253601,
+      "learning_rate": 4.8943483704846475e-06,
+      "loss": 2.2471,
+      "step": 46
+    },
+    {
+      "epoch": 0.8584474885844748,
+      "grad_norm": 1.0739811658859253,
+      "learning_rate": 2.7630079602323442e-06,
+      "loss": 2.2019,
+      "step": 47
+    },
+    {
+      "epoch": 0.8767123287671232,
+      "grad_norm": 1.3249667882919312,
+      "learning_rate": 1.231165940486234e-06,
+      "loss": 1.947,
+      "step": 48
+    },
+    {
+      "epoch": 0.8949771689497716,
+      "grad_norm": 1.720015287399292,
+      "learning_rate": 3.0826662668720364e-07,
+      "loss": 2.2611,
+      "step": 49
+    },
+    {
+      "epoch": 0.91324200913242,
+      "grad_norm": 1.1720777750015259,
+      "learning_rate": 0.0,
+      "loss": 2.0832,
+      "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": 8260884309737472.0,
+  "total_flos": 1.0723756650528768e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null