Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:73c29b9e275fcfdc9f3f386092e53c5011b7375df7ef561fd867997704aa871c
+oid sha256:33f78eaf5246ced2b191c6d399665aa2b2cc1146004eefc59163630b1b822dca
 size 81576

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c66a366b18b08a7f981d9bec98b5d66f14b90694d6a97e57375b5d75eaa5b34
+oid sha256:6cd4985b940ebfa8acce07dc09a39639895614c0626fcbf41b8a837f19acb905
 size 173094

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c1039e96a4ec12087edaa8ab2d18eba7c359b91687856664d415beaa872acc5
+oid sha256:85060d38305da5842ce5b70373bb3d7952ad87015fdb071fa07cc8695909737b
 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": 0.0028495753036807013,
+  "epoch": 0.0036533016713855147,
   "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": 273.807,
       "eval_steps_per_second": 136.927,
       "step": 39
+    },
+    {
+      "epoch": 0.0029226413371084116,
+      "grad_norm": 0.4572875201702118,
+      "learning_rate": 2.9289321881345254e-05,
+      "loss": 10.7623,
+      "step": 40
+    },
+    {
+      "epoch": 0.002995707370536122,
+      "grad_norm": 0.45184326171875,
+      "learning_rate": 2.3959403439996907e-05,
+      "loss": 10.7694,
+      "step": 41
+    },
+    {
+      "epoch": 0.0030687734039638323,
+      "grad_norm": 0.4599740207195282,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 10.7655,
+      "step": 42
+    },
+    {
+      "epoch": 0.0031418394373915427,
+      "grad_norm": 0.4575888216495514,
+      "learning_rate": 1.4735983564590783e-05,
+      "loss": 10.7638,
+      "step": 43
+    },
+    {
+      "epoch": 0.003214905470819253,
+      "grad_norm": 0.4490920901298523,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 10.7672,
+      "step": 44
+    },
+    {
+      "epoch": 0.0032879715042469634,
+      "grad_norm": 0.44325825572013855,
+      "learning_rate": 7.612046748871327e-06,
+      "loss": 10.7705,
+      "step": 45
+    },
+    {
+      "epoch": 0.0033610375376746733,
+      "grad_norm": 0.43270397186279297,
+      "learning_rate": 4.8943483704846475e-06,
+      "loss": 10.7745,
+      "step": 46
+    },
+    {
+      "epoch": 0.0034341035711023837,
+      "grad_norm": 0.467824786901474,
+      "learning_rate": 2.7630079602323442e-06,
+      "loss": 10.7668,
+      "step": 47
+    },
+    {
+      "epoch": 0.003507169604530094,
+      "grad_norm": 0.4718198776245117,
+      "learning_rate": 1.231165940486234e-06,
+      "loss": 10.7651,
+      "step": 48
+    },
+    {
+      "epoch": 0.0035802356379578044,
+      "grad_norm": 0.48334893584251404,
+      "learning_rate": 3.0826662668720364e-07,
+      "loss": 10.7576,
+      "step": 49
+    },
+    {
+      "epoch": 0.0036533016713855147,
+      "grad_norm": 0.45176786184310913,
+      "learning_rate": 0.0,
+      "loss": 10.7631,
+      "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": 6377799548928.0,
+  "total_flos": 8182450225152.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null