Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:02483fe372d3d242ca62830333ca997bba9389d569cf1d4930144ba7b4656113
+oid sha256:0fb9c3abf02e2998b74dc3a160b5a56ef829464ea107847ea732e873269d580e
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:33dad5b5e6dfbc404d40f0403c8c75cae312fcf87a019c097f4bc4dbf010c147
+oid sha256:72765fcb5a70f95315825938b2e447d806645c5ed18da2282868a17be2bf28ce
 size 320194002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:236dd30a5e26aa624791dbe00b5884cab2d7dcccfd406f5f6c8492945f86d633
+oid sha256:56045fef22a4ec444362f7d077827466d84b58f7233fe3b54db9ba0eb3df1da1
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a62e6ea25099651400ff4a3142a50e40bef5b52ba883be53b2fcb9d1a5b0a98c
+oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.007357674974707992,
+  "epoch": 0.011036512462061988,
   "eval_steps": 8,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -73,6 +73,42 @@
       "learning_rate": 0.00013090169943749476,
       "loss": 7.634,
       "step": 18
+    },
+    {
+      "epoch": 0.0077255587234433916,
+      "grad_norm": 2.283200263977051,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 6.9598,
+      "step": 21
+    },
+    {
+      "epoch": 0.00882920996964959,
+      "grad_norm": 2.059357166290283,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 6.8391,
+      "step": 24
+    },
+    {
+      "epoch": 0.00882920996964959,
+      "eval_loss": 1.6812446117401123,
+      "eval_runtime": 112.5995,
+      "eval_samples_per_second": 10.169,
+      "eval_steps_per_second": 5.089,
+      "step": 24
+    },
+    {
+      "epoch": 0.00993286121585579,
+      "grad_norm": 2.2149431705474854,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 6.698,
+      "step": 27
+    },
+    {
+      "epoch": 0.011036512462061988,
+      "grad_norm": 2.14638614654541,
+      "learning_rate": 0.0,
+      "loss": 6.6779,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -87,12 +123,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 6534646443540480.0,
+  "total_flos": 9801969665310720.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null