Training in progress, step 40, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5bc0d70b8248ecf21d87e10dfb317838207b601debca202ab25ba7dfd31c7137
+oid sha256:195a28b2df686a3846aee561c54fadd7212ce9bdd5a1ec0e5edbf8c4aa2faf42
 size 56662952

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da99d45537db9e1224e12843113d68cc627e9128a9d2b7dc8b8d235c773ac175
+oid sha256:029836c3888e274d9a809c2ff38c46c97a8657fe91ba8cc2ab57539de47c3ff8
 size 29091028

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:511c388ecced1bf90534e7c782daa31c1279d66c05f79ca95be901f6e792e195
+oid sha256:c83c4c308d6e06ee88694e3769fdc100ae6fe845c28c9e042e46ab8f2e937ba4
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a9f7d71d2520220b24b14e74f15b8fc66bb3fd91884b9f80b2d1815e9fc2c23c
+oid sha256:2d01151db1fc4f9c05131abecdc90435e3aab7eb2c3021fc926311286e779587
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0017061934823408974,
+  "epoch": 0.003412386964681795,
   "eval_steps": 5,
-  "global_step": 20,
+  "global_step": 40,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -89,6 +89,87 @@
       "eval_samples_per_second": 30.387,
       "eval_steps_per_second": 7.597,
       "step": 20
+    },
+    {
+      "epoch": 0.0017915031564579424,
+      "grad_norm": 1.7368289232254028,
+      "learning_rate": 0.00019876883405951377,
+      "loss": 5.4112,
+      "step": 21
+    },
+    {
+      "epoch": 0.002047432178809077,
+      "grad_norm": 1.4698233604431152,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 5.5543,
+      "step": 24
+    },
+    {
+      "epoch": 0.0021327418529261217,
+      "eval_loss": 2.7554147243499756,
+      "eval_runtime": 162.4735,
+      "eval_samples_per_second": 30.38,
+      "eval_steps_per_second": 7.595,
+      "step": 25
+    },
+    {
+      "epoch": 0.0023033612011602116,
+      "grad_norm": 1.428360104560852,
+      "learning_rate": 0.00014539904997395468,
+      "loss": 5.7486,
+      "step": 27
+    },
+    {
+      "epoch": 0.0025592902235113462,
+      "grad_norm": 1.2972009181976318,
+      "learning_rate": 0.0001,
+      "loss": 5.8351,
+      "step": 30
+    },
+    {
+      "epoch": 0.0025592902235113462,
+      "eval_loss": 2.7425527572631836,
+      "eval_runtime": 162.4527,
+      "eval_samples_per_second": 30.384,
+      "eval_steps_per_second": 7.596,
+      "step": 30
+    },
+    {
+      "epoch": 0.002815219245862481,
+      "grad_norm": 1.8566501140594482,
+      "learning_rate": 5.4600950026045326e-05,
+      "loss": 5.6888,
+      "step": 33
+    },
+    {
+      "epoch": 0.0029858385940965708,
+      "eval_loss": 2.738285779953003,
+      "eval_runtime": 162.4613,
+      "eval_samples_per_second": 30.383,
+      "eval_steps_per_second": 7.596,
+      "step": 35
+    },
+    {
+      "epoch": 0.0030711482682136155,
+      "grad_norm": 1.3856315612792969,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 5.6469,
+      "step": 36
+    },
+    {
+      "epoch": 0.00332707729056475,
+      "grad_norm": 1.330557942390442,
+      "learning_rate": 1.231165940486234e-06,
+      "loss": 5.5003,
+      "step": 39
+    },
+    {
+      "epoch": 0.003412386964681795,
+      "eval_loss": 2.73707914352417,
+      "eval_runtime": 162.6995,
+      "eval_samples_per_second": 30.338,
+      "eval_steps_per_second": 7.585,
+      "step": 40
     }
   ],
   "logging_steps": 3,
@@ -103,12 +184,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1382323480166400.0,
+  "total_flos": 2674495429017600.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null