Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f0e1cad118651e9e13382041b1f3deb412415791126ce23d4753c6f29503681
+oid sha256:4b56d57f70ac0ee2d2438d31bab2caefcb5451015de71bf8f6a04fe0721386e5
 size 41581360

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:24491a11bf8d7a14086fd1cae556664c30d7cfcb0926c814675623b36f1a06d3
+oid sha256:631ce313fa45564608cc3751e9a057bc6af98d80adec2b3503f2c7236db64cb9
 size 83372758

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:794880b382377c2c7f11356737e98f7e6f84270c7841235cd7da557833418c10
+oid sha256:ebc0854b7f90d3d89bad59e643f8ede1be48c2b7f392d043acfeb4c69061bf41
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef527702b4e2147a500c0b29beb26751d245ebb60338b3910b449b6549ac4d59
+oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.003771450122572129,
+  "epoch": 0.007542900245144258,
   "eval_steps": 5,
-  "global_step": 15,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -74,6 +74,65 @@
       "eval_samples_per_second": 9.036,
       "eval_steps_per_second": 4.521,
       "step": 15
+    },
+    {
+      "epoch": 0.004525740147086555,
+      "grad_norm": 0.2652558982372284,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 0.598,
+      "step": 18
+    },
+    {
+      "epoch": 0.005028600163429505,
+      "eval_loss": 0.6620884537696838,
+      "eval_runtime": 185.462,
+      "eval_samples_per_second": 9.031,
+      "eval_steps_per_second": 4.518,
+      "step": 20
+    },
+    {
+      "epoch": 0.005280030171600981,
+      "grad_norm": 0.2349843829870224,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 0.6841,
+      "step": 21
+    },
+    {
+      "epoch": 0.006034320196115406,
+      "grad_norm": 0.19294080138206482,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 0.6622,
+      "step": 24
+    },
+    {
+      "epoch": 0.006285750204286881,
+      "eval_loss": 0.649798572063446,
+      "eval_runtime": 185.4412,
+      "eval_samples_per_second": 9.033,
+      "eval_steps_per_second": 4.519,
+      "step": 25
+    },
+    {
+      "epoch": 0.006788610220629833,
+      "grad_norm": 0.17021793127059937,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 0.5969,
+      "step": 27
+    },
+    {
+      "epoch": 0.007542900245144258,
+      "grad_norm": 0.17728255689144135,
+      "learning_rate": 0.0,
+      "loss": 0.6806,
+      "step": 30
+    },
+    {
+      "epoch": 0.007542900245144258,
+      "eval_loss": 0.6474659442901611,
+      "eval_runtime": 185.4886,
+      "eval_samples_per_second": 9.03,
+      "eval_steps_per_second": 4.518,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -88,12 +147,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 3000583984250880.0,
+  "total_flos": 6001167968501760.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null