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:e89293597f61f414793c14757460cc291b775ee0f14434a8fb2291bdf032564a
+oid sha256:6dbc51a8589ef2ad702e7efb5eeeb3645ace9c477d11e7dd311b5c7a23dd6ba1
 size 28548400

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3336e597a0019f41fdee9e7b66eb766b7f4df84a7c675633b3649953ae24bf46
+oid sha256:b369ec1f8b95768079662fe87751a293ab7fd3a9834c71f18529ddf4767babea
 size 57261498

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f64149401f05956621f3966f029d91fa07bc1800e1df081a442f9c6740ae3a01
+oid sha256:acb98080a4d1c4b177c2a8f902398133bab7f4eda405c9063fc69f7bb582dede
 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": 0.005974905397331209,
+  "epoch": 0.011949810794662417,
   "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": 66.543,
       "eval_steps_per_second": 33.272,
       "step": 15
+    },
+    {
+      "epoch": 0.007169886476797451,
+      "grad_norm": 9.679789543151855,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 17.8988,
+      "step": 18
+    },
+    {
+      "epoch": 0.007966540529774946,
+      "eval_loss": 4.2372236251831055,
+      "eval_runtime": 15.9685,
+      "eval_samples_per_second": 66.255,
+      "eval_steps_per_second": 33.128,
+      "step": 20
+    },
+    {
+      "epoch": 0.008364867556263693,
+      "grad_norm": 9.835699081420898,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 17.8623,
+      "step": 21
+    },
+    {
+      "epoch": 0.009559848635729935,
+      "grad_norm": 9.328329086303711,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 17.2585,
+      "step": 24
+    },
+    {
+      "epoch": 0.009958175662218682,
+      "eval_loss": 4.13242769241333,
+      "eval_runtime": 15.958,
+      "eval_samples_per_second": 66.299,
+      "eval_steps_per_second": 33.15,
+      "step": 25
+    },
+    {
+      "epoch": 0.010754829715196175,
+      "grad_norm": 8.610879898071289,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 16.9122,
+      "step": 27
+    },
+    {
+      "epoch": 0.011949810794662417,
+      "grad_norm": 8.168183326721191,
+      "learning_rate": 0.0,
+      "loss": 16.8184,
+      "step": 30
+    },
+    {
+      "epoch": 0.011949810794662417,
+      "eval_loss": 4.110958099365234,
+      "eval_runtime": 15.9047,
+      "eval_samples_per_second": 66.521,
+      "eval_steps_per_second": 33.261,
+      "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": 228914374901760.0,
+  "total_flos": 457828749803520.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null