Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:adb3c156fc252694aec80509418baa36b78944d63295e7fdb79b390073055b10
+oid sha256:39616f97eac3ced2aca1fe61b2c07e4273b937087c4bbc8158e386a7337c64ea
 size 50503544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:660decfe805cc7ea33c57cbaa16f176dda37928ec05e18d1a561831865bc82f8
+oid sha256:723f11a2b1b8e390a42b0518b5458e2913b358a4d9fb6f76e928cc43dae463f3
 size 25986148

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d663cf82722c84e3314cb4000fba516db1f2170d5b76497c7310571e43f5b82
+oid sha256:a75ce7aed09fc39369efb67be97904d9741560e5cbb9055a4b14bb9dc6105a59
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a5c429039c67e17dc7a7bd38f4cb517c33028d543d23edda39c1a6193e218c8
+oid sha256:ff89adc403dff760938458ece81f75a781e317763a5b2256aaf5f942a4ae4899
 size 14512

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff2736979009751c0c6b0ddcc5f6544d6f723aa752b4798eab0b70fb76cf0083
+oid sha256:532138a5ca880d8da393ae449e5715b2766def36b8838785ca08d07228b119b7
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.04541154210028382,
+  "epoch": 0.06054872280037843,
   "eval_steps": 5,
-  "global_step": 15,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -144,6 +144,49 @@
       "eval_samples_per_second": 40.526,
       "eval_steps_per_second": 10.141,
       "step": 15
+    },
+    {
+      "epoch": 0.048438978240302744,
+      "grad_norm": 2.373675584793091,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 5.585,
+      "step": 16
+    },
+    {
+      "epoch": 0.051466414380321665,
+      "grad_norm": 2.601724624633789,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 5.5902,
+      "step": 17
+    },
+    {
+      "epoch": 0.054493850520340587,
+      "grad_norm": 2.4370365142822266,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 5.51,
+      "step": 18
+    },
+    {
+      "epoch": 0.05752128666035951,
+      "grad_norm": 2.936497449874878,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 5.4948,
+      "step": 19
+    },
+    {
+      "epoch": 0.06054872280037843,
+      "grad_norm": 3.4013614654541016,
+      "learning_rate": 0.0,
+      "loss": 5.4982,
+      "step": 20
+    },
+    {
+      "epoch": 0.06054872280037843,
+      "eval_loss": 5.492336750030518,
+      "eval_runtime": 54.9414,
+      "eval_samples_per_second": 40.516,
+      "eval_steps_per_second": 10.138,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -158,12 +201,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 4.940970105765888e+16,
+  "total_flos": 6.587960141021184e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null