Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ae37163bb06e09a013c201128dfe0068866ebda63f95297be02e61a08f74285
+oid sha256:214c78210c261c6ae2f4922df59937a0b59ae914976a7f12b7283db66d2b4cd7
 size 167832240

last-checkpoint/optimizer.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a06c7b5e8a71897fa59cd0b1b4ce6f499b6ac27f8240078d0eb27d97ca927638
+oid sha256:28797cc871fd3fda681fcfea1e9d60e7293fa802f225d4ec9e33785114a90f91
 size 335945362

last-checkpoint/pytorch_model_fsdp.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:18bc07941fefd40291133ceb556e8920bb46b84cc04fe0380db6edbfb34487d4
+oid sha256:202c97ed9da99d3bd3fbd279bd92ddff105809d3a1cb7280bd40d3d86154202d
 size 167939550

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7838bdf54360b703af24def5551264f7a7af5b9c8d73db80e1c723ea01150592
+oid sha256:d623d1ef75e6fda4b07e7a189f60857403d4c7bb847b5a54f3dbfb47e7c303af
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:64cf9bd29db2d9cc051450ea6e264744bc44af69b99ff1331fc8e223a3c90e58
+oid sha256:4c4e57641fefec2932abaa5e11dbf65801420531a3b7425c7291de4476d647ea
 size 14512

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:337059d54254bc9389c938dc292312990ce226dd122bd2ed92af370c28fd9326
+oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.02655356813571824,
+  "epoch": 0.029503964595242484,
   "eval_steps": 3,
-  "global_step": 27,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -277,6 +277,35 @@
       "eval_samples_per_second": 10.649,
       "eval_steps_per_second": 2.665,
       "step": 27
+    },
+    {
+      "epoch": 0.02753703362222632,
+      "grad_norm": 0.9006595611572266,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 1.1203,
+      "step": 28
+    },
+    {
+      "epoch": 0.0285204991087344,
+      "grad_norm": 0.9214680790901184,
+      "learning_rate": 3.1416838871368924e-06,
+      "loss": 1.1674,
+      "step": 29
+    },
+    {
+      "epoch": 0.029503964595242484,
+      "grad_norm": 0.9982773661613464,
+      "learning_rate": 7.885298685522235e-07,
+      "loss": 1.1062,
+      "step": 30
+    },
+    {
+      "epoch": 0.029503964595242484,
+      "eval_loss": 1.8830240964889526,
+      "eval_runtime": 320.1496,
+      "eval_samples_per_second": 10.698,
+      "eval_steps_per_second": 2.677,
+      "step": 30
     }
   ],
   "logging_steps": 1,
@@ -291,12 +320,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.963246895287501e+16,
+  "total_flos": 2.290353939939328e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null