Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7cc50ce2f5a1a084295cbf5b0d731e58f4b289665c29e0eb2db65ccb88cf7869
+oid sha256:0d1a9ad777fa6a20f366bab0f74b70f1fa2a4088ec2f37912c7e1fbf5113966b
 size 50624

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eed9716a07c756be90bc96923190d0c1e710ca6dc3238dc0a04aa8f86ad2bc37
+oid sha256:ed39847993544ab820c7cf805d6e45c78477afb6a4af4852b60915a449206959
 size 118090

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c5288ed9323916daf49e9e619b5ce81ab40c19e01021e3ee0c12210ac8bab7de
+oid sha256:4542ee77b862586921f712605c9da4a157f7c6fb74687d0b6cef8d69e7a87363
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46d68217ddf3e899bf1495ee33b9ec14e2c91ed912ffcb460a7bb01192b04b7d
+oid sha256:f0e9cc72c20ddd925ef39b6005e82a4d8730b1dde32cfcd070d74c83a8a3564a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.012064545317448348,
+  "epoch": 0.018096817976172522,
   "eval_steps": 5,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -89,6 +89,50 @@
       "eval_samples_per_second": 190.954,
       "eval_steps_per_second": 95.614,
       "step": 20
+    },
+    {
+      "epoch": 0.012667772583320766,
+      "grad_norm": 0.027766700834035873,
+      "learning_rate": 4.2178276747988446e-05,
+      "loss": 10.3737,
+      "step": 21
+    },
+    {
+      "epoch": 0.014477454380938018,
+      "grad_norm": 0.037035077810287476,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 10.3747,
+      "step": 24
+    },
+    {
+      "epoch": 0.015080681646810435,
+      "eval_loss": 10.37399673461914,
+      "eval_runtime": 3.6845,
+      "eval_samples_per_second": 189.714,
+      "eval_steps_per_second": 94.993,
+      "step": 25
+    },
+    {
+      "epoch": 0.016287136178555272,
+      "grad_norm": 0.027561597526073456,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 10.3736,
+      "step": 27
+    },
+    {
+      "epoch": 0.018096817976172522,
+      "grad_norm": 0.035397447645664215,
+      "learning_rate": 0.0,
+      "loss": 10.3744,
+      "step": 30
+    },
+    {
+      "epoch": 0.018096817976172522,
+      "eval_loss": 10.3739595413208,
+      "eval_runtime": 3.7296,
+      "eval_samples_per_second": 187.419,
+      "eval_steps_per_second": 93.843,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -103,12 +147,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1046048931840.0,
+  "total_flos": 1569073397760.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null