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:d231d37c5d5030a71e7389d19f5c4d5166f96c9aed876a63b0d45ad6606bb326
+oid sha256:7bc11ec775736ed09d6e0dd13fefe3e5cfa2f72ad59dede6fa011d5b569b63e1
 size 125040

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e509882135bf59b8d49a188f9841257f89347dfbfa05ec3a720fb7906a4adbf8
+oid sha256:df2f5d2802b02ecd7864867ca12b76d2c7667e5a43dcf384068cf609f09dc7d4
 size 162868

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff5440c0314dadc3defe4b4803f353543d71edfcba882e67961bec9458fb6240
+oid sha256:9ea24ba22f005ab5531315a7c25fe17ce3b0d82d32e4d057cd4a8d9beeaa0eb4
 size 14244

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": 0.631578947368421,
+  "epoch": 0.8421052631578947,
   "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": 145.805,
       "eval_steps_per_second": 74.681,
       "step": 15
+    },
+    {
+      "epoch": 0.6736842105263158,
+      "grad_norm": 5.448623180389404,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 177.5,
+      "step": 16
+    },
+    {
+      "epoch": 0.7157894736842105,
+      "grad_norm": 5.380776405334473,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 177.625,
+      "step": 17
+    },
+    {
+      "epoch": 0.7578947368421053,
+      "grad_norm": 5.429207801818848,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 177.6875,
+      "step": 18
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 5.550320625305176,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 177.3125,
+      "step": 19
+    },
+    {
+      "epoch": 0.8421052631578947,
+      "grad_norm": 5.13893461227417,
+      "learning_rate": 0.0,
+      "loss": 177.4375,
+      "step": 20
+    },
+    {
+      "epoch": 0.8421052631578947,
+      "eval_loss": 11.105182647705078,
+      "eval_runtime": 0.2631,
+      "eval_samples_per_second": 155.807,
+      "eval_steps_per_second": 79.803,
+      "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": 578688122880.0,
+  "total_flos": 771584163840.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null