Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:315f8cab177079d6e380b6f1cdda7eed7aa465799ae8f2108a8d27f87e9ef5b7
+oid sha256:2afacf7a5e798236cd04f62123437e9dd4b570cb7eea604942a1266e0f25aecb
 size 100059752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a18a323766377d7f9340a7a9699843051bd8d3f1def1038e05e9fd3ea72072a
+oid sha256:c6b69c604fcf160dea6aa8111382e7d080ff68e7494bfc65551a0d9df6b83cd9
 size 51244020

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": 0.0024489296136813534,
+  "epoch": 0.003265239484908471,
   "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": 20.466,
       "eval_steps_per_second": 10.233,
       "step": 15
+    },
+    {
+      "epoch": 0.002612191587926777,
+      "grad_norm": 0.7552852630615234,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 1.5054,
+      "step": 16
+    },
+    {
+      "epoch": 0.0027754535621722005,
+      "grad_norm": 0.5800599455833435,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 1.5831,
+      "step": 17
+    },
+    {
+      "epoch": 0.002938715536417624,
+      "grad_norm": 0.69074946641922,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 1.7167,
+      "step": 18
+    },
+    {
+      "epoch": 0.0031019775106630476,
+      "grad_norm": 0.6885969638824463,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 1.5598,
+      "step": 19
+    },
+    {
+      "epoch": 0.003265239484908471,
+      "grad_norm": 0.647728681564331,
+      "learning_rate": 0.0,
+      "loss": 1.6196,
+      "step": 20
+    },
+    {
+      "epoch": 0.003265239484908471,
+      "eval_loss": 1.6716474294662476,
+      "eval_runtime": 513.1143,
+      "eval_samples_per_second": 20.105,
+      "eval_steps_per_second": 10.052,
+      "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": 1.227876234952704e+16,
+  "total_flos": 1.633983160909824e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null