Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e26b285509f7cf3169e77f3aec8c0ba0880ba284f13653f6d6ceee9bef08537
+oid sha256:4ad239b0860e8a45b1ea236a962550ae8b42c5d7882d45c62ca8f4cebc5c36e7
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e8222153c5235889de053e1236e66eb6782f51ac30dfe6cdd7bef2b20d89dbe
+oid sha256:9633590a72b03a50d58219805f60223c0ef386700d1d2b28e4a58846e051cf8f
 size 43122580

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": 0.000925436786883476,
+  "epoch": 0.0012339157158446346,
   "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": 14.875,
       "eval_steps_per_second": 7.438,
       "step": 15
+    },
+    {
+      "epoch": 0.0009871325726757076,
+      "grad_norm": 84.9726791381836,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 25.0039,
+      "step": 16
+    },
+    {
+      "epoch": 0.0010488283584679395,
+      "grad_norm": 84.03262329101562,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 23.4361,
+      "step": 17
+    },
+    {
+      "epoch": 0.0011105241442601712,
+      "grad_norm": 79.8850326538086,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 23.1127,
+      "step": 18
+    },
+    {
+      "epoch": 0.0011722199300524029,
+      "grad_norm": 64.62732696533203,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 17.9182,
+      "step": 19
+    },
+    {
+      "epoch": 0.0012339157158446346,
+      "grad_norm": 69.32557678222656,
+      "learning_rate": 0.0,
+      "loss": 25.504,
+      "step": 20
+    },
+    {
+      "epoch": 0.0012339157158446346,
+      "eval_loss": 1.5561696290969849,
+      "eval_runtime": 1953.1879,
+      "eval_samples_per_second": 13.977,
+      "eval_steps_per_second": 6.989,
+      "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": 1.051603079528448e+16,
+  "total_flos": 1.402137439371264e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null