Training in progress, step 26, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea619bf04b3a8248ef7ee34abcb246789dca5a794b7747307fddce61f0cc7260
+oid sha256:fb2f4f179e39ab57283eb45b956f51fc538ae88828f13ae7ad366a4bd239001c
 size 41581360

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f099cfb9007e8bc6dad029a8fc453476368a360bf030f962a248e5cb1979f86
+oid sha256:2260d881cb30b0a70d19b81020c483791b462d9f32e59030eb45a0458d51949d
 size 21505540

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c6d67a0233c2da15c65c815c1791fe0448e2634e428be1e458d278e11ac4fa74
+oid sha256:79e434457798f9692151fe018459b1bda48cd1e999a3dd276a4432fd1d9a599e
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea3a68034a6fca5f7c1565a9344e41aadbdff3752a8799ae94336c8c84c6d63d
+oid sha256:fa0fde01e60897f55f4ebaca5a490a1a483a2c53b2ae8e7543860a62c5b3298c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.03307888040712468,
+  "epoch": 0.06615776081424936,
   "eval_steps": 13,
-  "global_step": 13,
+  "global_step": 26,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -114,6 +114,105 @@
       "eval_samples_per_second": 39.744,
       "eval_steps_per_second": 19.872,
       "step": 13
+    },
+    {
+      "epoch": 0.035623409669211195,
+      "grad_norm": 3.122359275817871,
+      "learning_rate": 4.877641290737884e-05,
+      "loss": 0.7318,
+      "step": 14
+    },
+    {
+      "epoch": 0.03816793893129771,
+      "grad_norm": 5.089092254638672,
+      "learning_rate": 4.8096988312782174e-05,
+      "loss": 0.8987,
+      "step": 15
+    },
+    {
+      "epoch": 0.04071246819338423,
+      "grad_norm": 2.803917407989502,
+      "learning_rate": 4.72751631047092e-05,
+      "loss": 0.5268,
+      "step": 16
+    },
+    {
+      "epoch": 0.043256997455470736,
+      "grad_norm": 2.718916654586792,
+      "learning_rate": 4.6316004108852305e-05,
+      "loss": 0.6317,
+      "step": 17
+    },
+    {
+      "epoch": 0.04580152671755725,
+      "grad_norm": 2.230231285095215,
+      "learning_rate": 4.522542485937369e-05,
+      "loss": 0.2857,
+      "step": 18
+    },
+    {
+      "epoch": 0.04834605597964377,
+      "grad_norm": 1.5982710123062134,
+      "learning_rate": 4.401014914000078e-05,
+      "loss": 0.1697,
+      "step": 19
+    },
+    {
+      "epoch": 0.05089058524173028,
+      "grad_norm": 1.402782917022705,
+      "learning_rate": 4.267766952966369e-05,
+      "loss": 0.2827,
+      "step": 20
+    },
+    {
+      "epoch": 0.05343511450381679,
+      "grad_norm": 1.7604286670684814,
+      "learning_rate": 4.123620120825459e-05,
+      "loss": 0.1834,
+      "step": 21
+    },
+    {
+      "epoch": 0.05597964376590331,
+      "grad_norm": 4.199867248535156,
+      "learning_rate": 3.969463130731183e-05,
+      "loss": 0.4652,
+      "step": 22
+    },
+    {
+      "epoch": 0.058524173027989825,
+      "grad_norm": 1.1508660316467285,
+      "learning_rate": 3.8062464117898724e-05,
+      "loss": 0.1081,
+      "step": 23
+    },
+    {
+      "epoch": 0.061068702290076333,
+      "grad_norm": 1.6623399257659912,
+      "learning_rate": 3.634976249348867e-05,
+      "loss": 0.1578,
+      "step": 24
+    },
+    {
+      "epoch": 0.06361323155216285,
+      "grad_norm": 1.1933339834213257,
+      "learning_rate": 3.456708580912725e-05,
+      "loss": 0.1515,
+      "step": 25
+    },
+    {
+      "epoch": 0.06615776081424936,
+      "grad_norm": 1.6038551330566406,
+      "learning_rate": 3.272542485937369e-05,
+      "loss": 0.2152,
+      "step": 26
+    },
+    {
+      "epoch": 0.06615776081424936,
+      "eval_loss": 0.18286243081092834,
+      "eval_runtime": 4.0988,
+      "eval_samples_per_second": 40.499,
+      "eval_steps_per_second": 20.25,
+      "step": 26
     }
   ],
   "logging_steps": 1,
@@ -133,7 +232,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 650126529921024.0,
+  "total_flos": 1300253059842048.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null