Training in progress, step 26, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:97bb5ef0995aa795d131b41a1e68558748eb47463eca59a4cce6bac254ab1430
+oid sha256:7cb9718c1a8a0bf8da47033043d4a70251149b9da824bb2ed243a3dd164003a8
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d529acaf7d180ca823ee374c53d807f9801e1ee71fd90965e4daa94f1c25ed9c
+oid sha256:b04779d32c92be2cb6498cf24d3f55b98c60d72cd2d6986135e0d87376aaf5d3
 size 85723284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bdde3ec3ee1ba7531772170d89a5d7f54043d0790ffa76d22a3a219e00fe00f9
+oid sha256:3c103f85206916bbddbfdec4d0ebb18b19e3d0dd8d88c9b4c12898c57e206a7e
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4395bafb1cf8adc0d9dbfe550d1b98763496e37a8fadb76c1ca1168a4a757f4e
+oid sha256:37841e69eda911caeb33edeefa0b2f140e72dcce247aeb757b2fe89c00d7887b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.01015228426395939,
+  "epoch": 0.02030456852791878,
   "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": 7.17,
       "eval_steps_per_second": 3.587,
       "step": 13
+    },
+    {
+      "epoch": 0.010933229207340883,
+      "grad_norm": 70.08533477783203,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 17.0262,
+      "step": 14
+    },
+    {
+      "epoch": 0.011714174150722375,
+      "grad_norm": 69.94759368896484,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 18.1821,
+      "step": 15
+    },
+    {
+      "epoch": 0.012495119094103866,
+      "grad_norm": 58.61181640625,
+      "learning_rate": 9.45503262094184e-05,
+      "loss": 17.1924,
+      "step": 16
+    },
+    {
+      "epoch": 0.013276064037485357,
+      "grad_norm": 54.452816009521484,
+      "learning_rate": 9.263200821770461e-05,
+      "loss": 14.6744,
+      "step": 17
+    },
+    {
+      "epoch": 0.014057008980866849,
+      "grad_norm": 67.27265930175781,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 17.592,
+      "step": 18
+    },
+    {
+      "epoch": 0.01483795392424834,
+      "grad_norm": 51.187679290771484,
+      "learning_rate": 8.802029828000156e-05,
+      "loss": 20.2565,
+      "step": 19
+    },
+    {
+      "epoch": 0.015618898867629832,
+      "grad_norm": 45.95616912841797,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 16.9602,
+      "step": 20
+    },
+    {
+      "epoch": 0.016399843811011325,
+      "grad_norm": 46.94184112548828,
+      "learning_rate": 8.247240241650918e-05,
+      "loss": 16.319,
+      "step": 21
+    },
+    {
+      "epoch": 0.017180788754392814,
+      "grad_norm": 43.87798309326172,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 12.6792,
+      "step": 22
+    },
+    {
+      "epoch": 0.017961733697774308,
+      "grad_norm": 51.43169403076172,
+      "learning_rate": 7.612492823579745e-05,
+      "loss": 16.1705,
+      "step": 23
+    },
+    {
+      "epoch": 0.018742678641155797,
+      "grad_norm": 47.817901611328125,
+      "learning_rate": 7.269952498697734e-05,
+      "loss": 11.841,
+      "step": 24
+    },
+    {
+      "epoch": 0.01952362358453729,
+      "grad_norm": 56.87557601928711,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 17.5764,
+      "step": 25
+    },
+    {
+      "epoch": 0.02030456852791878,
+      "grad_norm": 45.88191223144531,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 13.4572,
+      "step": 26
+    },
+    {
+      "epoch": 0.02030456852791878,
+      "eval_loss": 0.8506395816802979,
+      "eval_runtime": 300.4403,
+      "eval_samples_per_second": 7.179,
+      "eval_steps_per_second": 3.591,
+      "step": 26
     }
   ],
   "logging_steps": 1,
@@ -133,7 +232,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7.312546786285978e+16,
+  "total_flos": 1.4625093572571955e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null