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:e43b29307385a1a441b513ec5ffc9acf3db0b05311cacd4e4d6e39c64ead4733
+oid sha256:ca7e26554e6e5033f1f7b770adea583fc2db8cc4929fe3fcebc0a7722f56c7d3
 size 26008

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d54d01af83d998c3d470a7a519a6f43b96fe12d5385a1149c1dda7a12694d45d
+oid sha256:b418bf7c4c6f29842bcd99ac3db501a5e925844dcbdf0fa7a794de52066bd03d
 size 61926

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e4a3ee778160f42a22e93367025f5b4d76e7fc51b428625824d02549c0d97d5
+oid sha256:424d06375131df3df5d4883391c61f995c66d877e893fd245f2c624058954297
 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": 0.00851900393184797,
+  "epoch": 0.01703800786369594,
   "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": 205.047,
       "eval_steps_per_second": 102.563,
       "step": 13
+    },
+    {
+      "epoch": 0.009174311926605505,
+      "grad_norm": 0.011835216544568539,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 11.9299,
+      "step": 14
+    },
+    {
+      "epoch": 0.009829619921363041,
+      "grad_norm": 0.01589955948293209,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 11.9325,
+      "step": 15
+    },
+    {
+      "epoch": 0.010484927916120577,
+      "grad_norm": 0.010300605557858944,
+      "learning_rate": 9.45503262094184e-05,
+      "loss": 11.93,
+      "step": 16
+    },
+    {
+      "epoch": 0.011140235910878113,
+      "grad_norm": 0.013794222846627235,
+      "learning_rate": 9.263200821770461e-05,
+      "loss": 11.9315,
+      "step": 17
+    },
+    {
+      "epoch": 0.011795543905635648,
+      "grad_norm": 0.014298832975327969,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 11.9313,
+      "step": 18
+    },
+    {
+      "epoch": 0.012450851900393184,
+      "grad_norm": 0.017451252788305283,
+      "learning_rate": 8.802029828000156e-05,
+      "loss": 11.9296,
+      "step": 19
+    },
+    {
+      "epoch": 0.01310615989515072,
+      "grad_norm": 0.017337026074528694,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 11.9303,
+      "step": 20
+    },
+    {
+      "epoch": 0.013761467889908258,
+      "grad_norm": 0.016705993562936783,
+      "learning_rate": 8.247240241650918e-05,
+      "loss": 11.9319,
+      "step": 21
+    },
+    {
+      "epoch": 0.014416775884665793,
+      "grad_norm": 0.014467249624431133,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 11.9311,
+      "step": 22
+    },
+    {
+      "epoch": 0.01507208387942333,
+      "grad_norm": 0.017065448686480522,
+      "learning_rate": 7.612492823579745e-05,
+      "loss": 11.9321,
+      "step": 23
+    },
+    {
+      "epoch": 0.015727391874180863,
+      "grad_norm": 0.014603197574615479,
+      "learning_rate": 7.269952498697734e-05,
+      "loss": 11.9317,
+      "step": 24
+    },
+    {
+      "epoch": 0.0163826998689384,
+      "grad_norm": 0.020358189940452576,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 11.9313,
+      "step": 25
+    },
+    {
+      "epoch": 0.01703800786369594,
+      "grad_norm": 0.012381589971482754,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 11.9309,
+      "step": 26
+    },
+    {
+      "epoch": 0.01703800786369594,
+      "eval_loss": 11.930882453918457,
+      "eval_runtime": 12.5197,
+      "eval_samples_per_second": 205.357,
+      "eval_steps_per_second": 102.718,
+      "step": 26
     }
   ],
   "logging_steps": 1,
@@ -133,7 +232,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 77944848384.0,
+  "total_flos": 155889696768.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null