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:f9eb46ec5d997662813b6157464c4260ce8588517e26b0bac6152b1d16d556b7
+oid sha256:a386a072d53d4e92267ee41675841f2f159bc4e78a89124c66863c963b7aa307
 size 35237104

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:923a554241031c7bd10dcbcacdad6bdac74ddcb82ab16f3a5abcf05f641c03d6
+oid sha256:213f6b01d272ab2470e99d39ed860d0f1c384c7c14601c14c9e064a7ee95acd5
 size 18810036

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": 0.0008794219491880145,
+  "epoch": 0.001758843898376029,
   "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": 28.548,
       "eval_steps_per_second": 14.274,
       "step": 13
+    },
+    {
+      "epoch": 0.0009470697914332463,
+      "grad_norm": 2.2020058631896973,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 2.5448,
+      "step": 14
+    },
+    {
+      "epoch": 0.0010147176336784782,
+      "grad_norm": 1.4748566150665283,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 2.622,
+      "step": 15
+    },
+    {
+      "epoch": 0.0010823654759237102,
+      "grad_norm": 1.5124787092208862,
+      "learning_rate": 9.45503262094184e-05,
+      "loss": 2.6661,
+      "step": 16
+    },
+    {
+      "epoch": 0.001150013318168942,
+      "grad_norm": 2.291480541229248,
+      "learning_rate": 9.263200821770461e-05,
+      "loss": 1.9446,
+      "step": 17
+    },
+    {
+      "epoch": 0.001217661160414174,
+      "grad_norm": 1.5338326692581177,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 1.5786,
+      "step": 18
+    },
+    {
+      "epoch": 0.0012853090026594058,
+      "grad_norm": 1.017585039138794,
+      "learning_rate": 8.802029828000156e-05,
+      "loss": 1.669,
+      "step": 19
+    },
+    {
+      "epoch": 0.0013529568449046378,
+      "grad_norm": 1.0846589803695679,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 1.8216,
+      "step": 20
+    },
+    {
+      "epoch": 0.0014206046871498696,
+      "grad_norm": 1.0249284505844116,
+      "learning_rate": 8.247240241650918e-05,
+      "loss": 2.1166,
+      "step": 21
+    },
+    {
+      "epoch": 0.0014882525293951013,
+      "grad_norm": 1.2318507432937622,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 1.7656,
+      "step": 22
+    },
+    {
+      "epoch": 0.0015559003716403333,
+      "grad_norm": 1.3429690599441528,
+      "learning_rate": 7.612492823579745e-05,
+      "loss": 1.8599,
+      "step": 23
+    },
+    {
+      "epoch": 0.0016235482138855651,
+      "grad_norm": 0.7906981110572815,
+      "learning_rate": 7.269952498697734e-05,
+      "loss": 2.1856,
+      "step": 24
+    },
+    {
+      "epoch": 0.0016911960561307971,
+      "grad_norm": 0.8192072510719299,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 1.9776,
+      "step": 25
+    },
+    {
+      "epoch": 0.001758843898376029,
+      "grad_norm": 0.7536182403564453,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 1.8015,
+      "step": 26
+    },
+    {
+      "epoch": 0.001758843898376029,
+      "eval_loss": 1.444047451019287,
+      "eval_runtime": 871.7811,
+      "eval_samples_per_second": 28.559,
+      "eval_steps_per_second": 14.28,
+      "step": 26
     }
   ],
   "logging_steps": 1,
@@ -133,7 +232,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3748962364293120.0,
+  "total_flos": 7497924728586240.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null