Training in progress, step 26, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e33da6f677ca4bd6501d8e0001b949d5372e56c89e19219d1c3cc0a26bd472c
+oid sha256:4c96a98c8e8c0ebe728488647f7b680178769e3ea0b0f466c9b9934406668b5c
 size 30322120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d80158bdc9a3f5b38415ea8ee8df9d1d0450ec32d0e6ce732b8c33584e1bceb
+oid sha256:b2c2e89a0dfa486bc5dd5d13c6241da684f7f7653be35deaa6bc5f1d060ea20b
 size 15768084

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1cd14b6e9df65974236243be7a1649a308a1ce4739bd3c9051412f6981a69e18
+oid sha256:04c1e33264acca2abb6dd72706d07111d0f013ace21da22da195123054b2c451
 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": 0.2086258776328987,
+  "epoch": 0.4172517552657974,
   "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": 9.367,
       "eval_steps_per_second": 4.683,
       "step": 13
+    },
+    {
+      "epoch": 0.2246740220661986,
+      "grad_norm": 0.14492028951644897,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 2.5018,
+      "step": 14
+    },
+    {
+      "epoch": 0.24072216649949849,
+      "grad_norm": 0.13506127893924713,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 2.5642,
+      "step": 15
+    },
+    {
+      "epoch": 0.2567703109327984,
+      "grad_norm": 0.133815199136734,
+      "learning_rate": 9.45503262094184e-05,
+      "loss": 2.484,
+      "step": 16
+    },
+    {
+      "epoch": 0.2728184553660983,
+      "grad_norm": 0.1350664347410202,
+      "learning_rate": 9.263200821770461e-05,
+      "loss": 2.5023,
+      "step": 17
+    },
+    {
+      "epoch": 0.2888665997993982,
+      "grad_norm": 0.13471205532550812,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 2.5607,
+      "step": 18
+    },
+    {
+      "epoch": 0.3049147442326981,
+      "grad_norm": 0.12733304500579834,
+      "learning_rate": 8.802029828000156e-05,
+      "loss": 2.3489,
+      "step": 19
+    },
+    {
+      "epoch": 0.320962888665998,
+      "grad_norm": 0.13001815974712372,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 2.5144,
+      "step": 20
+    },
+    {
+      "epoch": 0.3370110330992979,
+      "grad_norm": 0.13591095805168152,
+      "learning_rate": 8.247240241650918e-05,
+      "loss": 2.2412,
+      "step": 21
+    },
+    {
+      "epoch": 0.3530591775325978,
+      "grad_norm": 0.13400661945343018,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 2.4606,
+      "step": 22
+    },
+    {
+      "epoch": 0.3691073219658977,
+      "grad_norm": 0.13440661132335663,
+      "learning_rate": 7.612492823579745e-05,
+      "loss": 2.526,
+      "step": 23
+    },
+    {
+      "epoch": 0.38515546639919757,
+      "grad_norm": 0.13519461452960968,
+      "learning_rate": 7.269952498697734e-05,
+      "loss": 2.5468,
+      "step": 24
+    },
+    {
+      "epoch": 0.4012036108324975,
+      "grad_norm": 0.14065755903720856,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 2.4216,
+      "step": 25
+    },
+    {
+      "epoch": 0.4172517552657974,
+      "grad_norm": 0.12566477060317993,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 2.3784,
+      "step": 26
+    },
+    {
+      "epoch": 0.4172517552657974,
+      "eval_loss": 2.5140509605407715,
+      "eval_runtime": 22.4277,
+      "eval_samples_per_second": 9.363,
+      "eval_steps_per_second": 4.682,
+      "step": 26
     }
   ],
   "logging_steps": 1,
@@ -133,7 +232,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6476337883643904.0,
+  "total_flos": 1.2999268126162944e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null