Training in progress, step 26, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:25f0b4dee1f7caf7bae6e0b2406ac105697cfbc94e454fa20130055a517fd752
+oid sha256:ba769a8518b703318fb50ec0f856f3debaabfac894332b3efbda487ff002a1ac
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e2c120a2b1f03e9204e181c0b9dc66796acb69609fa2756fec9c0a1f265c610c
+oid sha256:2fac0a59a674845a28b12987443b28a5b806173435f68d0abca5c63b68915c12
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4105db75dc6a75e46fcdb66ea6bc0fb1b54935802136f485ae6ccfb2b46e435e
+oid sha256:719020131bf833c90632c6b01b06c5301e1876ba50a1273eb06ec350ba411a1a
 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": 0.1317289423685877,
+  "epoch": 0.2634578847371754,
   "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": 42.377,
       "eval_steps_per_second": 21.315,
       "step": 13
+    },
+    {
+      "epoch": 0.14186193793540217,
+      "grad_norm": 2.615652084350586,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 1.1747,
+      "step": 14
+    },
+    {
+      "epoch": 0.1519949335022166,
+      "grad_norm": 3.228269338607788,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 1.1195,
+      "step": 15
+    },
+    {
+      "epoch": 0.16212792906903103,
+      "grad_norm": 3.2835893630981445,
+      "learning_rate": 9.45503262094184e-05,
+      "loss": 0.7324,
+      "step": 16
+    },
+    {
+      "epoch": 0.17226092463584547,
+      "grad_norm": 3.4717910289764404,
+      "learning_rate": 9.263200821770461e-05,
+      "loss": 0.4257,
+      "step": 17
+    },
+    {
+      "epoch": 0.1823939202026599,
+      "grad_norm": 1.8152432441711426,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 0.2427,
+      "step": 18
+    },
+    {
+      "epoch": 0.19252691576947434,
+      "grad_norm": 1.5609540939331055,
+      "learning_rate": 8.802029828000156e-05,
+      "loss": 0.1929,
+      "step": 19
+    },
+    {
+      "epoch": 0.2026599113362888,
+      "grad_norm": 1.3951321840286255,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 0.0777,
+      "step": 20
+    },
+    {
+      "epoch": 0.21279290690310323,
+      "grad_norm": 1.6223750114440918,
+      "learning_rate": 8.247240241650918e-05,
+      "loss": 0.061,
+      "step": 21
+    },
+    {
+      "epoch": 0.22292590246991767,
+      "grad_norm": 0.5461512804031372,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 0.0276,
+      "step": 22
+    },
+    {
+      "epoch": 0.2330588980367321,
+      "grad_norm": 2.7356250286102295,
+      "learning_rate": 7.612492823579745e-05,
+      "loss": 0.258,
+      "step": 23
+    },
+    {
+      "epoch": 0.24319189360354654,
+      "grad_norm": 1.6690704822540283,
+      "learning_rate": 7.269952498697734e-05,
+      "loss": 0.0822,
+      "step": 24
+    },
+    {
+      "epoch": 0.253324889170361,
+      "grad_norm": 1.9990379810333252,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 0.1948,
+      "step": 25
+    },
+    {
+      "epoch": 0.2634578847371754,
+      "grad_norm": 1.84889817237854,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 0.0953,
+      "step": 26
+    },
+    {
+      "epoch": 0.2634578847371754,
+      "eval_loss": 0.1430395096540451,
+      "eval_runtime": 3.934,
+      "eval_samples_per_second": 42.45,
+      "eval_steps_per_second": 21.352,
+      "step": 26
     }
   ],
   "logging_steps": 1,
@@ -133,7 +232,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8568679201505280.0,
+  "total_flos": 1.713735840301056e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null