Training in progress, step 39, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d34181d4ed1ef070c690841d92f2ae126aa45d79dee1740f0a4ce36882531d88
+oid sha256:36369ca4fcebb046f012b2c38065061c0dbcc197ea02533d23d69a4cb3a08296
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c992a4268a63cf9c3dfb9fe99ea395ac6c2fd521df796234fb736c1b503d24bb
+oid sha256:0ca784afa662e7382dd839289567429925dfdc7bc73d13c00b8d6bfb1566ae29
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:afe3321a5df89872b1953a1ab29c627c51a1ad7d4b66802512ee71a313ca37bb
+oid sha256:8311729536aebb3f7c37c9f4f6b8414ba95b49789c2765866d4643fc033869b3
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa0fde01e60897f55f4ebaca5a490a1a483a2c53b2ae8e7543860a62c5b3298c
+oid sha256:28418a35cb7e15ebbce37743b08fd366c25ee320167b307a3e449a74781d02de
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.03022377215925603,
+  "epoch": 0.045335658238884045,
   "eval_steps": 13,
-  "global_step": 26,
+  "global_step": 39,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -213,6 +213,105 @@
       "eval_samples_per_second": 19.432,
       "eval_steps_per_second": 9.743,
       "step": 26
+    },
+    {
+      "epoch": 0.03138622493461203,
+      "grad_norm": 1.445319414138794,
+      "learning_rate": 3.083613409639764e-05,
+      "loss": 2.0072,
+      "step": 27
+    },
+    {
+      "epoch": 0.032548677709968034,
+      "grad_norm": 1.4100600481033325,
+      "learning_rate": 2.8910861626005776e-05,
+      "loss": 2.9271,
+      "step": 28
+    },
+    {
+      "epoch": 0.03371113048532404,
+      "grad_norm": 1.2174726724624634,
+      "learning_rate": 2.6961477393196126e-05,
+      "loss": 2.325,
+      "step": 29
+    },
+    {
+      "epoch": 0.03487358326068003,
+      "grad_norm": 1.3934134244918823,
+      "learning_rate": 2.5e-05,
+      "loss": 2.4305,
+      "step": 30
+    },
+    {
+      "epoch": 0.036036036036036036,
+      "grad_norm": 1.353877067565918,
+      "learning_rate": 2.303852260680388e-05,
+      "loss": 1.9587,
+      "step": 31
+    },
+    {
+      "epoch": 0.03719848881139204,
+      "grad_norm": 1.3453905582427979,
+      "learning_rate": 2.1089138373994223e-05,
+      "loss": 2.4014,
+      "step": 32
+    },
+    {
+      "epoch": 0.03836094158674804,
+      "grad_norm": 1.4014428853988647,
+      "learning_rate": 1.9163865903602374e-05,
+      "loss": 2.4628,
+      "step": 33
+    },
+    {
+      "epoch": 0.03952339436210404,
+      "grad_norm": 1.7237356901168823,
+      "learning_rate": 1.7274575140626318e-05,
+      "loss": 2.5534,
+      "step": 34
+    },
+    {
+      "epoch": 0.04068584713746004,
+      "grad_norm": 1.6201252937316895,
+      "learning_rate": 1.5432914190872757e-05,
+      "loss": 2.6219,
+      "step": 35
+    },
+    {
+      "epoch": 0.041848299912816043,
+      "grad_norm": 1.7005544900894165,
+      "learning_rate": 1.3650237506511331e-05,
+      "loss": 2.2468,
+      "step": 36
+    },
+    {
+      "epoch": 0.043010752688172046,
+      "grad_norm": 1.5233935117721558,
+      "learning_rate": 1.1937535882101281e-05,
+      "loss": 2.4295,
+      "step": 37
+    },
+    {
+      "epoch": 0.04417320546352804,
+      "grad_norm": 1.4735093116760254,
+      "learning_rate": 1.0305368692688174e-05,
+      "loss": 2.3018,
+      "step": 38
+    },
+    {
+      "epoch": 0.045335658238884045,
+      "grad_norm": 1.803377389907837,
+      "learning_rate": 8.763798791745411e-06,
+      "loss": 2.6965,
+      "step": 39
+    },
+    {
+      "epoch": 0.045335658238884045,
+      "eval_loss": 0.5883385539054871,
+      "eval_runtime": 18.5863,
+      "eval_samples_per_second": 19.531,
+      "eval_steps_per_second": 9.792,
+      "step": 39
     }
   ],
   "logging_steps": 1,
@@ -232,7 +331,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7288580783210496.0,
+  "total_flos": 1.0749638697025536e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null