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:d029e3c7fbf757782bd042f04c828071e646509ff1874afd0b68ef68de0c8716
+oid sha256:9257ac4bd5394e1a091d3849a60d9e88ad607d26e1c814afb826237b140b2fe9
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e0727bb7e7c6a685c5daaae1d6c23bff46a0c79c5699ee029690e8a9f493b90
+oid sha256:83456b36b0dce72567d87510e714139be0044d8bc08e8e3ff02de707249fd696
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:884181cdc565c65bf5ff64272d5d48915d11b997882ba7383a9b08f8a31a1ce5
+oid sha256:ed392f1e42c4e7f65661970b1ec941968361613202f48a3141f9aacaa4003064
 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": 0.005168472318854984,
+  "epoch": 0.007752708478282477,
   "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": 28.498,
       "eval_steps_per_second": 14.256,
       "step": 26
+    },
+    {
+      "epoch": 0.0053672597157340225,
+      "grad_norm": 3.7985334396362305,
+      "learning_rate": 3.083613409639764e-05,
+      "loss": 13.1346,
+      "step": 27
+    },
+    {
+      "epoch": 0.0055660471126130606,
+      "grad_norm": 2.66591477394104,
+      "learning_rate": 2.8910861626005776e-05,
+      "loss": 14.0919,
+      "step": 28
+    },
+    {
+      "epoch": 0.005764834509492099,
+      "grad_norm": 3.770318031311035,
+      "learning_rate": 2.6961477393196126e-05,
+      "loss": 12.0625,
+      "step": 29
+    },
+    {
+      "epoch": 0.005963621906371136,
+      "grad_norm": 3.1966161727905273,
+      "learning_rate": 2.5e-05,
+      "loss": 13.3168,
+      "step": 30
+    },
+    {
+      "epoch": 0.006162409303250174,
+      "grad_norm": 3.4274048805236816,
+      "learning_rate": 2.303852260680388e-05,
+      "loss": 13.7754,
+      "step": 31
+    },
+    {
+      "epoch": 0.006361196700129212,
+      "grad_norm": 3.12906813621521,
+      "learning_rate": 2.1089138373994223e-05,
+      "loss": 11.2148,
+      "step": 32
+    },
+    {
+      "epoch": 0.00655998409700825,
+      "grad_norm": 2.4191653728485107,
+      "learning_rate": 1.9163865903602374e-05,
+      "loss": 11.369,
+      "step": 33
+    },
+    {
+      "epoch": 0.006758771493887287,
+      "grad_norm": 3.0178472995758057,
+      "learning_rate": 1.7274575140626318e-05,
+      "loss": 11.5686,
+      "step": 34
+    },
+    {
+      "epoch": 0.006957558890766325,
+      "grad_norm": 3.4739089012145996,
+      "learning_rate": 1.5432914190872757e-05,
+      "loss": 13.3696,
+      "step": 35
+    },
+    {
+      "epoch": 0.007156346287645363,
+      "grad_norm": 4.477285385131836,
+      "learning_rate": 1.3650237506511331e-05,
+      "loss": 13.9461,
+      "step": 36
+    },
+    {
+      "epoch": 0.007355133684524401,
+      "grad_norm": 3.5579240322113037,
+      "learning_rate": 1.1937535882101281e-05,
+      "loss": 12.4578,
+      "step": 37
+    },
+    {
+      "epoch": 0.0075539210814034394,
+      "grad_norm": 3.2776896953582764,
+      "learning_rate": 1.0305368692688174e-05,
+      "loss": 11.7642,
+      "step": 38
+    },
+    {
+      "epoch": 0.007752708478282477,
+      "grad_norm": 2.8097920417785645,
+      "learning_rate": 8.763798791745411e-06,
+      "loss": 11.8259,
+      "step": 39
+    },
+    {
+      "epoch": 0.007752708478282477,
+      "eval_loss": 3.0318076610565186,
+      "eval_runtime": 73.9722,
+      "eval_samples_per_second": 28.646,
+      "eval_steps_per_second": 14.33,
+      "step": 39
     }
   ],
   "logging_steps": 1,
@@ -232,7 +331,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4275424481771520.0,
+  "total_flos": 6392777558458368.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null