Training in progress, step 24, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f52197f08ac97bce789589be026a6552fa357a40982aaf726e97861587d3fb4
+oid sha256:afd43459aca1d3dd6ba19b492ff0b1a518fa26343349db3dbf7339d087eebd23
 size 26008

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aee98f50f61c85daaf59201011827a23c014e12e6fa98809c0893fd188daf5fe
+oid sha256:fc371ca6c71178a5286fd3a76a50b707a2e0fe394fa8ac95b37cb90ad0207a90
 size 61926

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c6eeca6fec2d74dc35412cee25843a6e2b45b715cb98314d10ac41fc41a4cabc
+oid sha256:e9c762e745e6b10819fd8afb33b4a1b715c756c7b22945b0044c81ebcb593a7d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e3233603be2c007aac019155f1cd5d754e2eeb600f6ca413bd2048966230a2e8
+oid sha256:b9fbbdb6036d2372f81987526c35ebf7be4064ed59a37e6c1ea765cbfb6cc373
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0014851513868181212,
+  "epoch": 0.0022277270802271818,
   "eval_steps": 8,
-  "global_step": 16,
+  "global_step": 24,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -143,6 +143,70 @@
       "eval_samples_per_second": 157.535,
       "eval_steps_per_second": 78.772,
       "step": 16
+    },
+    {
+      "epoch": 0.0015779733484942537,
+      "grad_norm": 0.012164338491857052,
+      "learning_rate": 7.269952498697734e-05,
+      "loss": 11.9297,
+      "step": 17
+    },
+    {
+      "epoch": 0.0016707953101703862,
+      "grad_norm": 0.017325541004538536,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 11.9274,
+      "step": 18
+    },
+    {
+      "epoch": 0.001763617271846519,
+      "grad_norm": 0.01545996405184269,
+      "learning_rate": 5.782172325201155e-05,
+      "loss": 11.9279,
+      "step": 19
+    },
+    {
+      "epoch": 0.0018564392335226514,
+      "grad_norm": 0.012894785962998867,
+      "learning_rate": 5e-05,
+      "loss": 11.9308,
+      "step": 20
+    },
+    {
+      "epoch": 0.001949261195198784,
+      "grad_norm": 0.01422932744026184,
+      "learning_rate": 4.2178276747988446e-05,
+      "loss": 11.929,
+      "step": 21
+    },
+    {
+      "epoch": 0.002042083156874917,
+      "grad_norm": 0.011517844162881374,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 11.9292,
+      "step": 22
+    },
+    {
+      "epoch": 0.002134905118551049,
+      "grad_norm": 0.0101248100399971,
+      "learning_rate": 2.7300475013022663e-05,
+      "loss": 11.9274,
+      "step": 23
+    },
+    {
+      "epoch": 0.0022277270802271818,
+      "grad_norm": 0.015307254157960415,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 11.9269,
+      "step": 24
+    },
+    {
+      "epoch": 0.0022277270802271818,
+      "eval_loss": 11.927979469299316,
+      "eval_runtime": 115.0963,
+      "eval_samples_per_second": 157.651,
+      "eval_steps_per_second": 78.83,
+      "step": 24
     }
   ],
   "logging_steps": 1,
@@ -162,7 +226,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 98555265024.0,
+  "total_flos": 147645530112.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null