Training in progress, step 36, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:11c4d594833855b876f3de4cb794e7f0b8e9ed7d6883bafc6697762f882f2d89
+oid sha256:ebedb82f8f80f1d83184422667e7ca02340a20c0414db33f19cababf31c0edaf
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:755576e2942a21fc96bb71e9d413a6a0a0e2a41ca2deab181a8ebfcb9481ed34
+oid sha256:f226bf7ef13778cfee789ebaa17bfb88e7252f92210cc18a9977de1c2a1982d3
 size 81730196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c535d322f74c9d3b81f5ae8eda9978ae89ee98f7142986d1695029a6439098ec
+oid sha256:b5224358fefc4a6c20673e2c295e1dbc37dff7b6514472d01bd9b5aa0159f5f9
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:95e5b5e126f269e3dd52e13e2ce68743557810f4e2bb59a1eda63231c7828066
+oid sha256:bc389ed2ec8a0148b9b29024154a8f2f11c6a7454ef1d0724563562d03a46e01
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.018977332630469163,
+  "epoch": 0.025303110173958882,
   "eval_steps": 9,
-  "global_step": 27,
+  "global_step": 36,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -102,6 +102,35 @@
       "eval_samples_per_second": 7.127,
       "eval_steps_per_second": 0.892,
       "step": 27
+    },
+    {
+      "epoch": 0.021085925144965736,
+      "grad_norm": 0.19669905304908752,
+      "learning_rate": 4.415111107797445e-05,
+      "loss": 0.8562,
+      "step": 30
+    },
+    {
+      "epoch": 0.02319451765946231,
+      "grad_norm": 0.16489790380001068,
+      "learning_rate": 4.2366459261474933e-05,
+      "loss": 0.7713,
+      "step": 33
+    },
+    {
+      "epoch": 0.025303110173958882,
+      "grad_norm": 0.18417863547801971,
+      "learning_rate": 4.039153688314145e-05,
+      "loss": 0.7589,
+      "step": 36
+    },
+    {
+      "epoch": 0.025303110173958882,
+      "eval_loss": 0.7888206243515015,
+      "eval_runtime": 336.3758,
+      "eval_samples_per_second": 7.126,
+      "eval_steps_per_second": 0.892,
+      "step": 36
     }
   ],
   "logging_steps": 3,
@@ -121,7 +150,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7.139816462352384e+16,
+  "total_flos": 9.519755283136512e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null