Training in progress, step 36, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6c87775b5edcb585b28c4eddf54d4dce8265909ac975ae4e8fc2a1c79dad687a
+oid sha256:bc34b779669ac664537d405202e60d4c4bf74ba69f23a278bff1710c7ff69392
 size 72396376

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c1c3428353a34d0c5b140915486f3aa259f22376c50e64b89b91fa5ea52e74f
+oid sha256:ef316a2427ed9f06bf60371ff6402a618ce78c0a4452e5aaa88d3811a3dedfd2
 size 37134420

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9bd09ace895178fe2265702e7f4382b90709d73d1ef6b0e69e6c37a98d08dcfd
+oid sha256:508bf57c0b7938cf6320eb2547b85198a04772745c43c070dc89ffb1a83ebce8
 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": 0.10121836925960637,
+  "epoch": 0.13495782567947517,
   "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": 34.755,
       "eval_steps_per_second": 4.402,
       "step": 27
+    },
+    {
+      "epoch": 0.11246485473289597,
+      "grad_norm": 0.19368326663970947,
+      "learning_rate": 4.415111107797445e-05,
+      "loss": 1.9612,
+      "step": 30
+    },
+    {
+      "epoch": 0.12371134020618557,
+      "grad_norm": 0.17149889469146729,
+      "learning_rate": 4.2366459261474933e-05,
+      "loss": 2.022,
+      "step": 33
+    },
+    {
+      "epoch": 0.13495782567947517,
+      "grad_norm": 0.18569713830947876,
+      "learning_rate": 4.039153688314145e-05,
+      "loss": 1.9794,
+      "step": 36
+    },
+    {
+      "epoch": 0.13495782567947517,
+      "eval_loss": 1.9658715724945068,
+      "eval_runtime": 12.9648,
+      "eval_samples_per_second": 34.709,
+      "eval_steps_per_second": 4.397,
+      "step": 36
     }
   ],
   "logging_steps": 3,
@@ -121,7 +150,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8726412244549632.0,
+  "total_flos": 1.1768647705952256e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null