Training in progress, step 18500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e87cb14acd4e6fe6bcad897a8f042f31acae6fb2e34f61ed68b17e469e4f393
+oid sha256:a9f8e1e9f015d9568bf75922d777d726b01fb6e502bd445c08094a91f28ae1a8
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5e64bb265a77f08e4da4240e30c68e0a0ae7eb01df9530a76fcba45020acfd6b
+oid sha256:01ffcfafbc1c4522f01ae60dab6db775fcdcd8fec900d37f15a5127a63ce98b4
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea1c5d0777adfd9f21aec03650885c94d8b0325360d164ecc81c3a16d777cc03
+oid sha256:6769e966cbd01b0928c6dfa08d9183af00ab69c61a86a4a6ef846a74f2cd4f12
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4bc3c023f1bacc02e7db4990bce2636fd592e49ea544612a30431a586cc170fc
+oid sha256:88eb0259375aeb4797384085a6556dffb88f3f28e3b811d250261aef798e28f2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.0821109265089035,
   "best_model_checkpoint": "./fine-tuned/checkpoint-17500",
-  "epoch": 1.44,
+  "epoch": 1.48,
   "eval_steps": 500,
-  "global_step": 18000,
+  "global_step": 18500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2815,6 +2815,84 @@
       "eval_samples_per_second": 22.709,
       "eval_steps_per_second": 5.677,
       "step": 18000
+    },
+    {
+      "epoch": 1.444,
+      "grad_norm": 0.150528684258461,
+      "learning_rate": 8.3448e-06,
+      "loss": 0.0519,
+      "step": 18050
+    },
+    {
+      "epoch": 1.448,
+      "grad_norm": 0.08878117799758911,
+      "learning_rate": 8.2848e-06,
+      "loss": 0.0544,
+      "step": 18100
+    },
+    {
+      "epoch": 1.452,
+      "grad_norm": 0.12337563931941986,
+      "learning_rate": 8.224800000000001e-06,
+      "loss": 0.0509,
+      "step": 18150
+    },
+    {
+      "epoch": 1.456,
+      "grad_norm": 0.12858565151691437,
+      "learning_rate": 8.1648e-06,
+      "loss": 0.0561,
+      "step": 18200
+    },
+    {
+      "epoch": 1.46,
+      "grad_norm": 0.14318782091140747,
+      "learning_rate": 8.1048e-06,
+      "loss": 0.0539,
+      "step": 18250
+    },
+    {
+      "epoch": 1.464,
+      "grad_norm": 0.16946159303188324,
+      "learning_rate": 8.044800000000001e-06,
+      "loss": 0.0545,
+      "step": 18300
+    },
+    {
+      "epoch": 1.468,
+      "grad_norm": 0.11605024337768555,
+      "learning_rate": 7.9848e-06,
+      "loss": 0.0563,
+      "step": 18350
+    },
+    {
+      "epoch": 1.472,
+      "grad_norm": 0.20185694098472595,
+      "learning_rate": 7.9248e-06,
+      "loss": 0.0536,
+      "step": 18400
+    },
+    {
+      "epoch": 1.476,
+      "grad_norm": 0.16189858317375183,
+      "learning_rate": 7.8648e-06,
+      "loss": 0.0523,
+      "step": 18450
+    },
+    {
+      "epoch": 1.48,
+      "grad_norm": 0.24366913735866547,
+      "learning_rate": 7.8048e-06,
+      "loss": 0.057,
+      "step": 18500
+    },
+    {
+      "epoch": 1.48,
+      "eval_loss": 0.08215340971946716,
+      "eval_runtime": 88.0726,
+      "eval_samples_per_second": 22.709,
+      "eval_steps_per_second": 5.677,
+      "step": 18500
     }
   ],
   "logging_steps": 50,
@@ -2834,7 +2912,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.384496812032e+16,
+  "total_flos": 4.506288390144e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null