Training in progress, step 17500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:688c3b1d28f6b863bee92004557adc364c4b2e5ee4097d484ed3aaba40d50c14
+oid sha256:e12d395d228986d4722c9bfdd3b7c1a0c87813d6c1948380328534f75ad454cd
 size 891558696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a993357ca1b551b4a094ee2409999ca1a4657c3428fde811fa9954bc1b8b645
+oid sha256:ad3401b5dfde1c4ac0b81be604349a5d0c27404fba8d352372bd54950216bb24
 size 1783272762

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b8fa477eb7529f96adee96884288f62ffdf70dbb1416c416ce42fdc1eba5e518
+oid sha256:7f87436d1ed788958cb08087900b45d6f1fbde14c0d7db3fa0e7c937f406062a
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:57233dc32b29f0dc0010f99ddb975758e3cef5e747558908f115a1d09e80f707
+oid sha256:4d166d24f789387f6695cee2a14320335faa00c9fa99f8038d6fcfa9ae735c9d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.1333333333333333,
+  "epoch": 1.1666666666666667,
   "eval_steps": 500,
-  "global_step": 17000,
+  "global_step": 17500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1205,6 +1205,41 @@
       "learning_rate": 1.2446666666666667e-05,
       "loss": 0.058,
       "step": 17000
+    },
+    {
+      "epoch": 1.1400000000000001,
+      "grad_norm": 0.26193323731422424,
+      "learning_rate": 1.2402222222222222e-05,
+      "loss": 0.0606,
+      "step": 17100
+    },
+    {
+      "epoch": 1.1466666666666667,
+      "grad_norm": 0.18597596883773804,
+      "learning_rate": 1.235777777777778e-05,
+      "loss": 0.0565,
+      "step": 17200
+    },
+    {
+      "epoch": 1.1533333333333333,
+      "grad_norm": 0.27906695008277893,
+      "learning_rate": 1.2313333333333335e-05,
+      "loss": 0.0616,
+      "step": 17300
+    },
+    {
+      "epoch": 1.16,
+      "grad_norm": 0.20379580557346344,
+      "learning_rate": 1.226888888888889e-05,
+      "loss": 0.0572,
+      "step": 17400
+    },
+    {
+      "epoch": 1.1666666666666667,
+      "grad_norm": 0.2315666228532791,
+      "learning_rate": 1.2224444444444445e-05,
+      "loss": 0.0571,
+      "step": 17500
     }
   ],
   "logging_steps": 100,
@@ -1224,7 +1259,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.140913655808e+16,
+  "total_flos": 4.26270523392e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null