Training in progress, step 1800, checkpoint

last-checkpoint/model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8288a02283f86e9ba638fcdafdad6ac55a5bf4c5099f8ee42ed13013ea826eb4
+oid sha256:9504097674ab65e0b578a537215795127828dc3848d2e4873d658311c1534e62
 size 4978139416

last-checkpoint/model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a97f66c1c28574e6392a73fea8effb2b5863a86aaab48224adfe1b025bb3191
+oid sha256:7951a74954187d35b833d6d8691c87dcbdef74a3c5d520bbb89ddf73c4c64a1c
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:98cc6c42135d5fdae0950a750eaccd195bb5b28087533bf97a0e88b169b95efd
+oid sha256:9f18849e5ff0941d6d82b638d7c00894ec5fd481eaf6afd0143fabdea22866d0
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e44798068a9718e8bcfd56ffc9856739f99cbd9473873a0e9a358ac7d41155d6
-size 14567
+oid sha256:fbd1a54c5b324d97726a1024b86dcbf61d66728c010a8906fe7f5578ce6b350f
+size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:270b38fcc20aa3dd5713b96e8eb52fafaafc66915212800045170780fba378bf
+oid sha256:9a476ee52ee296b1d46ee34fc092913aff5958cef2900b5569da3f9890dd90c4
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.6735424121237634,
+  "epoch": 0.7577352136392338,
   "eval_steps": 100,
-  "global_step": 1600,
+  "global_step": 1800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -263,6 +263,38 @@
       "eval_samples_per_second": 27.312,
       "eval_steps_per_second": 3.415,
       "step": 1600
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 2.9270007610321045,
+      "learning_rate": 4.915618374558304e-05,
+      "loss": 2.418,
+      "step": 1700
+    },
+    {
+      "epoch": 0.72,
+      "eval_cer": 0.624877791247898,
+      "eval_loss": 2.498126983642578,
+      "eval_runtime": 355.9419,
+      "eval_samples_per_second": 26.628,
+      "eval_steps_per_second": 3.329,
+      "step": 1700
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 3.458078622817993,
+      "learning_rate": 4.908551236749117e-05,
+      "loss": 2.6118,
+      "step": 1800
+    },
+    {
+      "epoch": 0.76,
+      "eval_cer": 0.5718074185600877,
+      "eval_loss": 3.407224655151367,
+      "eval_runtime": 343.8365,
+      "eval_samples_per_second": 27.565,
+      "eval_steps_per_second": 3.446,
+      "step": 1800
     }
   ],
   "logging_steps": 100,
@@ -270,7 +302,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 1.752021221030171e+19,
+  "total_flos": 1.9750080760883966e+19,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null