Training in progress, step 40400, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:234d353a9c16df150a9c4d16ea704e6c85931b80cbba47b784e4547b73a51715
+oid sha256:6188044dbfec3db480d47482cff436a4a882d1e2da837b0331ecfd8d831437af
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:939ab97ad49a707233e95f14ca0a1419257ae4e79296c50f05ffbdd48d9d5bca
+oid sha256:30f19f0d03c8ad0878ba2daf65268a6123dc51dcef9f90b49e7b00d458a2ed2b
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1bbf2096820ceefbefa37220cda6972a36788b6a6894f9f4793885c92ca72069
+oid sha256:d239ea849485001cc71d8e8f299676d711228873c7837c94f2dd42aa10fa13af
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:15ed916a67962ea3d466c350187b755a76acf54704cf9a56f9ed8a19cc7f3bbd
+oid sha256:200cb07eac893fb8762313e23cc9c505d8353297219dcb475604278f65095793
 size 14567

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ddc3dcc2dc6784f422e1a3ad05503da45d0549dd29f1492b723c27b252617267
+oid sha256:d8af456d177bc478bc5d435dfa70de8769ea30f35830dafa9b724c49a14923c8
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 16.88065670385182,
+  "epoch": 17.006945906125026,
   "eval_steps": 100,
-  "global_step": 40100,
+  "global_step": 40400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -6423,6 +6423,54 @@
       "eval_samples_per_second": 25.054,
       "eval_steps_per_second": 3.132,
       "step": 40100
+    },
+    {
+      "epoch": 16.92,
+      "grad_norm": 3.6556479930877686,
+      "learning_rate": 2.1956890459363957e-05,
+      "loss": 1.0403,
+      "step": 40200
+    },
+    {
+      "epoch": 16.92,
+      "eval_cer": 0.3646293652966251,
+      "eval_loss": 2.4574332237243652,
+      "eval_runtime": 392.3067,
+      "eval_samples_per_second": 24.16,
+      "eval_steps_per_second": 3.021,
+      "step": 40200
+    },
+    {
+      "epoch": 16.96,
+      "grad_norm": 1.9411290884017944,
+      "learning_rate": 2.1886219081272085e-05,
+      "loss": 0.7538,
+      "step": 40300
+    },
+    {
+      "epoch": 16.96,
+      "eval_cer": 0.36607387274647063,
+      "eval_loss": 1.7143244743347168,
+      "eval_runtime": 378.8409,
+      "eval_samples_per_second": 25.018,
+      "eval_steps_per_second": 3.128,
+      "step": 40300
+    },
+    {
+      "epoch": 17.01,
+      "grad_norm": 7.614956378936768,
+      "learning_rate": 2.1815547703180214e-05,
+      "loss": 0.7241,
+      "step": 40400
+    },
+    {
+      "epoch": 17.01,
+      "eval_cer": 0.3618430057486997,
+      "eval_loss": 1.6417515277862549,
+      "eval_runtime": 391.0073,
+      "eval_samples_per_second": 24.24,
+      "eval_steps_per_second": 3.031,
+      "step": 40400
     }
   ],
   "logging_steps": 100,
@@ -6430,7 +6478,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 4.393961093701251e+20,
+  "total_flos": 4.4276874138754004e+20,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null