Training in progress, step 53900, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e35b78386d3b49c89f85ffffe06aae621443cf1b932a8092b4db090fbd3ec96
+oid sha256:10b2dcef9f26179151435e50d8e64e0973728607ca53d2c9bca9890649ccae83
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:874666ed33022a022c5899409f513db7f4eb2c26c88a84553937a6e405f29378
+oid sha256:631fa048ad4716521ddf3c742f0d06469909e5075a79096a62d3bf501816a346
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:81361d862eaf160b9e170db03019275ae10369ec53a2433cdd4bf4a722d8c87d
+oid sha256:b0e6a675d71cea3e043d398f0c5c226166bd97c3d96321b395a156a2148869be
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d5783c2395d6ceb319348029dab347862318433ddfe999f17859fa9858fbd44
+oid sha256:b5210adbdeeb201664228e6f6260e1e39bb443611ef0bc349a9a68a41921abb3
 size 14567

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc7f8ff46b15057ea0b7cff87e35527c6b328af1a3f89ae33ca25b7b381ad498
+oid sha256:5f72bd9fcf066733ad01f4170825cb13eef2cf7fb9d9def60eafcaf568f587f6
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 22.52157440538834,
+  "epoch": 22.68996000841928,
   "eval_steps": 100,
-  "global_step": 53500,
+  "global_step": 53900,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -8567,6 +8567,70 @@
       "eval_samples_per_second": 24.135,
       "eval_steps_per_second": 3.018,
       "step": 53500
+    },
+    {
+      "epoch": 22.56,
+      "grad_norm": 1.8772177696228027,
+      "learning_rate": 1.2490459363957597e-05,
+      "loss": 0.3069,
+      "step": 53600
+    },
+    {
+      "epoch": 22.56,
+      "eval_cer": 0.3383080442688984,
+      "eval_loss": 2.481276035308838,
+      "eval_runtime": 425.0385,
+      "eval_samples_per_second": 22.299,
+      "eval_steps_per_second": 2.788,
+      "step": 53600
+    },
+    {
+      "epoch": 22.61,
+      "grad_norm": 1.4407734870910645,
+      "learning_rate": 1.2419787985865725e-05,
+      "loss": 0.3018,
+      "step": 53700
+    },
+    {
+      "epoch": 22.61,
+      "eval_cer": 0.3348739783348324,
+      "eval_loss": 2.4129292964935303,
+      "eval_runtime": 399.5718,
+      "eval_samples_per_second": 23.72,
+      "eval_steps_per_second": 2.966,
+      "step": 53700
+    },
+    {
+      "epoch": 22.65,
+      "grad_norm": 5.736636638641357,
+      "learning_rate": 1.2349116607773852e-05,
+      "loss": 0.2925,
+      "step": 53800
+    },
+    {
+      "epoch": 22.65,
+      "eval_cer": 0.3356121191975284,
+      "eval_loss": 2.4841222763061523,
+      "eval_runtime": 427.1982,
+      "eval_samples_per_second": 22.186,
+      "eval_steps_per_second": 2.774,
+      "step": 53800
+    },
+    {
+      "epoch": 22.69,
+      "grad_norm": 6.094464302062988,
+      "learning_rate": 1.227844522968198e-05,
+      "loss": 0.2981,
+      "step": 53900
+    },
+    {
+      "epoch": 22.69,
+      "eval_cer": 0.3367071096163623,
+      "eval_loss": 2.4353983402252197,
+      "eval_runtime": 389.5123,
+      "eval_samples_per_second": 24.333,
+      "eval_steps_per_second": 3.042,
+      "step": 53900
     }
   ],
   "logging_steps": 100,
@@ -8574,7 +8638,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 5.862232878225574e+20,
+  "total_flos": 5.906211157631806e+20,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null