Training in progress, step 18100, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ac85ec2c9aba65ba5a73c821698bedfac0ab44056cd9185b3e753286a39e09c
+oid sha256:df46bc5f465c989d1a8cc6f0e6039781b545120f2df3d1b7fb002a887ec69b00
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f61593c5f78f153cc487d9b55550c24e4357647243b54c97f2007711e16bc6a
+oid sha256:75d0e847683cbb45573b010875b950e16ef41b5d925e08518f7837393f21bd39
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:91da2be2eef1794b5936410e53d53a35f682508081fa6cc959e3b5be890cfca3
+oid sha256:996dfb379c06547b7b56b793c0f9abedb6be7ca70b0ce6367496f82a5b3240ec
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:97ab373cd59fc6f59c96aa1f7842448ef3e4e7e697c811c91fd0af922706a46c
+oid sha256:d8715bc2559d2ee7e5873f236ec06231d78ced8a7948c7205c5f7a1421acc6a6
 size 14567

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b095bc8b48379c3c360d6339687aca8dc7b9bc6703181a7b751f54a1030c1459
+oid sha256:189b4b005e317aa08bdd308bd3d138b2e45b50b0349edd45a9624f1f263b3bd6
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 7.535255735634603,
+  "epoch": 7.619448537150074,
   "eval_steps": 100,
-  "global_step": 17900,
+  "global_step": 18100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2871,6 +2871,38 @@
       "eval_samples_per_second": 26.345,
       "eval_steps_per_second": 3.294,
       "step": 17900
+    },
+    {
+      "epoch": 7.58,
+      "grad_norm": 10.005617141723633,
+      "learning_rate": 3.764098939929329e-05,
+      "loss": 2.1197,
+      "step": 18000
+    },
+    {
+      "epoch": 7.58,
+      "eval_cer": 0.4567307692307692,
+      "eval_loss": 1.900498628616333,
+      "eval_runtime": 386.3412,
+      "eval_samples_per_second": 24.533,
+      "eval_steps_per_second": 3.067,
+      "step": 18000
+    },
+    {
+      "epoch": 7.62,
+      "grad_norm": 3.4333086013793945,
+      "learning_rate": 3.7570318021201415e-05,
+      "loss": 1.3268,
+      "step": 18100
+    },
+    {
+      "epoch": 7.62,
+      "eval_cer": 0.4478413046028704,
+      "eval_loss": 1.8988970518112183,
+      "eval_runtime": 368.4314,
+      "eval_samples_per_second": 25.725,
+      "eval_steps_per_second": 3.216,
+      "step": 18100
     }
   ],
   "logging_steps": 100,
@@ -2878,7 +2910,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 1.9617546605638022e+20,
+  "total_flos": 1.983329480682695e+20,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null