Training in progress, step 18400, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df46bc5f465c989d1a8cc6f0e6039781b545120f2df3d1b7fb002a887ec69b00
+oid sha256:ce9799401c39c71a0cd9f1ebdf6a16f0ac4e723de7b22b57d999c5161366972b
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:75d0e847683cbb45573b010875b950e16ef41b5d925e08518f7837393f21bd39
+oid sha256:2a108474f50a0efca90382b4d207acc17a6d168f1ba66241707a217c75910dce
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:996dfb379c06547b7b56b793c0f9abedb6be7ca70b0ce6367496f82a5b3240ec
+oid sha256:7a9d6a3ff9e16aec0f67353aa981343ca07640557c27a59eca4811f64c218c41
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8715bc2559d2ee7e5873f236ec06231d78ced8a7948c7205c5f7a1421acc6a6
-size 14567
+oid sha256:b3841b9e537739134e582030ad4b8b96b4b45677b00f72ce75fa56b4b4070d92
+size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:189b4b005e317aa08bdd308bd3d138b2e45b50b0349edd45a9624f1f263b3bd6
+oid sha256:7c544fcd0738aab978188bc5cbfad82678c3f7d9d75b06c8c4f740f0ef0a9607
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 7.619448537150074,
+  "epoch": 7.745737739423279,
   "eval_steps": 100,
-  "global_step": 18100,
+  "global_step": 18400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2903,6 +2903,54 @@
       "eval_samples_per_second": 25.725,
       "eval_steps_per_second": 3.216,
       "step": 18100
+    },
+    {
+      "epoch": 7.66,
+      "grad_norm": 4.548975944519043,
+      "learning_rate": 3.749964664310954e-05,
+      "loss": 1.3146,
+      "step": 18200
+    },
+    {
+      "epoch": 7.66,
+      "eval_cer": 0.4571047280122013,
+      "eval_loss": 2.1630055904388428,
+      "eval_runtime": 388.4273,
+      "eval_samples_per_second": 24.401,
+      "eval_steps_per_second": 3.051,
+      "step": 18200
+    },
+    {
+      "epoch": 7.7,
+      "grad_norm": 1.7991045713424683,
+      "learning_rate": 3.742897526501767e-05,
+      "loss": 2.0035,
+      "step": 18300
+    },
+    {
+      "epoch": 7.7,
+      "eval_cer": 0.45147579289038364,
+      "eval_loss": 2.4393255710601807,
+      "eval_runtime": 378.3611,
+      "eval_samples_per_second": 25.05,
+      "eval_steps_per_second": 3.132,
+      "step": 18300
+    },
+    {
+      "epoch": 7.75,
+      "grad_norm": 2.6425940990448,
+      "learning_rate": 3.73583038869258e-05,
+      "loss": 1.3294,
+      "step": 18400
+    },
+    {
+      "epoch": 7.75,
+      "eval_cer": 0.4522603730788784,
+      "eval_loss": 1.833477258682251,
+      "eval_runtime": 381.8605,
+      "eval_samples_per_second": 24.821,
+      "eval_steps_per_second": 3.103,
+      "step": 18400
     }
   ],
   "logging_steps": 100,
@@ -2910,7 +2958,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 1.983329480682695e+20,
+  "total_flos": 2.0158114839380017e+20,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null