Training in progress, step 38700, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:38fe8c8210e898bd06af9b7e9f27fbc330459317179a7a884008078c60e0c10f
+oid sha256:78672eae05411d7dfefd57b3254fa47cd72769991a6baaa5e1092236d2622db5
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90543948d1b0ff49713db63f240147f17ff54181792a7b8c29240f456f05f355
+oid sha256:22915e67daad57243bf515bd80ed79bb3ec54110fd7c78d46422156d5fdcb88c
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b7214ac524d3177b868886fd848f68e1df212f4c4706f4d11e43917a7fda086
+oid sha256:380581ce44959c9c175fb724813187d7c36d1ce791ca3dfe21d6b0b4f80f6aaf
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df7df7f93f7fbc3135f5dffa21af5c0112888a2aa76e699392d1402149cfd3a3
-size 14567
+oid sha256:f1d509fbeb2d6b8e5d595bc7a9e0a2d01ae61002e35af8526d5144d83377487f
+size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e46ccca528ca5f7b67e61b75ba1fbda18ae88f62be2df40952de726b01c6277
+oid sha256:8ece92974bf15f79708e9c8cceb24d9f0629188b90b52a77e12c8501d92cc731
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 16.207114291728058,
+  "epoch": 16.291307093243528,
   "eval_steps": 100,
-  "global_step": 38500,
+  "global_step": 38700,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -6167,6 +6167,38 @@
       "eval_samples_per_second": 24.88,
       "eval_steps_per_second": 3.111,
       "step": 38500
+    },
+    {
+      "epoch": 16.25,
+      "grad_norm": 3.8447253704071045,
+      "learning_rate": 2.3086925795053004e-05,
+      "loss": 0.7266,
+      "step": 38600
+    },
+    {
+      "epoch": 16.25,
+      "eval_cer": 0.37181523992022214,
+      "eval_loss": 2.117140293121338,
+      "eval_runtime": 398.2953,
+      "eval_samples_per_second": 23.796,
+      "eval_steps_per_second": 2.975,
+      "step": 38600
+    },
+    {
+      "epoch": 16.29,
+      "grad_norm": 2.052280902862549,
+      "learning_rate": 2.301625441696113e-05,
+      "loss": 0.737,
+      "step": 38700
+    },
+    {
+      "epoch": 16.29,
+      "eval_cer": 0.37181768409526417,
+      "eval_loss": 2.6678144931793213,
+      "eval_runtime": 376.034,
+      "eval_samples_per_second": 25.205,
+      "eval_steps_per_second": 3.151,
+      "step": 38700
     }
   ],
   "logging_steps": 100,
@@ -6174,7 +6206,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 4.2189272769289296e+20,
+  "total_flos": 4.2406406618689883e+20,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null