Training in progress, step 38500, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28ca21937cf2d822209b3c05259b3ccf17f101b2990d8d77f4f382436b31f814
+oid sha256:38fe8c8210e898bd06af9b7e9f27fbc330459317179a7a884008078c60e0c10f
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:51b1bd241413fe670b447d5fde039c29e6fd164bd0971b9a810ec7e6e9644b5a
+oid sha256:90543948d1b0ff49713db63f240147f17ff54181792a7b8c29240f456f05f355
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e5f33e40ef0be0f68a21ea1be25305932b46c0041756190634386e045512b523
+oid sha256:5b7214ac524d3177b868886fd848f68e1df212f4c4706f4d11e43917a7fda086
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49898aff321bba13610449837ec6d94a8745b9be57e0cd4bf6c2fa192326186c
-size 14503
+oid sha256:df7df7f93f7fbc3135f5dffa21af5c0112888a2aa76e699392d1402149cfd3a3
+size 14567

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:32bd40b48ca3b96bc4530717bd2eed9f4f0e2a6be042cb204a84f6ce13b0abc0
+oid sha256:2e46ccca528ca5f7b67e61b75ba1fbda18ae88f62be2df40952de726b01c6277
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 16.122921490212587,
+  "epoch": 16.207114291728058,
   "eval_steps": 100,
-  "global_step": 38300,
+  "global_step": 38500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -6135,6 +6135,38 @@
       "eval_samples_per_second": 25.182,
       "eval_steps_per_second": 3.148,
       "step": 38300
+    },
+    {
+      "epoch": 16.17,
+      "grad_norm": 3.3271946907043457,
+      "learning_rate": 2.322826855123675e-05,
+      "loss": 0.7428,
+      "step": 38400
+    },
+    {
+      "epoch": 16.17,
+      "eval_cer": 0.37296644636502285,
+      "eval_loss": 1.7951716184616089,
+      "eval_runtime": 401.591,
+      "eval_samples_per_second": 23.601,
+      "eval_steps_per_second": 2.951,
+      "step": 38400
+    },
+    {
+      "epoch": 16.21,
+      "grad_norm": 2.013002395629883,
+      "learning_rate": 2.3157597173144876e-05,
+      "loss": 0.7499,
+      "step": 38500
+    },
+    {
+      "epoch": 16.21,
+      "eval_cer": 0.37256560165812835,
+      "eval_loss": 1.7327371835708618,
+      "eval_runtime": 380.9473,
+      "eval_samples_per_second": 24.88,
+      "eval_steps_per_second": 3.111,
+      "step": 38500
     }
   ],
   "logging_steps": 100,
@@ -6142,7 +6174,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 4.196836719020362e+20,
+  "total_flos": 4.2189272769289296e+20,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null