Training in progress, step 46700, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b27f517045a239ca3d4c09cfcbc5d90d49a9dc5fb03fcb2ed0885dce063b5310
+oid sha256:34c44a9f07e1b8aa6dc225c094543b21169c807ababebf17aecec1cdab52533e
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a4020fe34ad40d60ab49cb79998fc9757fa6962619664a49f924687783b3f01
+oid sha256:8fa8ecef7a478c24fdefb985526ee50f6d66cb28942cfbb7207572dd699188e0
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b3789d043057ca3bdf90a7ba4cfb8ad1bdc5bbc2f61f9921c6b8d8b227b8605
+oid sha256:264756f803302ce1b7070f07c807bd37de2d9873f549d008ab996618e392720f
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3497a81af3830b12cea55fc1a002714afd90521c8567293cc3b2539688efc021
-size 14567
+oid sha256:14eca18c97605af6ae4689d37dc0ca3a788eaef7ff89fb5e8f8f6afe500d717c
+size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c96c7193a25b743904e5970326ee4765878ca8dbd521d975c5aaa2469d0561c
+oid sha256:e80af03aafdc9b8ba4ba9d26243edd821da4e02e74dd9d4d85df35d2aa6ecc98
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 19.574826352346875,
+  "epoch": 19.659019153862346,
   "eval_steps": 100,
-  "global_step": 46500,
+  "global_step": 46700,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -7447,6 +7447,38 @@
       "eval_samples_per_second": 25.464,
       "eval_steps_per_second": 3.184,
       "step": 46500
+    },
+    {
+      "epoch": 19.62,
+      "grad_norm": 2.0272178649902344,
+      "learning_rate": 1.7436042402826856e-05,
+      "loss": 0.4745,
+      "step": 46600
+    },
+    {
+      "epoch": 19.62,
+      "eval_cer": 0.3511057447890188,
+      "eval_loss": 3.3171424865722656,
+      "eval_runtime": 381.183,
+      "eval_samples_per_second": 24.865,
+      "eval_steps_per_second": 3.109,
+      "step": 46600
+    },
+    {
+      "epoch": 19.66,
+      "grad_norm": 4.2316412925720215,
+      "learning_rate": 1.7365371024734984e-05,
+      "loss": 0.4875,
+      "step": 46700
+    },
+    {
+      "epoch": 19.66,
+      "eval_cer": 0.3484904774940362,
+      "eval_loss": 2.8240554332733154,
+      "eval_runtime": 368.9178,
+      "eval_samples_per_second": 25.691,
+      "eval_steps_per_second": 3.212,
+      "step": 46700
     }
   ],
   "logging_steps": 100,
@@ -7454,7 +7486,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 5.096052922697529e+20,
+  "total_flos": 5.1179007006614834e+20,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null