Training in progress, step 8900, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4bc6ee20e92be470779004e487dfec7d1c7ec07a2307cf5787abeeb10837bfba
+oid sha256:0a3d3cd63d6d2b7817fcaeb0e700ec073e895b1392f5b11376dc400ab356ad89
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e3073616d523d72de602ba9879e633da89b6ad0e5050b67500ae028d8db836c3
+oid sha256:19af523b850e718dee98ab66147dcd21a5c1fd9aaa4d714d77ca732c79c11797
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:30f6c92c06d152dcf5d8bd4289cc9ae76a99dba6607556e40d75736ff19eb390
+oid sha256:7b3a0ca77765fef36444952fa33403a178b84113717e1a5400a06d438d3d2241
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b52bc615e0fc35d8314852721291c3faa4ffac229e09429b2519ba20b083ffa6
-size 14567
+oid sha256:bf0eecf02c50d92c6abe3654ed45f596e15ae45458fb25a4d3411d8513d6ee7d
+size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a3d5eed609678a53ce1b4b4f600df93cccb5300509c18134b26b05aaf3106e36
+oid sha256:76ddf596f4dea4d14b5183a987af8ee8a1b47eeae5be8f03bff40eab4d3ed32c
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 3.6623868659229637,
+  "epoch": 3.746579667438434,
   "eval_steps": 100,
-  "global_step": 8700,
+  "global_step": 8900,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1399,6 +1399,38 @@
       "eval_samples_per_second": 26.524,
       "eval_steps_per_second": 3.316,
       "step": 8700
+    },
+    {
+      "epoch": 3.7,
+      "grad_norm": 14.154474258422852,
+      "learning_rate": 4.414063604240283e-05,
+      "loss": 1.6646,
+      "step": 8800
+    },
+    {
+      "epoch": 3.7,
+      "eval_cer": 0.49412175902389427,
+      "eval_loss": 2.7898120880126953,
+      "eval_runtime": 372.8281,
+      "eval_samples_per_second": 25.422,
+      "eval_steps_per_second": 3.178,
+      "step": 8800
+    },
+    {
+      "epoch": 3.75,
+      "grad_norm": 6.580379486083984,
+      "learning_rate": 4.406996466431096e-05,
+      "loss": 1.9858,
+      "step": 8900
+    },
+    {
+      "epoch": 3.75,
+      "eval_cer": 0.5368801572093387,
+      "eval_loss": 3.0827128887176514,
+      "eval_runtime": 359.3692,
+      "eval_samples_per_second": 26.374,
+      "eval_steps_per_second": 3.297,
+      "step": 8900
     }
   ],
   "logging_steps": 100,
@@ -1406,7 +1438,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 9.533433836349682e+19,
+  "total_flos": 9.754876784382558e+19,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null