Training in progress, step 40600, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6188044dbfec3db480d47482cff436a4a882d1e2da837b0331ecfd8d831437af
+oid sha256:b03dc9e0469a4511d3960e8ccc32ec9be77fb87dc6998ca5230f5d24b80dd574
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:30f19f0d03c8ad0878ba2daf65268a6123dc51dcef9f90b49e7b00d458a2ed2b
+oid sha256:e8ef085b7b6748391bb90ac62d5548dc82db571deca605fc3e13a91144e2ddcb
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d239ea849485001cc71d8e8f299676d711228873c7837c94f2dd42aa10fa13af
+oid sha256:dfa7234bcf7f52f0002950ee4c95f584023eaebde1bd2b931543505530d4bf62
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:200cb07eac893fb8762313e23cc9c505d8353297219dcb475604278f65095793
-size 14567
+oid sha256:9c2dc3633beab3a54043bc13682c039467daffe3d3f1de119b8bf092c5378995
+size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8af456d177bc478bc5d435dfa70de8769ea30f35830dafa9b724c49a14923c8
+oid sha256:e15e995c71854cd5ff2c0e03c1bb6ee2b6ba36e7be4d986833bffdd5d14ed7fc
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 17.006945906125026,
+  "epoch": 17.091138707640496,
   "eval_steps": 100,
-  "global_step": 40400,
+  "global_step": 40600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -6471,6 +6471,38 @@
       "eval_samples_per_second": 24.24,
       "eval_steps_per_second": 3.031,
       "step": 40400
+    },
+    {
+      "epoch": 17.05,
+      "grad_norm": 1.9776512384414673,
+      "learning_rate": 2.1744876325088338e-05,
+      "loss": 0.6509,
+      "step": 40500
+    },
+    {
+      "epoch": 17.05,
+      "eval_cer": 0.3647295764733487,
+      "eval_loss": 2.075551986694336,
+      "eval_runtime": 398.6714,
+      "eval_samples_per_second": 23.774,
+      "eval_steps_per_second": 2.972,
+      "step": 40500
+    },
+    {
+      "epoch": 17.09,
+      "grad_norm": 3.229382276535034,
+      "learning_rate": 2.167420494699647e-05,
+      "loss": 0.6699,
+      "step": 40600
+    },
+    {
+      "epoch": 17.09,
+      "eval_cer": 0.36611786789722733,
+      "eval_loss": 1.8951997756958008,
+      "eval_runtime": 377.7399,
+      "eval_samples_per_second": 25.091,
+      "eval_steps_per_second": 3.137,
+      "step": 40600
     }
   ],
   "logging_steps": 100,
@@ -6478,7 +6510,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 4.4276874138754004e+20,
+  "total_flos": 4.449729914752364e+20,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null