Training in progress, step 45000, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d986491485545d732d2543b339c31a259dcb270837f25d91f6c0b31f3ac46e38
+oid sha256:91e422627c4b9c768f46280d63fdbcfda35620e774f98056638ba875f3575284
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:af17d7c2b3c7bf2b538b3ba90686b2f4e4ed09dd4b9a9afb1fe76d2905f4f613
+oid sha256:acf19318ad1b6dc72bddec929f0849bc212f2e1e8bd60f19ac70115441c83c91
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:33f3fc9081c7129e45e682bf733c743600617e1c0e5a4ea79dca6c91a1e29f04
+oid sha256:e5d07a63df9aaae7d187b5731e2c4c19721e7a2e9545c19b5722e4ffda120ed9
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ffd4ac7d16e7a8d42ef9c4f13d915aa5d41769606ce52a3a1031a916b016bf9
-size 14567
+oid sha256:815af6775e420c509219caee17b9a5516bbf2b05365eac817aa0f9a01cbd8f8d
+size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e3647f0c4181d85f62ad117eca30124a1bd2379804c9e34d325ea3a74a4ab0d
+oid sha256:02a1219b2614f7ac1e5741ff596a810f142ab9bd2e0d40eb1eb0d44675ea0fea
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 18.859187539465374,
+  "epoch": 18.943380340980845,
   "eval_steps": 100,
-  "global_step": 44800,
+  "global_step": 45000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -7175,6 +7175,38 @@
       "eval_samples_per_second": 25.04,
       "eval_steps_per_second": 3.131,
       "step": 44800
+    },
+    {
+      "epoch": 18.9,
+      "grad_norm": 1.822228193283081,
+      "learning_rate": 1.8637455830388695e-05,
+      "loss": 0.5733,
+      "step": 44900
+    },
+    {
+      "epoch": 18.9,
+      "eval_cer": 0.34930194360799344,
+      "eval_loss": 2.7781569957733154,
+      "eval_runtime": 405.1046,
+      "eval_samples_per_second": 23.396,
+      "eval_steps_per_second": 2.925,
+      "step": 44900
+    },
+    {
+      "epoch": 18.94,
+      "grad_norm": 15.387603759765625,
+      "learning_rate": 1.856678445229682e-05,
+      "loss": 0.5554,
+      "step": 45000
+    },
+    {
+      "epoch": 18.94,
+      "eval_cer": 0.35281422314340466,
+      "eval_loss": 2.2615067958831787,
+      "eval_runtime": 386.1566,
+      "eval_samples_per_second": 24.544,
+      "eval_steps_per_second": 3.069,
+      "step": 45000
     }
   ],
   "logging_steps": 100,
@@ -7182,7 +7214,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 4.909167843123271e+20,
+  "total_flos": 4.930677119902053e+20,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null