Training in progress, step 16100, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c20ad3beef3f33ef2b4c145c9b9506f9a226a39e2e73693f7ae2fcfc0dcf1cd
+oid sha256:ebf347754f884e2be6c737513e953f16639c828eacaa1196164f202af9bb103e
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:74d0557152fa6f6a5c4206d20e2e5e3e65c08a54d396cdd08189203105bb821e
+oid sha256:a8fca4698c7851865d350d5a18365b9dde8232295e53b36b937ec9bf1c60fe24
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49a17f38b1772819369863ac91e47ffc5deca1f2b7e3fbb755cc5669eb6f2884
+oid sha256:7159f5fbaa38bda316b60c946c6762774b19db88edab49a28e92d29d69196ee1
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f938892d18549bfd11854e754003e9c1d26470f2c462d1c3bdac6d13825d7005
+oid sha256:322006629ea084c5430f118689d25b57d89dd320732fc96397a67db570b5b88d
 size 14567

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49c14c6d2163c777317ea1561699a4fab0cc691b0ee652db9a2586b628592aa5
+oid sha256:e8edd30f1a6fae9f9bbc6afdf7e51d48a66558699024e20d036d47bf4e1de3c2
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 6.693327720479899,
+  "epoch": 6.77752052199537,
   "eval_steps": 100,
-  "global_step": 15900,
+  "global_step": 16100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2551,6 +2551,38 @@
       "eval_samples_per_second": 26.109,
       "eval_steps_per_second": 3.264,
       "step": 15900
+    },
+    {
+      "epoch": 6.74,
+      "grad_norm": 8.302891731262207,
+      "learning_rate": 3.9053710247349825e-05,
+      "loss": 1.4603,
+      "step": 16000
+    },
+    {
+      "epoch": 6.74,
+      "eval_cer": 0.47225128074772205,
+      "eval_loss": 1.5901261568069458,
+      "eval_runtime": 376.5314,
+      "eval_samples_per_second": 25.172,
+      "eval_steps_per_second": 3.147,
+      "step": 16000
+    },
+    {
+      "epoch": 6.78,
+      "grad_norm": 3.2967019081115723,
+      "learning_rate": 3.898303886925795e-05,
+      "loss": 1.5493,
+      "step": 16100
+    },
+    {
+      "epoch": 6.78,
+      "eval_cer": 0.47416751398068124,
+      "eval_loss": 1.6550699472427368,
+      "eval_runtime": 363.1067,
+      "eval_samples_per_second": 26.103,
+      "eval_steps_per_second": 3.264,
+      "step": 16100
     }
   ],
   "logging_steps": 100,
@@ -2558,7 +2590,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 1.7421368190330087e+20,
+  "total_flos": 1.7642477539687376e+20,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null