Training in progress, step 16300, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ebf347754f884e2be6c737513e953f16639c828eacaa1196164f202af9bb103e
+oid sha256:7b8f159de36d64281ddd74c716173e22dda43638490d210d663f6239504808c0
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a8fca4698c7851865d350d5a18365b9dde8232295e53b36b937ec9bf1c60fe24
+oid sha256:0177c8aa518ca2ca2c236f872b9ea81f1b5759873aabb911e5262ebffe2abe3b
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7159f5fbaa38bda316b60c946c6762774b19db88edab49a28e92d29d69196ee1
+oid sha256:9bb867ed0ec5031e1aeb6ba6b339623fbe0e6f95f55f1e5e5eb609dd6315043f
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:322006629ea084c5430f118689d25b57d89dd320732fc96397a67db570b5b88d
-size 14567
+oid sha256:c21a862ff8666bb46f50a482a414a6564395b399e94962d06b8d979c0e47eaf1
+size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e8edd30f1a6fae9f9bbc6afdf7e51d48a66558699024e20d036d47bf4e1de3c2
+oid sha256:d885b462e40c8dc986005d71bf297429595c7992d35a7d138df0b70b9a59f663
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 6.77752052199537,
+  "epoch": 6.861713323510839,
   "eval_steps": 100,
-  "global_step": 16100,
+  "global_step": 16300,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2583,6 +2583,38 @@
       "eval_samples_per_second": 26.103,
       "eval_steps_per_second": 3.264,
       "step": 16100
+    },
+    {
+      "epoch": 6.82,
+      "grad_norm": 2.848189115524292,
+      "learning_rate": 3.891236749116608e-05,
+      "loss": 1.5642,
+      "step": 16200
+    },
+    {
+      "epoch": 6.82,
+      "eval_cer": 0.4807154589183059,
+      "eval_loss": 2.1456046104431152,
+      "eval_runtime": 376.8904,
+      "eval_samples_per_second": 25.148,
+      "eval_steps_per_second": 3.144,
+      "step": 16200
+    },
+    {
+      "epoch": 6.86,
+      "grad_norm": 4.148609638214111,
+      "learning_rate": 3.88416961130742e-05,
+      "loss": 1.379,
+      "step": 16300
+    },
+    {
+      "epoch": 6.86,
+      "eval_cer": 0.4555746744358844,
+      "eval_loss": 1.7261931896209717,
+      "eval_runtime": 360.5421,
+      "eval_samples_per_second": 26.288,
+      "eval_steps_per_second": 3.287,
+      "step": 16300
     }
   ],
   "logging_steps": 100,
@@ -2590,7 +2622,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 1.7642477539687376e+20,
+  "total_flos": 1.785994345378592e+20,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null