Training in progress, step 16500, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b8f159de36d64281ddd74c716173e22dda43638490d210d663f6239504808c0
+oid sha256:ffcfe122bd2d59d01967428904ec5ea9fa859cb879f1770bb1d1e760b1b7688c
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0177c8aa518ca2ca2c236f872b9ea81f1b5759873aabb911e5262ebffe2abe3b
+oid sha256:f82abcf3aa79e7aebdfb7e800e2da4ec60cfd150519c69f6e42fff57f12e5649
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9bb867ed0ec5031e1aeb6ba6b339623fbe0e6f95f55f1e5e5eb609dd6315043f
+oid sha256:4863c0159897cbd8e6cad80102a7234e43e4dd9ec61c50a16d612844e381c121
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c21a862ff8666bb46f50a482a414a6564395b399e94962d06b8d979c0e47eaf1
-size 14503
+oid sha256:958c40c9a12bc1ec4000782ee24253ec47677cd329681042cb696da20d4daa37
+size 14567

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d885b462e40c8dc986005d71bf297429595c7992d35a7d138df0b70b9a59f663
+oid sha256:815a23a9cc5b941ec9802a205234677f07d3ff4d13a1a86a9f1b1c15fe345d83
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 6.861713323510839,
+  "epoch": 6.94590612502631,
   "eval_steps": 100,
-  "global_step": 16300,
+  "global_step": 16500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2615,6 +2615,38 @@
       "eval_samples_per_second": 26.288,
       "eval_steps_per_second": 3.287,
       "step": 16300
+    },
+    {
+      "epoch": 6.9,
+      "grad_norm": 8.180316925048828,
+      "learning_rate": 3.877102473498234e-05,
+      "loss": 1.6474,
+      "step": 16400
+    },
+    {
+      "epoch": 6.9,
+      "eval_cer": 0.4800946384576278,
+      "eval_loss": 2.309068202972412,
+      "eval_runtime": 377.3872,
+      "eval_samples_per_second": 25.115,
+      "eval_steps_per_second": 3.14,
+      "step": 16400
+    },
+    {
+      "epoch": 6.95,
+      "grad_norm": 1.7500585317611694,
+      "learning_rate": 3.870035335689046e-05,
+      "loss": 1.3755,
+      "step": 16500
+    },
+    {
+      "epoch": 6.95,
+      "eval_cer": 0.4641219545578976,
+      "eval_loss": 1.5506832599639893,
+      "eval_runtime": 359.5594,
+      "eval_samples_per_second": 26.36,
+      "eval_steps_per_second": 3.296,
+      "step": 16500
     }
   ],
   "logging_steps": 100,
@@ -2622,7 +2654,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 1.785994345378592e+20,
+  "total_flos": 1.807384038236432e+20,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null