Training in progress, step 28100, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d49c4af7d6780b5bb59189d0dd1867f0b68d29fb3ba703be67e4405ffdd2f7b
+oid sha256:591e41e3676418cd1c0210ac5103de2c047f43c3f40415a403018bd7d93769db
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b3d226082b9d4eb89eb67558845e0d50815390f41da6ece0ea8d6981473441ce
+oid sha256:863179f4b823aa37294186590a641d7ed7cb2231bfd420a0c652e61f745b5712
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8cb4a963bc15dc86cedf79321c880d41e114671433f6bd415c17a07b684173dd
+oid sha256:95a10135880171da7d27bdded0b5de859e991b9d6813ef6865b69bba57646c69
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8dd54598a42f926ce0b6c3ce03e26f6e03ec6fcf83016be5d7c0d02f5bedcfc6
-size 14503
+oid sha256:03f3a47e3fd45356df14e05e927bc513c40aadb8fa39b6a917dcbafa2c841ea6
+size 14567

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b0ced60e8e837d5a867fc1635f2587bd5e4112e1921c82905c17a08e817c88f2
+oid sha256:5f156c07503fa6a6e1c8ecec02179bc06ca2b282b6a513c49c6076a8fe0c0f5f
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 11.744895811408124,
+  "epoch": 11.829088612923595,
   "eval_steps": 100,
-  "global_step": 27900,
+  "global_step": 28100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -4471,6 +4471,38 @@
       "eval_samples_per_second": 25.238,
       "eval_steps_per_second": 3.155,
       "step": 27900
+    },
+    {
+      "epoch": 11.79,
+      "grad_norm": 2.216014862060547,
+      "learning_rate": 3.0576678445229683e-05,
+      "loss": 1.2095,
+      "step": 28000
+    },
+    {
+      "epoch": 11.79,
+      "eval_cer": 0.42844188729420046,
+      "eval_loss": 1.8659263849258423,
+      "eval_runtime": 392.5017,
+      "eval_samples_per_second": 24.148,
+      "eval_steps_per_second": 3.019,
+      "step": 28000
+    },
+    {
+      "epoch": 11.83,
+      "grad_norm": 6.676244258880615,
+      "learning_rate": 3.0506007067137808e-05,
+      "loss": 1.4826,
+      "step": 28100
+    },
+    {
+      "epoch": 11.83,
+      "eval_cer": 0.4170275898478745,
+      "eval_loss": 1.5196857452392578,
+      "eval_runtime": 370.7857,
+      "eval_samples_per_second": 25.562,
+      "eval_steps_per_second": 3.196,
+      "step": 28100
     }
   ],
   "logging_steps": 100,
@@ -4478,7 +4510,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 3.057677998172635e+20,
+  "total_flos": 3.079345538947467e+20,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null