Training in progress, step 32100, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f1945bb6ddf30b2e4e4d92dc6ee4fc7d055d8084fe3ccfb116c609ff34fb39a9
+oid sha256:46b7ed34acfee810bf1df0de4de59541603b041a38fbb4dbcde73ee390120e45
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:968c0b29c790917699e87f69bf4aa6ac1b07a8edffd5fe57d7f83fe35c794971
+oid sha256:14e0b8af6860fa5a3a1dec8a82763be4461db9bc19598a99d13ba72ca5d0b4cd
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5480abc34a2c091a74e506fa88c8f91b9508337e6b6f219e4137a8ec9418527a
+oid sha256:fb216ea78e406e00f2b6177c3e619ca935a753a4d2c9133ddb3865ce6a36e93d
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43d752b29aed24741788ac40b8b42ea9e26aed84562cc2ec34fd9be16f1fa0b9
+oid sha256:180490a53f200a0ccf80e64da4cf9435033e2460013ac665192a9282d9293db7
 size 14567

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:acfed987dc1065bc7e53e8a29458596da758156c2105dbe2e31f48b243130117
+oid sha256:6d4c398e04ff23b7cf398d4be71ed5c551bcad34152f6745e47db5a460b70aee
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 13.344559040202062,
+  "epoch": 13.512944643233004,
   "eval_steps": 100,
-  "global_step": 31700,
+  "global_step": 32100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -5079,6 +5079,70 @@
       "eval_samples_per_second": 25.399,
       "eval_steps_per_second": 3.176,
       "step": 31700
+    },
+    {
+      "epoch": 13.39,
+      "grad_norm": 2.613786458969116,
+      "learning_rate": 2.7891872791519434e-05,
+      "loss": 1.002,
+      "step": 31800
+    },
+    {
+      "epoch": 13.39,
+      "eval_cer": 0.39678737632474287,
+      "eval_loss": 2.017918109893799,
+      "eval_runtime": 398.8604,
+      "eval_samples_per_second": 23.763,
+      "eval_steps_per_second": 2.971,
+      "step": 31800
+    },
+    {
+      "epoch": 13.43,
+      "grad_norm": 5.32037878036499,
+      "learning_rate": 2.7821201413427562e-05,
+      "loss": 1.0059,
+      "step": 31900
+    },
+    {
+      "epoch": 13.43,
+      "eval_cer": 0.40224277501857575,
+      "eval_loss": 2.3004064559936523,
+      "eval_runtime": 375.8974,
+      "eval_samples_per_second": 25.214,
+      "eval_steps_per_second": 3.152,
+      "step": 31900
+    },
+    {
+      "epoch": 13.47,
+      "grad_norm": 1.963639736175537,
+      "learning_rate": 2.7750530035335694e-05,
+      "loss": 0.9866,
+      "step": 32000
+    },
+    {
+      "epoch": 13.47,
+      "eval_cer": 0.4031495639591725,
+      "eval_loss": 2.7950069904327393,
+      "eval_runtime": 392.4567,
+      "eval_samples_per_second": 24.15,
+      "eval_steps_per_second": 3.019,
+      "step": 32000
+    },
+    {
+      "epoch": 13.51,
+      "grad_norm": 10.024706840515137,
+      "learning_rate": 2.767985865724382e-05,
+      "loss": 1.0195,
+      "step": 32100
+    },
+    {
+      "epoch": 13.51,
+      "eval_cer": 0.409443314692425,
+      "eval_loss": 2.4231760501861572,
+      "eval_runtime": 370.8807,
+      "eval_samples_per_second": 25.555,
+      "eval_steps_per_second": 3.195,
+      "step": 32100
     }
   ],
   "logging_steps": 100,
@@ -5086,7 +5150,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 3.473760721513529e+20,
+  "total_flos": 3.5171047954888104e+20,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null