Training in progress, step 13900, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:30d085aaa0f82d54e68daaff76a5edf1a83caa6fc552bc63e28873040f03bf9a
+oid sha256:fb04ec4f3d36dd72f1880e67e379df925d69c4c1ee3be76fa1a43897ef9b16aa
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b3208fa1d71ea807e3133c94abe026dccee956ff323c98dc52647f372ccad32
+oid sha256:5c667ab0a8a130f4910409ed5385aecf8d04f340e0b73bf61de9998e419ee5ef
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e9806b2d6e21ab5a74e92bf2a1176e3dc60de6b2f8bacd510d899a41faeac49
+oid sha256:10d91ae259b3415ae409d9b1aee3a858751c6d1e1cb5fb402436da9dbabb9012
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ce0016f9e7b603d570201d200237a8a9050741d2a9b12cc7d3687acfd6a9d1c
+oid sha256:9b368cb744e028a8d7ec06984741ea4d567105d2c13b979cf5f116c73e24cca3
 size 14567

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a88883a6f3ed79ad9be6875b04b7df75d671a094bc1c6e0ebf303bf9ba54f1d
+oid sha256:2b01cc7e72200b1387dbf60d697bf53f87ac3009f238952d98a6ef44ab1024b0
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 5.767206903809724,
+  "epoch": 5.8513997053251945,
   "eval_steps": 100,
-  "global_step": 13700,
+  "global_step": 13900,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2199,6 +2199,38 @@
       "eval_samples_per_second": 25.905,
       "eval_steps_per_second": 3.239,
       "step": 13700
+    },
+    {
+      "epoch": 5.81,
+      "grad_norm": 1.8314547538757324,
+      "learning_rate": 4.060777385159011e-05,
+      "loss": 2.3976,
+      "step": 13800
+    },
+    {
+      "epoch": 5.81,
+      "eval_cer": 0.4735149192444566,
+      "eval_loss": 2.7786667346954346,
+      "eval_runtime": 377.8869,
+      "eval_samples_per_second": 25.082,
+      "eval_steps_per_second": 3.136,
+      "step": 13800
+    },
+    {
+      "epoch": 5.85,
+      "grad_norm": 3.4417295455932617,
+      "learning_rate": 4.0537102473498235e-05,
+      "loss": 2.0057,
+      "step": 13900
+    },
+    {
+      "epoch": 5.85,
+      "eval_cer": 0.47049147471745334,
+      "eval_loss": 3.252101182937622,
+      "eval_runtime": 365.7598,
+      "eval_samples_per_second": 25.913,
+      "eval_steps_per_second": 3.24,
+      "step": 13900
     }
   ],
   "logging_steps": 100,
@@ -2206,7 +2238,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 1.5014329647964724e+20,
+  "total_flos": 1.523070949553679e+20,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null