Training in progress, step 27500, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e15296cc7fc7c22faf537cf2d8c8189212cd4050aec0cc26ecd5ca6b2b31430c
+oid sha256:2990a3bb6d69e18c103cd2337804d461c6c67326e8e0f062fe20b13112717c31
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:efb178d8b8052b34bfc9ce5171bddbd008d7445958fd6793e6c78c28460f94e3
+oid sha256:a3f96081b3cdc78cf713fd98ff997e0bb9a91ae50630385c65abc9cf9314347b
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:616fbff97ed13f412ac2118b023cc68e97d2cdaa667165e80291c9b722839e9c
+oid sha256:7000394dc2c4f6debb1651edfed8e64b05b328880d95d9bde162788468b1edcb
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5e1fa851642b5df9872122f6cd49ffbd3855aa0c135f0547c13649b70bce71d4
-size 14503
+oid sha256:f83e3367e58d9a4431dc150c90b3ffeb9508f969b56e80c75c390795e94f6d91
+size 14567

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1556b06bd9834de95519bce0dfbc04d14a4931ce96de22038d246f85d978575d
+oid sha256:a9171e687a5332bf79e87905511cf6fd0514a885fad349a7f1665c05a38dc32e
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 11.492317406861714,
+  "epoch": 11.576510208377183,
   "eval_steps": 100,
-  "global_step": 27300,
+  "global_step": 27500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -4375,6 +4375,38 @@
       "eval_samples_per_second": 24.145,
       "eval_steps_per_second": 3.019,
       "step": 27300
+    },
+    {
+      "epoch": 11.53,
+      "grad_norm": 19.142953872680664,
+      "learning_rate": 3.1e-05,
+      "loss": 1.1284,
+      "step": 27400
+    },
+    {
+      "epoch": 11.53,
+      "eval_cer": 0.43251877126432287,
+      "eval_loss": 2.1405186653137207,
+      "eval_runtime": 413.4099,
+      "eval_samples_per_second": 22.926,
+      "eval_steps_per_second": 2.866,
+      "step": 27400
+    },
+    {
+      "epoch": 11.58,
+      "grad_norm": 9.353096961975098,
+      "learning_rate": 3.092932862190813e-05,
+      "loss": 1.3106,
+      "step": 27500
+    },
+    {
+      "epoch": 11.58,
+      "eval_cer": 0.4250787024363537,
+      "eval_loss": 2.7651588916778564,
+      "eval_runtime": 372.5808,
+      "eval_samples_per_second": 25.439,
+      "eval_steps_per_second": 3.181,
+      "step": 27500
     }
   ],
   "logging_steps": 100,
@@ -4382,7 +4414,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 2.992071149315134e+20,
+  "total_flos": 3.014141824593385e+20,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null