Training in progress, step 45900, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8dcae94e0ba5659a94762126ca017500f9640d109bedc1a86e16f7c3a364e9f5
+oid sha256:777938124b8f08a6fc51de91ba4f6a248e0db6ecac962b10d96fb7af7371d947
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a4dca8d70c56075bf2982f5f2b6c6bc3e36a911dffcbaf478a2abecf931e8e68
+oid sha256:426caf72cf84a12bb83fee44c5ab19d9a2c05db3c88c152eeba1f77afb9c94e6
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:194585cbf7d9cfd62136cd29e1512102cdc3ce800cad797ad714867a01a807e3
+oid sha256:e181b4508fa0c0aef068c5ce9add7596cdd91480b74f68ef60dd67316c6f7a0c
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:01cb821d23c120c3f2fb4bfd56f972b2f4b5203cf129d2966782cb58aafc588a
-size 14503
+oid sha256:ae2667702793407db19d3728855aeacbfeb7c14b67574cd2f6c8c45fc93cc266
+size 14567

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b83145c90d97eef0fc9a5597e2a0947d443830911cd43cef4159f379916f7334
+oid sha256:bac30970e8a48e7dc94fd4d8f03dc31e7111fa8cfb4c3ecd5d2ab0fbdb55b042
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 19.238055146284992,
+  "epoch": 19.322247947800463,
   "eval_steps": 100,
-  "global_step": 45700,
+  "global_step": 45900,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -7319,6 +7319,38 @@
       "eval_samples_per_second": 25.748,
       "eval_steps_per_second": 3.219,
       "step": 45700
+    },
+    {
+      "epoch": 19.28,
+      "grad_norm": 2.2689895629882812,
+      "learning_rate": 1.8001413427561838e-05,
+      "loss": 0.471,
+      "step": 45800
+    },
+    {
+      "epoch": 19.28,
+      "eval_cer": 0.3532492863008877,
+      "eval_loss": 2.3049328327178955,
+      "eval_runtime": 377.068,
+      "eval_samples_per_second": 25.136,
+      "eval_steps_per_second": 3.143,
+      "step": 45800
+    },
+    {
+      "epoch": 19.32,
+      "grad_norm": 6.475673198699951,
+      "learning_rate": 1.7930742049469966e-05,
+      "loss": 0.4834,
+      "step": 45900
+    },
+    {
+      "epoch": 19.32,
+      "eval_cer": 0.3522642837589457,
+      "eval_loss": 2.4670591354370117,
+      "eval_runtime": 369.8781,
+      "eval_samples_per_second": 25.625,
+      "eval_steps_per_second": 3.204,
+      "step": 45900
     }
   ],
   "logging_steps": 100,
@@ -7326,7 +7358,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 5.008227787418482e+20,
+  "total_flos": 5.030211590848743e+20,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null