Training in progress, step 47700, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:67401216b3029d2622e7e7add3d17e2a39d754ad2562031455d96e2f627ae67b
+oid sha256:c737cef3e8496bd78bd7ec0023f68befe3d9a9c05598534030ccd26c85918ac6
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6921906aba6ad6cda84ac2dad9392fde118c107f9c07cce5a4b585abe35d446d
+oid sha256:f2723715a10a82482c591b82cb51edd59abae6401d5ba96ea07090b181b9d643
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb52b0ddcb7b49c326f60274849ef6aa3c79a378160d3f09440dbe910b761c44
+oid sha256:9b283c3ae87191de5fca07697a3974a9d234e69848cf8838bc28bee17cf75ce3
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c20e682f3fe40fa57d88e22486ddd5912b58563883c794fa3b1d8da05268377
-size 14567
+oid sha256:392684c134f5cf29a9c14bb0a154c1d7d4d520741978198c633be27f537faa31
+size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:372a4198b83fdb5e8fb2ecd27baf4c7bfc16f7ae1e02bdddaa16958cd86125f9
+oid sha256:9916ddee38224af3ba1b5cf7e13befa56143fa30905487537b8489305fe5fcae
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 19.995790359924225,
+  "epoch": 20.079983161439696,
   "eval_steps": 100,
-  "global_step": 47500,
+  "global_step": 47700,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -7607,6 +7607,38 @@
       "eval_samples_per_second": 24.219,
       "eval_steps_per_second": 3.028,
       "step": 47500
+    },
+    {
+      "epoch": 20.04,
+      "grad_norm": 2.881988525390625,
+      "learning_rate": 1.6729328621908126e-05,
+      "loss": 0.4024,
+      "step": 47600
+    },
+    {
+      "epoch": 20.04,
+      "eval_cer": 0.3465546908607407,
+      "eval_loss": 2.992396831512451,
+      "eval_runtime": 406.9581,
+      "eval_samples_per_second": 23.29,
+      "eval_steps_per_second": 2.912,
+      "step": 47600
+    },
+    {
+      "epoch": 20.08,
+      "grad_norm": 2.220200777053833,
+      "learning_rate": 1.6658657243816255e-05,
+      "loss": 0.4103,
+      "step": 47700
+    },
+    {
+      "epoch": 20.08,
+      "eval_cer": 0.3478818779085683,
+      "eval_loss": 3.0730020999908447,
+      "eval_runtime": 382.3538,
+      "eval_samples_per_second": 24.789,
+      "eval_steps_per_second": 3.099,
+      "step": 47700
     }
   ],
   "logging_steps": 100,
@@ -7614,7 +7646,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 5.20459391384764e+20,
+  "total_flos": 5.227217240325222e+20,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null