Training in progress, step 47500, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c0a7eca189b6cba3d0264a3a6b528f4d768503319d4957c82aafb34cecdfdf4a
+oid sha256:67401216b3029d2622e7e7add3d17e2a39d754ad2562031455d96e2f627ae67b
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d44c9dabcde04ec924b500d0f45e98bbda60772b9108bedac5d65641ce067cb9
+oid sha256:6921906aba6ad6cda84ac2dad9392fde118c107f9c07cce5a4b585abe35d446d
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a5815b1015337a35948babb6d5b6ab9cf7c776143678a541486d413ba284536e
+oid sha256:eb52b0ddcb7b49c326f60274849ef6aa3c79a378160d3f09440dbe910b761c44
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d54689fcde880091f1c0ee11daaede986eacb0d5ba40ec6c4cb9bad1bdacaa9
-size 14503
+oid sha256:1c20e682f3fe40fa57d88e22486ddd5912b58563883c794fa3b1d8da05268377
+size 14567

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d0677dbdd096b9b20e1b9970b686999e123df432ab47b960e13026ac8fbafd2
+oid sha256:372a4198b83fdb5e8fb2ecd27baf4c7bfc16f7ae1e02bdddaa16958cd86125f9
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 19.911597558408754,
+  "epoch": 19.995790359924225,
   "eval_steps": 100,
-  "global_step": 47300,
+  "global_step": 47500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -7575,6 +7575,38 @@
       "eval_samples_per_second": 24.565,
       "eval_steps_per_second": 3.071,
       "step": 47300
+    },
+    {
+      "epoch": 19.95,
+      "grad_norm": 3.6561086177825928,
+      "learning_rate": 1.6870671378091874e-05,
+      "loss": 0.4914,
+      "step": 47400
+    },
+    {
+      "epoch": 19.95,
+      "eval_cer": 0.3475079191271362,
+      "eval_loss": 2.747345447540283,
+      "eval_runtime": 406.0174,
+      "eval_samples_per_second": 23.344,
+      "eval_steps_per_second": 2.919,
+      "step": 47400
+    },
+    {
+      "epoch": 20.0,
+      "grad_norm": 2.65822696685791,
+      "learning_rate": 1.6800000000000002e-05,
+      "loss": 0.4636,
+      "step": 47500
+    },
+    {
+      "epoch": 20.0,
+      "eval_cer": 0.34717795549646085,
+      "eval_loss": 3.2108983993530273,
+      "eval_runtime": 391.3482,
+      "eval_samples_per_second": 24.219,
+      "eval_steps_per_second": 3.028,
+      "step": 47500
     }
   ],
   "logging_steps": 100,
@@ -7582,7 +7614,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 5.183308424712062e+20,
+  "total_flos": 5.20459391384764e+20,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null