Training in progress, step 37300, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:381f57f24d93696513b5b64ff4e2b26e4aa55b4c5527b3fea9b18b1fc4cf72bc
+oid sha256:e144bce46edf775616a4443f82caf425c0686653b94ab2fb483c2313495144e3
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb33ab1b771a570de1383d0627b9c859532e9fc93dbf7d6c5f3ea94a017d8931
+oid sha256:eddb4901907ffccd8be8dddebdf534eb37f79032b8b4e81df81b79532d08d4d1
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dede614aaa93a8236b1aaee0b270dbb1e0e0ee731df570c565b17414017d0f04
+oid sha256:75ad29ad88eda9c787c71227c136deda6d40511f9d451c48bfb06d56d2adb55d
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:953d28bb26d9f06c74ed4ce0f50682b88b7c1a740875d4c88a1a0b092ef89394
+oid sha256:16adb65f6f3f6217c263cb3f3368dbfde118f82cd4ff73c393b45170a494b241
 size 14567

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5bbb7a0763de581151b4ca9c96854f5bc48332bf11f33793e4cc2d52e736e678
+oid sha256:aad7c4d73dc18622cfa786ae77c4f4bb6ce05f62b97dafb8f0c14d806f84f5f0
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 15.617764681119764,
+  "epoch": 15.701957482635235,
   "eval_steps": 100,
-  "global_step": 37100,
+  "global_step": 37300,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -5943,6 +5943,38 @@
       "eval_samples_per_second": 25.027,
       "eval_steps_per_second": 3.129,
       "step": 37100
+    },
+    {
+      "epoch": 15.66,
+      "grad_norm": 51.162017822265625,
+      "learning_rate": 2.4076325088339225e-05,
+      "loss": 0.8849,
+      "step": 37200
+    },
+    {
+      "epoch": 15.66,
+      "eval_cer": 0.38121553713190726,
+      "eval_loss": 1.649156928062439,
+      "eval_runtime": 393.043,
+      "eval_samples_per_second": 24.114,
+      "eval_steps_per_second": 3.015,
+      "step": 37200
+    },
+    {
+      "epoch": 15.7,
+      "grad_norm": 1.459133505821228,
+      "learning_rate": 2.400565371024735e-05,
+      "loss": 0.8247,
+      "step": 37300
+    },
+    {
+      "epoch": 15.7,
+      "eval_cer": 0.37826297368112316,
+      "eval_loss": 1.726231575012207,
+      "eval_runtime": 372.5489,
+      "eval_samples_per_second": 25.441,
+      "eval_steps_per_second": 3.181,
+      "step": 37300
     }
   ],
   "logging_steps": 100,
@@ -5950,7 +5982,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 4.066405780809435e+20,
+  "total_flos": 4.087953409101901e+20,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null