Training in progress, step 36100, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b35f734ee856f18dc12768c16472dc4fa4a48e29bb5476207b1dd1732446ff9
+oid sha256:f7d3f4d3140e24d9a2d9d515b8e731fb422050a6d4777c3f3f41351c89e5a125
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cfa23d05a63ef98a7a08510cfe63830d8c0bfde6e697c271a310ceb8b3f71341
+oid sha256:0c34024a06fc4af618b6f6751f21e3b53d49f48981ef0d0d79f68ee6eff6a9b5
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a5a4e470770ebadc4146150e5c1b050c970bb70871bdd3d49120d1a71cafdf88
+oid sha256:2c97f92419b82a234f5ed95c05e5eeea91614d5e9d89d45875d7e2fcc4d2634c
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa8c3ee406720d81ffabaf84f9e91e08e6b6eb075e6cb1267455d95c6a23d91a
+oid sha256:fcd61ea82574fa5aa908afe65ac4133feb6f83558ee3a2931d9b8b5b34f0e3f4
 size 14567

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:89c666c1e074cfdb22c4aa9905324d78e551418b1a46be058b6dc5f2e31bf25c
+oid sha256:8b4e7346e819a03a37a4b1eb1e2725223d670f029e6e9ea037250603b481398f
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 15.112607872026942,
+  "epoch": 15.196800673542413,
   "eval_steps": 100,
-  "global_step": 35900,
+  "global_step": 36100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -5751,6 +5751,38 @@
       "eval_samples_per_second": 24.943,
       "eval_steps_per_second": 3.118,
       "step": 35900
+    },
+    {
+      "epoch": 15.15,
+      "grad_norm": 8.684925079345703,
+      "learning_rate": 2.4924381625441698e-05,
+      "loss": 0.8427,
+      "step": 36000
+    },
+    {
+      "epoch": 15.15,
+      "eval_cer": 0.3852386492511048,
+      "eval_loss": 2.0919713973999023,
+      "eval_runtime": 387.8899,
+      "eval_samples_per_second": 24.435,
+      "eval_steps_per_second": 3.055,
+      "step": 36000
+    },
+    {
+      "epoch": 15.2,
+      "grad_norm": 2.094461441040039,
+      "learning_rate": 2.4853710247349822e-05,
+      "loss": 0.8353,
+      "step": 36100
+    },
+    {
+      "epoch": 15.2,
+      "eval_cer": 0.38358149857260176,
+      "eval_loss": 1.544800043106079,
+      "eval_runtime": 374.0519,
+      "eval_samples_per_second": 25.339,
+      "eval_steps_per_second": 3.168,
+      "step": 36100
     }
   ],
   "logging_steps": 100,
@@ -5758,7 +5790,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 3.934653943012538e+20,
+  "total_flos": 3.956666718927042e+20,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null