Training in progress, step 32300, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46b7ed34acfee810bf1df0de4de59541603b041a38fbb4dbcde73ee390120e45
+oid sha256:02ef20f83611dc5ecda3865d609d1c2529353faeb6e69db3373387d266c57e6d
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:14e0b8af6860fa5a3a1dec8a82763be4461db9bc19598a99d13ba72ca5d0b4cd
+oid sha256:cea2f0b6eea82ec7b672c6f99ffe205fc0b7e54f20c87785b2f34e524aa97736
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb216ea78e406e00f2b6177c3e619ca935a753a4d2c9133ddb3865ce6a36e93d
+oid sha256:b1f8cabf689066796731ca11e18b147c9b88c182baa68362d28e596087a999dd
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:180490a53f200a0ccf80e64da4cf9435033e2460013ac665192a9282d9293db7
+oid sha256:2604f2db63f8d40bcc859d3c5d9db567a5197e74b5fcf8b847396dd21324043f
 size 14567

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d4c398e04ff23b7cf398d4be71ed5c551bcad34152f6745e47db5a460b70aee
+oid sha256:529f0d80ba72a29cd60cd97ed89d7289715ba99737c418335d0e26f49eb2d4a3
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 13.512944643233004,
+  "epoch": 13.597137444748475,
   "eval_steps": 100,
-  "global_step": 32100,
+  "global_step": 32300,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -5143,6 +5143,38 @@
       "eval_samples_per_second": 25.555,
       "eval_steps_per_second": 3.195,
       "step": 32100
+    },
+    {
+      "epoch": 13.56,
+      "grad_norm": 4.829713344573975,
+      "learning_rate": 2.7609187279151943e-05,
+      "loss": 1.0437,
+      "step": 32200
+    },
+    {
+      "epoch": 13.56,
+      "eval_cer": 0.4043276563294357,
+      "eval_loss": 1.8479336500167847,
+      "eval_runtime": 398.7479,
+      "eval_samples_per_second": 23.769,
+      "eval_steps_per_second": 2.972,
+      "step": 32200
+    },
+    {
+      "epoch": 13.6,
+      "grad_norm": 3.0680336952209473,
+      "learning_rate": 2.7538515901060075e-05,
+      "loss": 1.4222,
+      "step": 32300
+    },
+    {
+      "epoch": 13.6,
+      "eval_cer": 0.4040881271753158,
+      "eval_loss": 2.828200101852417,
+      "eval_runtime": 367.3731,
+      "eval_samples_per_second": 25.799,
+      "eval_steps_per_second": 3.226,
+      "step": 32300
     }
   ],
   "logging_steps": 100,
@@ -5150,7 +5182,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 3.5171047954888104e+20,
+  "total_flos": 3.5387141404690835e+20,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null