Training in progress, step 13700, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:31b62a1eed64814fb09932d72e4b158e825506d75ad15f298d9e787f0552502f
+oid sha256:30d085aaa0f82d54e68daaff76a5edf1a83caa6fc552bc63e28873040f03bf9a
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a47b4b5e03532ead7e8fc7c3e923c4911144dbd2504a20958ebe8635de704ed1
+oid sha256:6b3208fa1d71ea807e3133c94abe026dccee956ff323c98dc52647f372ccad32
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:78a5cb22af6a2e357b345873f02b48b612899f785e45880c5d3859603cec97ca
+oid sha256:1e9806b2d6e21ab5a74e92bf2a1176e3dc60de6b2f8bacd510d899a41faeac49
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e72175515cc54637e49cc1705761942275c0209bb6b05ae32b0a8db952e415f
-size 14503
+oid sha256:2ce0016f9e7b603d570201d200237a8a9050741d2a9b12cc7d3687acfd6a9d1c
+size 14567

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a4b19e6e6a244eb7dd17c9a36301bdbe54a114d743b96df3cd2e7dd5ae72aa2
+oid sha256:1a88883a6f3ed79ad9be6875b04b7df75d671a094bc1c6e0ebf303bf9ba54f1d
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 5.683014102294254,
+  "epoch": 5.767206903809724,
   "eval_steps": 100,
-  "global_step": 13500,
+  "global_step": 13700,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2167,6 +2167,38 @@
       "eval_samples_per_second": 26.025,
       "eval_steps_per_second": 3.254,
       "step": 13500
+    },
+    {
+      "epoch": 5.73,
+      "grad_norm": 4.778401851654053,
+      "learning_rate": 4.074911660777385e-05,
+      "loss": 1.9508,
+      "step": 13600
+    },
+    {
+      "epoch": 5.73,
+      "eval_cer": 0.4695724649016464,
+      "eval_loss": 1.914655327796936,
+      "eval_runtime": 378.9026,
+      "eval_samples_per_second": 25.014,
+      "eval_steps_per_second": 3.127,
+      "step": 13600
+    },
+    {
+      "epoch": 5.77,
+      "grad_norm": 4.1898345947265625,
+      "learning_rate": 4.0678445229681986e-05,
+      "loss": 2.1823,
+      "step": 13700
+    },
+    {
+      "epoch": 5.77,
+      "eval_cer": 0.47729850220953424,
+      "eval_loss": 1.71451997756958,
+      "eval_runtime": 365.8718,
+      "eval_samples_per_second": 25.905,
+      "eval_steps_per_second": 3.239,
+      "step": 13700
     }
   ],
   "logging_steps": 100,
@@ -2174,7 +2206,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 1.4794168929030072e+20,
+  "total_flos": 1.5014329647964724e+20,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null