Training in progress, step 35500, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c5e27caae33c684f3640dae183538f233c632e6b6dd013d1391ffa6812ef5b0f
+oid sha256:56ff4705ab488bb59741b0e5c71e9ac05b7326124a2bfb5d7f395e778b9050e3
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37818e67057bc9ab28e81eaabfd7516fb101e3ee984df530db2cd877e1ad02b7
+oid sha256:7bebf964f27f1886af6b09595cbe151e56d1dfb73585f5c75ef9fe367ce5cb5c
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:11dce48e3fc1d772256c604b93835d59113a4d934c93e60ceefb0e7a3d7b4c83
+oid sha256:43d29c51ee6b98cdc02945191da5c1b40cb5666775063ea99d3215e1a3f3026d
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dcb03d30f7f2fad34efa71219b03cd9586a94705f7898bc5dca76c5295036d2c
-size 14567
+oid sha256:e7d96028437c689f30c391fd7b819c0717a3f42c10fd6e760f3a8d7f10e65590
+size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:44ced050c05b9918ceaed2d8641bd55ffcbf9685f204bd1a0efee676b85d41a8
+oid sha256:a2a895192cf0f0de5099223427191af438af44d9d236e07991f988cd0f9fc2af
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 14.86002946748053,
+  "epoch": 14.944222268996,
   "eval_steps": 100,
-  "global_step": 35300,
+  "global_step": 35500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -5655,6 +5655,38 @@
       "eval_samples_per_second": 25.677,
       "eval_steps_per_second": 3.21,
       "step": 35300
+    },
+    {
+      "epoch": 14.9,
+      "grad_norm": 2.0357742309570312,
+      "learning_rate": 2.5348409893992936e-05,
+      "loss": 0.9183,
+      "step": 35400
+    },
+    {
+      "epoch": 14.9,
+      "eval_cer": 0.38374036995033434,
+      "eval_loss": 1.656967043876648,
+      "eval_runtime": 397.837,
+      "eval_samples_per_second": 23.824,
+      "eval_steps_per_second": 2.979,
+      "step": 35400
+    },
+    {
+      "epoch": 14.94,
+      "grad_norm": 2.4356577396392822,
+      "learning_rate": 2.527773851590106e-05,
+      "loss": 0.9208,
+      "step": 35500
+    },
+    {
+      "epoch": 14.94,
+      "eval_cer": 0.3846764889914356,
+      "eval_loss": 1.6596330404281616,
+      "eval_runtime": 368.5045,
+      "eval_samples_per_second": 25.72,
+      "eval_steps_per_second": 3.216,
+      "step": 35500
     }
   ],
   "logging_steps": 100,
@@ -5662,7 +5694,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 3.8682651120044894e+20,
+  "total_flos": 3.89001558499963e+20,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null