Training in progress, step 34700, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7dde78f2f1969345a22710b02dad86de0a28263f667c5019c90aec37011dc2df
+oid sha256:9867f224290cad13cee2149e3f5b88b51d71f4cd5c80186c5e74ad5b9c9aa605
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d673a19cfec5851d535cbb42cc99c5bcfb76dcfc5db1ed80e4b0e8136200acc
+oid sha256:353be69f812937f23a9ca7a7a09cb32160785e43f6ae776dd247459ea7615c12
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c6998c3f78f855591ccca0963694f8694ed36fb2614f0be8e0a562e441198dd5
+oid sha256:82dcac1bc761474f881c627c4621b78ab1a57da749763717e9a164523afda69f
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ada95d205b5a39eda24ebdce0e8a5ed373f9e446a705032948e14e07c6062dd5
+oid sha256:33684118cae1307b6ed1a910d74ee2b4d35f0d7a91b6c16c2caf9ca77105918c
 size 14567

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:64f9e3827b8202a59f622a236dc60a703867ee0b6877abae1ad4c8c5512a0181
+oid sha256:ce84586ac34d9d46ffac97deffc1538ae04a68c67811b91ea3d3bec0fe9c9a7a
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 14.523258261418649,
+  "epoch": 14.60745106293412,
   "eval_steps": 100,
-  "global_step": 34500,
+  "global_step": 34700,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -5527,6 +5527,38 @@
       "eval_samples_per_second": 25.184,
       "eval_steps_per_second": 3.149,
       "step": 34500
+    },
+    {
+      "epoch": 14.57,
+      "grad_norm": 2.1704392433166504,
+      "learning_rate": 2.5913074204946997e-05,
+      "loss": 0.9261,
+      "step": 34600
+    },
+    {
+      "epoch": 14.57,
+      "eval_cer": 0.38692268585507017,
+      "eval_loss": 1.6806480884552002,
+      "eval_runtime": 393.3479,
+      "eval_samples_per_second": 24.096,
+      "eval_steps_per_second": 3.013,
+      "step": 34600
+    },
+    {
+      "epoch": 14.61,
+      "grad_norm": 4.049818515777588,
+      "learning_rate": 2.5842402826855122e-05,
+      "loss": 0.9017,
+      "step": 34700
+    },
+    {
+      "epoch": 14.61,
+      "eval_cer": 0.3871744358844003,
+      "eval_loss": 1.6744087934494019,
+      "eval_runtime": 365.5955,
+      "eval_samples_per_second": 25.925,
+      "eval_steps_per_second": 3.241,
+      "step": 34700
     }
   ],
   "logging_steps": 100,
@@ -5534,7 +5566,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 3.78048558664814e+20,
+  "total_flos": 3.8025780817217e+20,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null