Training in progress, step 4000, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cda231612e7da9ba6fe5b73580b35ba57a5509163e110e5e0eba0e5b73599828
+oid sha256:f6eab5677f46f55cd5bdf940b57732922d460c486b51deec090c4defd40f1c8c
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b7bf19e287139c8acae351b1673a21b2058f7cec0fcff727e026d3c46270716
+oid sha256:5b8c2159ac9a55adb8b2efbc9dc72bd1d7b6bb28185d5fa12310c92401b0223a
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a5f5a1c77820b7bbc317c1aff8a45aed6a8560151a804ae0da402a849cde98b3
+oid sha256:765a34232b9fc6ca107a22d9bbab31ff13323544b7064a9c0f78ca6902d25e92
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ba629318d7b57f286219027aeead93614853054919718b951849895b202cb795
+oid sha256:a32065c1b18af280e4ddb270084d4ac6e2b0c6e9dff4248b8a94a19b71f33829
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9fd2fb3de96e6243302ce77c9c01fd7c31f2ad88c6a97730bbe44948db0ff021
+oid sha256:ab0eb803166017b70d1ead17be9d54077f2b2855eb034642119a0cce3bca01ec
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.599663228793938,
+  "epoch": 1.6838560303094086,
   "eval_steps": 100,
-  "global_step": 3800,
+  "global_step": 4000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -615,6 +615,38 @@
       "eval_samples_per_second": 27.449,
       "eval_steps_per_second": 3.432,
       "step": 3800
+    },
+    {
+      "epoch": 1.64,
+      "grad_norm": 7.307125568389893,
+      "learning_rate": 4.760212014134276e-05,
+      "loss": 1.6227,
+      "step": 3900
+    },
+    {
+      "epoch": 1.64,
+      "eval_cer": 0.551083258378632,
+      "eval_loss": 1.9913257360458374,
+      "eval_runtime": 354.7374,
+      "eval_samples_per_second": 26.718,
+      "eval_steps_per_second": 3.34,
+      "step": 3900
+    },
+    {
+      "epoch": 1.68,
+      "grad_norm": 4.344304084777832,
+      "learning_rate": 4.753144876325089e-05,
+      "loss": 3.1757,
+      "step": 4000
+    },
+    {
+      "epoch": 1.68,
+      "eval_cer": 0.5003299636306754,
+      "eval_loss": 1.8998807668685913,
+      "eval_runtime": 348.4123,
+      "eval_samples_per_second": 27.203,
+      "eval_steps_per_second": 3.401,
+      "step": 4000
     }
   ],
   "logging_steps": 100,
@@ -622,7 +654,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 4.173960303853909e+19,
+  "total_flos": 4.390201253897497e+19,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null