Training in progress, step 1200, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:87323aa246e5525c967b36e0a7119ff06b3213e7668c1f5846d8420c500de1a2
+oid sha256:61b8021f9700ff5c5a17072304ab83458e600fd5cf520c83a2df81d3e12713b5
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d68b084be2ded48e2587a63e4b50b52268b9c95e406eb01dbcf32f79501fadf3
+oid sha256:05a3cfa7b8112c854ad186de5515ccb58d7210b5499e8ba4ca4e74fe50b0c81e
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2eebd57b0d4504fb08b3859d2e5922af006f7b80e276d54f3a75630a03f57cc0
+oid sha256:0805474fc2a510c29c9124dcbdf181d2a422e2a187e2857f77d0cb12089454cf
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:573e592efc8bd12844dd0aa8efeae01c2194994d68d8419691db30231224e469
-size 14503
+oid sha256:a33c7c0713cd434979900bbb76c769cb47e1c794cc69ae0ade79202acbe1ca24
+size 14567

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8cf4161a8d89b4d12d1aa80ad587062e7bdf9b94508fc5ae11c0dc8e85a1cabf
+oid sha256:53d39c2fe1b10580ca81da249157bc3c1421f568f4e7be1b465cf7546d04dffd
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.3367712060618817,
+  "epoch": 0.5051568090928226,
   "eval_steps": 100,
-  "global_step": 800,
+  "global_step": 1200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -135,6 +135,70 @@
       "eval_samples_per_second": 27.593,
       "eval_steps_per_second": 3.45,
       "step": 800
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 3.173403263092041,
+      "learning_rate": 4.972155477031802e-05,
+      "loss": 4.2294,
+      "step": 900
+    },
+    {
+      "epoch": 0.38,
+      "eval_cer": 0.5840918423213797,
+      "eval_loss": 2.6817102432250977,
+      "eval_runtime": 354.5341,
+      "eval_samples_per_second": 26.734,
+      "eval_steps_per_second": 3.342,
+      "step": 900
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 4.8158440589904785,
+      "learning_rate": 4.965088339222615e-05,
+      "loss": 2.2949,
+      "step": 1000
+    },
+    {
+      "epoch": 0.42,
+      "eval_cer": 0.5736649915920379,
+      "eval_loss": 1.9513429403305054,
+      "eval_runtime": 345.1224,
+      "eval_samples_per_second": 27.463,
+      "eval_steps_per_second": 3.434,
+      "step": 1000
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 3.0650887489318848,
+      "learning_rate": 4.958021201413428e-05,
+      "loss": 2.6115,
+      "step": 1100
+    },
+    {
+      "epoch": 0.46,
+      "eval_cer": 0.5645799929607759,
+      "eval_loss": 2.8409903049468994,
+      "eval_runtime": 352.0824,
+      "eval_samples_per_second": 26.92,
+      "eval_steps_per_second": 3.366,
+      "step": 1100
+    },
+    {
+      "epoch": 0.51,
+      "grad_norm": 3.0540664196014404,
+      "learning_rate": 4.950954063604241e-05,
+      "loss": 2.3453,
+      "step": 1200
+    },
+    {
+      "epoch": 0.51,
+      "eval_cer": 0.598292499315631,
+      "eval_loss": 1.8713030815124512,
+      "eval_runtime": 344.1368,
+      "eval_samples_per_second": 27.541,
+      "eval_steps_per_second": 3.443,
+      "step": 1200
     }
   ],
   "logging_steps": 100,
@@ -142,7 +206,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 8.803126663244048e+18,
+  "total_flos": 1.3170915279641096e+19,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null