Training in progress, step 51100, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b8c55cd18309bf4d096f4b3253c534937b641ff135e763ecb864e9f8ebd8618a
+oid sha256:6bc94c256078d60ae60c29652217c2629d9b9f6461e83c504a29f2ff2d758717
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ec6752b7c42decf02f2e39800b6145d2ffde5bb2151b7574bdd01ba232e6372
+oid sha256:f82a0535ceb94588d81de04a572d016f4ae08f4ed23493fe6e58cef9b9b99eef
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:095dcbda7d00d483e2fa14803e5220f34c3024566d3114fc9f91b65d66ab3534
+oid sha256:b5931c1deaa9accec9ce16ef413a75648d348abcbfbaeca5ad9ddeaba52d1ff7
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:12f7743be5328471b18c330b88db7a79949aef581fc0209654a98b74372391d2
+oid sha256:cafedcdde0154a6bd325b96ceffadec13f91f8224b1692d8e35fbd99757a6c2c
 size 14567

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:760aea3902ababea5df05720420d447d30d1561a0385a51f231f0d512c4123e3
+oid sha256:6c69be6938fe5dd8ba71aa4b3717263a23a1baa9c26c2e9c021d17a37e3a94bd
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 21.427067985687223,
+  "epoch": 21.511260787202694,
   "eval_steps": 100,
-  "global_step": 50900,
+  "global_step": 51100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -8151,6 +8151,38 @@
       "eval_samples_per_second": 24.271,
       "eval_steps_per_second": 3.035,
       "step": 50900
+    },
+    {
+      "epoch": 21.47,
+      "grad_norm": 3.5707991123199463,
+      "learning_rate": 1.4327208480565372e-05,
+      "loss": 0.349,
+      "step": 51000
+    },
+    {
+      "epoch": 21.47,
+      "eval_cer": 0.338039185014274,
+      "eval_loss": 2.3195223808288574,
+      "eval_runtime": 421.6099,
+      "eval_samples_per_second": 22.48,
+      "eval_steps_per_second": 2.811,
+      "step": 51000
+    },
+    {
+      "epoch": 21.51,
+      "grad_norm": 1.6567233800888062,
+      "learning_rate": 1.42565371024735e-05,
+      "loss": 0.3534,
+      "step": 51100
+    },
+    {
+      "epoch": 21.51,
+      "eval_cer": 0.33963767549176804,
+      "eval_loss": 2.4492955207824707,
+      "eval_runtime": 387.5977,
+      "eval_samples_per_second": 24.453,
+      "eval_steps_per_second": 3.057,
+      "step": 51100
     }
   ],
   "logging_steps": 100,
@@ -8158,7 +8190,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 5.578208763591309e+20,
+  "total_flos": 5.6001325221620836e+20,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null