Training in progress, step 3600, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a09ae00ebc62ebcd9a090efa8346b0b355da09866b115ffafeb9415b7348a1f
+oid sha256:d91eeb91e22ee51b1c65e0c04b8e6cabb537d7c0caf4d077f5e1e69eb940968b
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72774ec6409b39c81c1aa220704d91224c558c6ea5b86aa374ce4de5fd8e4117
+oid sha256:e3fa62a4ee19ff913d4188ef73821370b4351489d9e353c373367e718c41ac6e
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43d8a703e7b68d5ff0f9ab10e9d171bd7ce6ce70b6e4e532a37f2b2de5240614
+oid sha256:9e6075a74dcc3a31b11a7f90c9467bb390ebde2f5281e9b62844ebc5a11f042c
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d8426d4aae6ad94244099d33cc22d6aea5fa1d82b7f3fc974721970e8c187bc
-size 14503
+oid sha256:902f08a8f6cb2d34977202b642aa8ca1da1a7e05061f8a4675f56789cb56a1ae
+size 14567

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0cdf3746ad5565e79e6e1cb78e78a4ab2fa5d41524e5a44428479a58b87e840e
+oid sha256:0c69799836d793c36bf22d6ba3fabc8c8590dabdbaf72f82cc4a147403fd5ff1
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.4312776257629973,
+  "epoch": 1.5154704272784678,
   "eval_steps": 100,
-  "global_step": 3400,
+  "global_step": 3600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -551,6 +551,38 @@
       "eval_samples_per_second": 27.684,
       "eval_steps_per_second": 3.461,
       "step": 3400
+    },
+    {
+      "epoch": 1.47,
+      "grad_norm": 5.24758768081665,
+      "learning_rate": 4.7884805653710253e-05,
+      "loss": 2.078,
+      "step": 3500
+    },
+    {
+      "epoch": 1.47,
+      "eval_cer": 0.5179402448085723,
+      "eval_loss": 2.244272470474243,
+      "eval_runtime": 354.1685,
+      "eval_samples_per_second": 26.761,
+      "eval_steps_per_second": 3.346,
+      "step": 3500
+    },
+    {
+      "epoch": 1.52,
+      "grad_norm": 6.822329044342041,
+      "learning_rate": 4.7814134275618375e-05,
+      "loss": 2.7694,
+      "step": 3600
+    },
+    {
+      "epoch": 1.52,
+      "eval_cer": 0.5457598451370693,
+      "eval_loss": 2.137202501296997,
+      "eval_runtime": 345.4818,
+      "eval_samples_per_second": 27.434,
+      "eval_steps_per_second": 3.43,
+      "step": 3600
     }
   ],
   "logging_steps": 100,
@@ -558,7 +590,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 3.7374716231040434e+19,
+  "total_flos": 3.957301946059647e+19,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null