Training in progress, step 7300, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ffe4a4c3e4e20b6f8d7533a207499d54e18533a2ff9988b5cf140b2c17082c0
+oid sha256:930ff99206b4cefd343133517df19a99faeea6029d6177481ccaec88e3dce2a1
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:50723aacfe1d09285d3d20c78e7a1e48064440bdd2388888b659a4f9def33f3c
+oid sha256:d6c24714dc5073398cfebd333596cf1b0bae2a24c794815e98acfcf729f25e62
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c0b9c0f6c20269a5797deab52d27abffe73bdbbaf470e35e43b903f7ebcadebf
+oid sha256:a5ace4eb638ee35078677814378e460122eee04667323d7ec66aafc41a0bcf3d
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c8a74dd20115cf8c84a288f3d48680cab469a7e69dc1d1632fbee207bbb0aa74
+oid sha256:abe36de378b59c2f69bfa0fcce3a08cc6146802a272942efe4095319e84db456
 size 14567

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:233cc1a95fc61bdbfaf2f246e87bbffc2fb4b93155b895b23bcd4b806754f9d4
+oid sha256:dd87e1ec2272e10b79236e6de3ce1bcd6d1b8483ab6bbbf6487a56197cdb7bd1
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.9888444537992003,
+  "epoch": 3.0730372553146705,
   "eval_steps": 100,
-  "global_step": 7100,
+  "global_step": 7300,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1143,6 +1143,38 @@
       "eval_samples_per_second": 25.848,
       "eval_steps_per_second": 3.232,
       "step": 7100
+    },
+    {
+      "epoch": 3.03,
+      "grad_norm": 237.01815795898438,
+      "learning_rate": 4.527137809187279e-05,
+      "loss": 3.0545,
+      "step": 7200
+    },
+    {
+      "epoch": 3.03,
+      "eval_cer": 0.5361493488717688,
+      "eval_loss": 2.276334524154663,
+      "eval_runtime": 373.4974,
+      "eval_samples_per_second": 25.376,
+      "eval_steps_per_second": 3.173,
+      "step": 7200
+    },
+    {
+      "epoch": 3.07,
+      "grad_norm": 2.9628891944885254,
+      "learning_rate": 4.520070671378092e-05,
+      "loss": 1.9898,
+      "step": 7300
+    },
+    {
+      "epoch": 3.07,
+      "eval_cer": 0.5218631457510461,
+      "eval_loss": 1.94766104221344,
+      "eval_runtime": 364.5953,
+      "eval_samples_per_second": 25.996,
+      "eval_steps_per_second": 3.25,
+      "step": 7300
     }
   ],
   "logging_steps": 100,
@@ -1150,7 +1182,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 7.774285790233235e+19,
+  "total_flos": 8.009534999457974e+19,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null