Training in progress, step 47300, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b23224f934a17dc506ef1427bbf8cfdde7e61c9bdb99bd40ce08a456d490987e
+oid sha256:c0a7eca189b6cba3d0264a3a6b528f4d768503319d4957c82aafb34cecdfdf4a
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7371001d4ba61fec2f6a59fd465a7448ca595cd03c65ce64b593c30a44dfdc70
+oid sha256:d44c9dabcde04ec924b500d0f45e98bbda60772b9108bedac5d65641ce067cb9
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:07b8ed1471e9d069014988f3a9a12d0676eb5b06684acbd3950cb1c7d97542ef
+oid sha256:a5815b1015337a35948babb6d5b6ab9cf7c776143678a541486d413ba284536e
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:78799255d33f45caeb9e5437f76e75e8206e20b85f04c1c95d15dd5e461cdfad
-size 14567
+oid sha256:0d54689fcde880091f1c0ee11daaede986eacb0d5ba40ec6c4cb9bad1bdacaa9
+size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc0e4855190486656b49bc2f9aa7a1bf13ae4f23b65ee19ad5630270c8d3910a
+oid sha256:5d0677dbdd096b9b20e1b9970b686999e123df432ab47b960e13026ac8fbafd2
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 19.827404756893287,
+  "epoch": 19.911597558408754,
   "eval_steps": 100,
-  "global_step": 47100,
+  "global_step": 47300,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -7543,6 +7543,38 @@
       "eval_samples_per_second": 25.595,
       "eval_steps_per_second": 3.2,
       "step": 47100
+    },
+    {
+      "epoch": 19.87,
+      "grad_norm": 1.6992497444152832,
+      "learning_rate": 1.701201413427562e-05,
+      "loss": 0.4712,
+      "step": 47200
+    },
+    {
+      "epoch": 19.87,
+      "eval_cer": 0.34815073716319267,
+      "eval_loss": 2.558990001678467,
+      "eval_runtime": 412.1751,
+      "eval_samples_per_second": 22.995,
+      "eval_steps_per_second": 2.875,
+      "step": 47200
+    },
+    {
+      "epoch": 19.91,
+      "grad_norm": 3.102717399597168,
+      "learning_rate": 1.6941342756183746e-05,
+      "loss": 0.4767,
+      "step": 47300
+    },
+    {
+      "epoch": 19.91,
+      "eval_cer": 0.3449659770834148,
+      "eval_loss": 2.632328748703003,
+      "eval_runtime": 385.8283,
+      "eval_samples_per_second": 24.565,
+      "eval_steps_per_second": 3.071,
+      "step": 47300
     }
   ],
   "logging_steps": 100,
@@ -7550,7 +7582,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 5.161374507685376e+20,
+  "total_flos": 5.183308424712062e+20,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null