Training in progress, step 9500, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e53d952088e21ee7c18f6fee4b8d7769b753af22ca10b63a69e3f8de2b65b0be
+oid sha256:a32dc99462660290df84c8528dc9eb39190be3d3c57683e7877e90642c878438
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:76dd5b4a8826aefc4d28f9aba3108c5d9d8a9bb5ddbd6054bc88418f54521ed3
+oid sha256:49f127aa66da05aa9808cb65c326d54eb1f62011422d2b38dbc32ab973d98742
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5bb833d4bc9327bd0e01ea33487a3bf19e25b2de7bacf92eb09217f6b4297dc2
+oid sha256:0521f879a75eea1399e7ebb7725746dc98364d1c9d3582f6a0a4284d965d9d7c
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f7b3c74ecbda77c6abb056be85c9b612f31948352a984f5f4ba2d90f864dc773
+oid sha256:bf6988d2899e29ce3c7ea0ad046e917da0407c7d088f3a2102b64354f3b328c9
 size 14567

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:336d1b7b025618b96c60c17b8c9303a9e5e4f82eb8a6c5c17e6b7e590bbf1488
+oid sha256:9e0200d46d39b183c05be433e7301e4dbe08836ad4684cdecd5d09269aef39dd
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 3.914965270469375,
+  "epoch": 3.999158071984845,
   "eval_steps": 100,
-  "global_step": 9300,
+  "global_step": 9500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1495,6 +1495,38 @@
       "eval_samples_per_second": 26.275,
       "eval_steps_per_second": 3.285,
       "step": 9300
+    },
+    {
+      "epoch": 3.96,
+      "grad_norm": 2.788163661956787,
+      "learning_rate": 4.371731448763251e-05,
+      "loss": 2.4278,
+      "step": 9400
+    },
+    {
+      "epoch": 3.96,
+      "eval_cer": 0.5205579562785968,
+      "eval_loss": 2.4102938175201416,
+      "eval_runtime": 376.1786,
+      "eval_samples_per_second": 25.195,
+      "eval_steps_per_second": 3.15,
+      "step": 9400
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 2.6063647270202637,
+      "learning_rate": 4.364664310954063e-05,
+      "loss": 1.5116,
+      "step": 9500
+    },
+    {
+      "epoch": 4.0,
+      "eval_cer": 0.4881310859958547,
+      "eval_loss": 1.728480339050293,
+      "eval_runtime": 352.8942,
+      "eval_samples_per_second": 26.858,
+      "eval_steps_per_second": 3.358,
+      "step": 9500
     }
   ],
   "logging_steps": 100,
@@ -1502,7 +1534,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 1.0193037614760552e+20,
+  "total_flos": 1.0405499901125573e+20,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null