Training in progress, step 5000, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:055979e5e4bab7fa9c297e62d4dd024246a4b92488281ca6ea9d09b258b2dbed
+oid sha256:41875e86984f9c499bbd46447c4b07ffb7cbdf07789f652a89a6868d23bab35f
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d5fd6e75335a40460c09860fda74c9a6c5d024c71c570c9f8edaef3d82e2c4b6
+oid sha256:cf6fc30af65fb1bb2b342a3d768a007f7604ee05fb1696eb8530da85555ef0b5
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:debc4e9a9196125845f12a1727f21f7a7bafd177d8aed8ac1735fdd1c7612955
+oid sha256:dc85d1a0b008548cc1a644ec52e7a922d0f2f1c680c67a89f68ab5e2f58767a5
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:74ca4a69432f7601c2ee6fa63216c3206d700ac81d698c937691e7b4a79a3cac
+oid sha256:6a56c4b251eaaa521dd5897d38bb3df55dc9d33c44687cea24d832bf76a4766d
 size 14567

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f3ec477801d437578c540c89110c8a9e9fd36ab687066f3be220e65fc1f6809
+oid sha256:57ebf369faef4240020a647139b481dc6228228676411a7d695726a9d3bf18a5
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.0206272363712903,
+  "epoch": 2.1048200378867605,
   "eval_steps": 100,
-  "global_step": 4800,
+  "global_step": 5000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -775,6 +775,38 @@
       "eval_samples_per_second": 27.39,
       "eval_steps_per_second": 3.424,
       "step": 4800
+    },
+    {
+      "epoch": 2.06,
+      "grad_norm": 4.198298931121826,
+      "learning_rate": 4.6896113074204954e-05,
+      "loss": 1.616,
+      "step": 4900
+    },
+    {
+      "epoch": 2.06,
+      "eval_cer": 0.523026573071057,
+      "eval_loss": 2.150926351547241,
+      "eval_runtime": 371.9418,
+      "eval_samples_per_second": 25.482,
+      "eval_steps_per_second": 3.186,
+      "step": 4900
+    },
+    {
+      "epoch": 2.1,
+      "grad_norm": 3.6696269512176514,
+      "learning_rate": 4.6825441696113075e-05,
+      "loss": 1.8252,
+      "step": 5000
+    },
+    {
+      "epoch": 2.1,
+      "eval_cer": 0.5257933792186461,
+      "eval_loss": 3.1695752143859863,
+      "eval_runtime": 351.2533,
+      "eval_samples_per_second": 26.983,
+      "eval_steps_per_second": 3.374,
+      "step": 5000
     }
   ],
   "logging_steps": 100,
@@ -782,7 +814,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 5.262746619312e+19,
+  "total_flos": 5.4841600382755045e+19,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null