Training in progress, step 4800, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a389c3f77e972b9ad2c3598a897a595d740c11eef3134fc3913b671d5c4aa98
+oid sha256:055979e5e4bab7fa9c297e62d4dd024246a4b92488281ca6ea9d09b258b2dbed
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4cf523156e6cfba18fe652208aa23b347ae9fa03eb5a27cf6ee2de9b87e0b018
+oid sha256:d5fd6e75335a40460c09860fda74c9a6c5d024c71c570c9f8edaef3d82e2c4b6
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:972ad41e162646ea15a0a97c616a6a668482e5a2db3e8f5673ee3c315481e243
+oid sha256:debc4e9a9196125845f12a1727f21f7a7bafd177d8aed8ac1735fdd1c7612955
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0965352267660a565504fd8fd4be8deea39448c1829b29947da55924c359a90b
+oid sha256:74ca4a69432f7601c2ee6fa63216c3206d700ac81d698c937691e7b4a79a3cac
 size 14567

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dd64d58f0ca1f8e908f6d74c38fec76a5c8bd2eba7e4b0c0c52260244cc0f23b
+oid sha256:1f3ec477801d437578c540c89110c8a9e9fd36ab687066f3be220e65fc1f6809
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.9364344348558198,
+  "epoch": 2.0206272363712903,
   "eval_steps": 100,
-  "global_step": 4600,
+  "global_step": 4800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -743,6 +743,38 @@
       "eval_samples_per_second": 27.885,
       "eval_steps_per_second": 3.486,
       "step": 4600
+    },
+    {
+      "epoch": 1.98,
+      "grad_norm": 3.5580544471740723,
+      "learning_rate": 4.703745583038869e-05,
+      "loss": 3.577,
+      "step": 4700
+    },
+    {
+      "epoch": 1.98,
+      "eval_cer": 0.5378284971256502,
+      "eval_loss": 2.777487277984619,
+      "eval_runtime": 356.1415,
+      "eval_samples_per_second": 26.613,
+      "eval_steps_per_second": 3.327,
+      "step": 4700
+    },
+    {
+      "epoch": 2.02,
+      "grad_norm": 2.3930351734161377,
+      "learning_rate": 4.6966784452296826e-05,
+      "loss": 2.733,
+      "step": 4800
+    },
+    {
+      "epoch": 2.02,
+      "eval_cer": 0.5305424113253294,
+      "eval_loss": 3.2367630004882812,
+      "eval_runtime": 346.0446,
+      "eval_samples_per_second": 27.39,
+      "eval_steps_per_second": 3.424,
+      "step": 4800
     }
   ],
   "logging_steps": 100,
@@ -750,7 +782,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 5.048556716553413e+19,
+  "total_flos": 5.262746619312e+19,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null