Training in progress, step 8300, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:408c6cd9a698b16001a43197f1c14eb97815dc79cf0faf065cdd9fae5f5d7a0c
+oid sha256:7cb9185b5a4178ca9b95ea9a03e81f42aab94937d5536d0aee20a7d50113c74e
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:29518292804cc1bbadfb0c2d47c708a9ad2a4899919ddbb39ca62659b229c095
+oid sha256:2f20f2e893a5805f94e67a072ca607e87d6bd1f6bf961c5d10cf2c83fc0eca10
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c599e77c37f648f3f925b89128d4d5cf7e01fb20ae88a5649c4f9e9edbed6487
+oid sha256:483b010e40619bd56631da53658bb649fe7d4dd6c1a8c3d654abffab621a3b4b
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2427345fe81496661e617176cf30f03a179e764f54042a1de82a0b0e5e040e18
+oid sha256:cdb949cb9ef5d042fa95175eb1cd636c4986ae56e852d369f16efd31f056bea0
 size 14567

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4541330612b9d0a7a65c65620d7604d28710aaed0289ff9c20765e43c3bdf6a7
+oid sha256:8f59710310815d68188af9ff723493a6950c9e2340e3b280d58445c624870566
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 3.4098084613765525,
+  "epoch": 3.4940012628920227,
   "eval_steps": 100,
-  "global_step": 8100,
+  "global_step": 8300,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1303,6 +1303,38 @@
       "eval_samples_per_second": 26.451,
       "eval_steps_per_second": 3.307,
       "step": 8100
+    },
+    {
+      "epoch": 3.45,
+      "grad_norm": 3.6079511642456055,
+      "learning_rate": 4.456466431095407e-05,
+      "loss": 1.7713,
+      "step": 8200
+    },
+    {
+      "epoch": 3.45,
+      "eval_cer": 0.495703140276094,
+      "eval_loss": 2.7158584594726562,
+      "eval_runtime": 373.6599,
+      "eval_samples_per_second": 25.365,
+      "eval_steps_per_second": 3.171,
+      "step": 8200
+    },
+    {
+      "epoch": 3.49,
+      "grad_norm": 3.969160318374634,
+      "learning_rate": 4.4493992932862195e-05,
+      "loss": 3.3072,
+      "step": 8300
+    },
+    {
+      "epoch": 3.49,
+      "eval_cer": 0.49535606742012434,
+      "eval_loss": 1.9461767673492432,
+      "eval_runtime": 357.0354,
+      "eval_samples_per_second": 26.546,
+      "eval_steps_per_second": 3.319,
+      "step": 8300
     }
   ],
   "logging_steps": 100,
@@ -1310,7 +1342,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 8.881279509355615e+19,
+  "total_flos": 9.10041827788282e+19,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null