End of training

README.md

@@ -13,12 +13,12 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model was trained from scratch on an unknown dataset.
 It achieves the following results on the evaluation set:
-- eval_loss: 0.8956
-- eval_runtime: 2002.7479
-- eval_samples_per_second: 111.404
-- eval_steps_per_second: 1.741
-- epoch: 7.97
-- step: 500000
+- eval_loss: 0.8931
+- eval_runtime: 1996.5839
+- eval_samples_per_second: 111.748
+- eval_steps_per_second: 1.746
+- epoch: 8.76
+- step: 550000
 
 ## Model description
 

logs/events.out.tfevents.1703947898.3f36621fd87b.26.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:614c40257a85d1520959e154b86388d7063f29a1d39f04b52c74588290b5217a
+size 5099

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e9c0967d22d575ceb8571846677a51d1c3b0d58fd127f993400d9cdce46a7fe4
+oid sha256:1dc23a0749cc905b73ffa76782f799bcf6e4895992703b79ae7baabb82acb863
 size 497918592

trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 7.968000509952033,
+  "epoch": 8.764800560947236,
   "eval_steps": 50000,
-  "global_step": 500000,
+  "global_step": 550000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -147,6 +147,20 @@
       "eval_samples_per_second": 111.404,
       "eval_steps_per_second": 1.741,
       "step": 500000
+    },
+    {
+      "epoch": 8.76,
+      "learning_rate": 4.9920355054102726e-05,
+      "loss": 0.8856,
+      "step": 550000
+    },
+    {
+      "epoch": 8.76,
+      "eval_loss": 0.8930546045303345,
+      "eval_runtime": 1996.5839,
+      "eval_samples_per_second": 111.748,
+      "eval_steps_per_second": 1.746,
+      "step": 550000
     }
   ],
   "logging_steps": 50000,
@@ -154,7 +168,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 500,
   "save_steps": 50000,
-  "total_flos": 1.04516584169472e+18,
+  "total_flos": 1.14968232787968e+18,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null