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: 0.9112
-- eval_runtime: 1361.672
-- eval_samples_per_second: 110.159
-- eval_steps_per_second: 1.721
-- epoch: 11.85
-- step: 500000
+- eval_loss: 0.9121
+- eval_runtime: 1374.6065
+- eval_samples_per_second: 109.122
+- eval_steps_per_second: 1.705
+- epoch: 13.04
+- step: 550000
 
 ## Model description
 

logs/events.out.tfevents.1708491210.a9eab0e53fc5.26.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e57b35d1df50f788c981d90d40c4f5f8c18d2c72e1ff6ddbf92466411f5bae8f
+size 5154

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:296515dd3d70398833ab4b19d88b7e46d0b53f16d5b6a86506db5d99c8581642
+oid sha256:bc26b7156c94261538c66d6f1c986a9445a4c87876cad57acc8a240d957d2680
 size 497918592

trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 11.8517113871243,
+  "epoch": 13.036882525836731,
   "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": 110.159,
       "eval_steps_per_second": 1.721,
       "step": 500000
+    },
+    {
+      "epoch": 13.04,
+      "learning_rate": 4.9407651464871526e-05,
+      "loss": 0.8809,
+      "step": 550000
+    },
+    {
+      "epoch": 13.04,
+      "eval_loss": 0.9120939373970032,
+      "eval_runtime": 1374.6065,
+      "eval_samples_per_second": 109.122,
+      "eval_steps_per_second": 1.705,
+      "step": 550000
     }
   ],
   "logging_steps": 50000,
@@ -154,7 +168,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 100,
   "save_steps": 50000,
-  "total_flos": 1.045156631150592e+18,
+  "total_flos": 1.149671353614336e+18,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null