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: 0.8804
-- eval_runtime: 2001.1642
-- eval_samples_per_second: 111.493
-- eval_steps_per_second: 1.742
-- epoch: 27.09
-- step: 1700000
+- eval_loss: 0.8755
+- eval_runtime: 2011.2204
+- eval_samples_per_second: 110.935
+- eval_steps_per_second: 1.734
+- epoch: 27.89
+- step: 1750000
 
 ## Model description
 

logs/events.out.tfevents.1706959201.da32439aada9.27.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78170dcdced1e0eb4f4cc7998c6687cb55b9d9832697924e5109cdff08996864
+size 5099

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da84264f61b81ecbeaa737abc94c8f7f2c8eaa12e6750a0475674fbc27a33a05
+oid sha256:d01d405f1fd949e31599c2d9dcedc77bbf8a8dd66e8e7243f43e7b70e2c97dd7
 size 497918592

trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 27.09120173383691,
+  "epoch": 27.888001784832113,
   "eval_steps": 50000,
-  "global_step": 1700000,
+  "global_step": 1750000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -483,6 +483,20 @@
       "eval_samples_per_second": 111.493,
       "eval_steps_per_second": 1.742,
       "step": 1700000
+    },
+    {
+      "epoch": 27.89,
+      "learning_rate": 4.992035186690252e-05,
+      "loss": 0.8188,
+      "step": 1750000
+    },
+    {
+      "epoch": 27.89,
+      "eval_loss": 0.875482976436615,
+      "eval_runtime": 2011.2204,
+      "eval_samples_per_second": 110.935,
+      "eval_steps_per_second": 1.734,
+      "step": 1750000
     }
   ],
   "logging_steps": 50000,
@@ -490,7 +504,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 500,
   "save_steps": 50000,
-  "total_flos": 3.55356281659392e+18,
+  "total_flos": 3.65807962939392e+18,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null