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: 0.8826
-- eval_runtime: 1984.894
-- eval_samples_per_second: 112.407
-- eval_steps_per_second: 1.757
-- epoch: 15.14
-- step: 950000
+- eval_loss: 0.8808
+- eval_runtime: 2006.4913
+- eval_samples_per_second: 111.197
+- eval_steps_per_second: 1.738
+- epoch: 15.94
+- step: 1000000
 
 ## Model description
 

logs/events.out.tfevents.1704950940.59e5ef9c65b4.27.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c55f7ac06463e7b77c85b5d728996cb0cdc630407aab992e3444598760dee18
+size 5099

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4317832d3dae9b56906cfddbe0df26656c15e502299d530213ef7b15c899ccf6
+oid sha256:298e43362a7a534b4bf75a6ea66a33046377289bf06732c22b0ed62a21b19beb
 size 497918592

trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 15.139200968908861,
+  "epoch": 15.936001019904065,
   "eval_steps": 50000,
-  "global_step": 950000,
+  "global_step": 1000000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -273,6 +273,20 @@
       "eval_samples_per_second": 112.407,
       "eval_steps_per_second": 1.757,
       "step": 950000
+    },
+    {
+      "epoch": 15.94,
+      "learning_rate": 4.992034549250211e-05,
+      "loss": 0.8502,
+      "step": 1000000
+    },
+    {
+      "epoch": 15.94,
+      "eval_loss": 0.8808427453041077,
+      "eval_runtime": 2006.4913,
+      "eval_samples_per_second": 111.197,
+      "eval_steps_per_second": 1.738,
+      "step": 1000000
     }
   ],
   "logging_steps": 50000,
@@ -280,7 +294,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 500,
   "save_steps": 50000,
-  "total_flos": 1.9858145439744e+18,
+  "total_flos": 2.0903313567744e+18,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null