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: 0.9440
-- eval_runtime: 1372.4075
-- eval_samples_per_second: 109.297
-- eval_steps_per_second: 1.708
-- epoch: 4.74
-- step: 200000
+- eval_loss: 0.9341
+- eval_runtime: 1371.037
+- eval_samples_per_second: 109.406
+- eval_steps_per_second: 1.71
+- epoch: 5.93
+- step: 250000
 
 ## Model description
 

logs/events.out.tfevents.1707241207.9e0a4dd4b052.27.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27617536009dd3c4482fd830ce731581dea0c8c34026aa83f068c40e235dee85
+size 5154

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e060633c939df2df9ef4e64f7f01d7b40ea23163d698925b3be67518a2a4825b
+oid sha256:165c3a8d32e2177a7f5e1d65c5b7bf467c7ecf6f0f5c9ce58d89844a6eb2fc1b
 size 497918592

trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 4.74068455484972,
+  "epoch": 5.92585569356215,
   "eval_steps": 50000,
-  "global_step": 200000,
+  "global_step": 250000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -63,6 +63,20 @@
       "eval_samples_per_second": 109.297,
       "eval_steps_per_second": 1.708,
       "step": 200000
+    },
+    {
+      "epoch": 5.93,
+      "learning_rate": 4.94076751682943e-05,
+      "loss": 0.9411,
+      "step": 250000
+    },
+    {
+      "epoch": 5.93,
+      "eval_loss": 0.9341336488723755,
+      "eval_runtime": 1371.037,
+      "eval_samples_per_second": 109.406,
+      "eval_steps_per_second": 1.71,
+      "step": 250000
     }
   ],
   "logging_steps": 50000,
@@ -70,7 +84,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 100,
   "save_steps": 50000,
-  "total_flos": 4.18063070527488e+17,
+  "total_flos": 5.2257883815936e+17,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null