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: 0.8787
-- eval_runtime: 1998.0285
-- eval_samples_per_second: 111.668
-- eval_steps_per_second: 1.745
-- epoch: 25.5
-- step: 1600000
+- eval_loss: 0.8791
+- eval_runtime: 2008.615
+- eval_samples_per_second: 111.079
+- eval_steps_per_second: 1.736
+- epoch: 26.29
+- step: 1650000
 
 ## Model description
 

logs/events.out.tfevents.1706631907.6842b220c3c1.26.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d887d5ca7717f2391911bdbcbadc952823688d4e53cca22b250049e7e65779c
+size 5099

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8353fee39d36c9ce0e2ccfab5ffffea43b72f9ad66289edfb90ed7298cc6dbdd
+oid sha256:928dde0b96414ccb0efff3d1e781716fc8dec2ee14936cc75b51774b157a21b9
 size 497918592

trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 25.497601631846504,
+  "epoch": 26.29440168284171,
   "eval_steps": 50000,
-  "global_step": 1600000,
+  "global_step": 1650000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -455,6 +455,20 @@
       "eval_samples_per_second": 111.668,
       "eval_steps_per_second": 1.745,
       "step": 1600000
+    },
+    {
+      "epoch": 26.29,
+      "learning_rate": 4.9920348679702315e-05,
+      "loss": 0.8201,
+      "step": 1650000
+    },
+    {
+      "epoch": 26.29,
+      "eval_loss": 0.8791316151618958,
+      "eval_runtime": 2008.615,
+      "eval_samples_per_second": 111.079,
+      "eval_steps_per_second": 1.736,
+      "step": 1650000
     }
   ],
   "logging_steps": 50000,
@@ -462,7 +476,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 500,
   "save_steps": 50000,
-  "total_flos": 3.344529844224e+18,
+  "total_flos": 3.44904633040896e+18,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null