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: 0.8783
-- eval_runtime: 1991.7989
-- eval_samples_per_second: 112.017
-- eval_steps_per_second: 1.751
-- epoch: 20.72
-- step: 1300000
+- eval_loss: 0.8800
+- eval_runtime: 2009.116
+- eval_samples_per_second: 111.051
+- eval_steps_per_second: 1.736
+- epoch: 21.51
+- step: 1350000
 
 ## Model description
 

logs/events.out.tfevents.1705893227.5c4654091326.26.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87dfabb41fe91ee309325aa0cf3fb00f719d0915d2da7b1412ebc04ff3da5da1
+size 5099

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e4c34037a32ea169313a062feef6dff06f4e10ff0eca165661cc478ec9832b1
+oid sha256:b555f9f5be3eef7badda0c03c78dbd75194665f5d38a060dc9f2384f01950c7b
 size 497918592

trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 20.716801325875284,
+  "epoch": 21.51360137687049,
   "eval_steps": 50000,
-  "global_step": 1300000,
+  "global_step": 1350000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -371,6 +371,20 @@
       "eval_samples_per_second": 112.017,
       "eval_steps_per_second": 1.751,
       "step": 1300000
+    },
+    {
+      "epoch": 21.51,
+      "learning_rate": 4.992034708610221e-05,
+      "loss": 0.8311,
+      "step": 1350000
+    },
+    {
+      "epoch": 21.51,
+      "eval_loss": 0.8799993991851807,
+      "eval_runtime": 2009.116,
+      "eval_samples_per_second": 111.051,
+      "eval_steps_per_second": 1.736,
+      "step": 1350000
     }
   ],
   "logging_steps": 50000,
@@ -378,7 +392,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 500,
   "save_steps": 50000,
-  "total_flos": 2.7174306004992e+18,
+  "total_flos": 2.82194708668416e+18,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null