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: 0.9052
-- eval_runtime: 1372.6886
-- eval_samples_per_second: 109.275
-- eval_steps_per_second: 1.708
-- epoch: 17.78
-- step: 750000
+- eval_loss: 0.9034
+- eval_runtime: 1376.7168
+- eval_samples_per_second: 108.955
+- eval_steps_per_second: 1.703
+- epoch: 18.96
+- step: 800000
 
 ## Model description
 

logs/events.out.tfevents.1709140136.1603750d14c2.25.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:739a6fc016aab02b7ce054e6e14a8c9a4bff35d40bed122d2e04dca553a4e4a2
+size 5154

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d29d6d99a53aea865a135433fe708f41fc80200781badae74d7b36925f8b4142
+oid sha256:a347c18c530d4f57e7d1f7191e6060cd0df8e867924acb29724727579ae0277b
 size 497918592

trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 17.777567080686453,
+  "epoch": 18.96273821939888,
   "eval_steps": 50000,
-  "global_step": 750000,
+  "global_step": 800000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -217,6 +217,20 @@
       "eval_samples_per_second": 109.275,
       "eval_steps_per_second": 1.708,
       "step": 750000
+    },
+    {
+      "epoch": 18.96,
+      "learning_rate": 4.940762776144876e-05,
+      "loss": 0.8528,
+      "step": 800000
+    },
+    {
+      "epoch": 18.96,
+      "eval_loss": 0.9034462571144104,
+      "eval_runtime": 1376.7168,
+      "eval_samples_per_second": 108.955,
+      "eval_steps_per_second": 1.703,
+      "step": 800000
     }
   ],
   "logging_steps": 50000,
@@ -224,7 +238,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 100,
   "save_steps": 50000,
-  "total_flos": 1.567734424141824e+18,
+  "total_flos": 1.672250191773696e+18,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e11847e74c240616571649a97da406725778726648f4a5d5ba652545c0ac20df
+oid sha256:eb10217ea6ee5a53faf925ba15fc624a98562d0ed446408452fcac3eb4a1b18e
 size 4728