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: 0.9228
-- eval_runtime: 1365.4307
-- eval_samples_per_second: 109.855
-- eval_steps_per_second: 1.717
-- epoch: 8.3
-- step: 350000
+- eval_loss: 0.9181
+- eval_runtime: 1373.3191
+- eval_samples_per_second: 109.224
+- eval_steps_per_second: 1.707
+- epoch: 9.48
+- step: 400000
 
 ## Model description
 

logs/events.out.tfevents.1708010990.ecce5c21fb5d.27.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc65cb7013b8f2509e3def68792a819e824f8fd3fa9e417ec5982b1afb8a503f
+size 5154

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:80c5d2288f11afad155ea8e263f6ab3a3f407be9730db3d7af7b8c2689bf5355
+oid sha256:380c6d61973d72a6f2fb8506f90319b6fc18085e94ed9f13614758ca5090a91a
 size 497918592

trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 8.296197970987011,
+  "epoch": 9.48136910969944,
   "eval_steps": 50000,
-  "global_step": 350000,
+  "global_step": 400000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -105,6 +105,20 @@
       "eval_samples_per_second": 109.855,
       "eval_steps_per_second": 1.717,
       "step": 350000
+    },
+    {
+      "epoch": 9.48,
+      "learning_rate": 4.940766331658292e-05,
+      "loss": 0.9026,
+      "step": 400000
+    },
+    {
+      "epoch": 9.48,
+      "eval_loss": 0.9180548787117004,
+      "eval_runtime": 1373.3191,
+      "eval_samples_per_second": 109.224,
+      "eval_steps_per_second": 1.707,
+      "step": 400000
     }
   ],
   "logging_steps": 50000,
@@ -112,7 +126,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 100,
   "save_steps": 50000,
-  "total_flos": 7.31609328254976e+17,
+  "total_flos": 8.36125095886848e+17,
   "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