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: 0.9278
-- eval_runtime: 1370.7524
-- eval_samples_per_second: 109.429
-- eval_steps_per_second: 1.71
-- epoch: 7.11
-- step: 300000
+- 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
 
 ## Model description
 

logs/events.out.tfevents.1707910972.44fe15909855.26.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84635da10e4293ca98e4ab09219c605aff6a9e2063436d7c931fb11bd501e73d
+size 5142

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:817c99b49cf8ff64a8be15c838a54ecbf8a4fc5594cd35f6f42a32968bfdcf15
+oid sha256:80c5d2288f11afad155ea8e263f6ab3a3f407be9730db3d7af7b8c2689bf5355
 size 497918592

trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 7.111026832274581,
+  "epoch": 8.296197970987011,
   "eval_steps": 50000,
-  "global_step": 300000,
+  "global_step": 350000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -91,6 +91,20 @@
       "eval_samples_per_second": 109.429,
       "eval_steps_per_second": 1.71,
       "step": 300000
+    },
+    {
+      "epoch": 8.3,
+      "learning_rate": 4.9407651464871526e-05,
+      "loss": 0.9129,
+      "step": 350000
+    },
+    {
+      "epoch": 8.3,
+      "eval_loss": 0.9227856993675232,
+      "eval_runtime": 1365.4307,
+      "eval_samples_per_second": 109.855,
+      "eval_steps_per_second": 1.717,
+      "step": 350000
     }
   ],
   "logging_steps": 50000,
@@ -98,7 +112,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 100,
   "save_steps": 50000,
-  "total_flos": 6.27093560623104e+17,
+  "total_flos": 7.31609328254976e+17,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null