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: 0.9003
-- eval_runtime: 1982.6092
-- eval_samples_per_second: 112.536
-- eval_steps_per_second: 1.759
-- epoch: 7.17
-- step: 450000
+- eval_loss: 0.8956
+- eval_runtime: 2002.7479
+- eval_samples_per_second: 111.404
+- eval_steps_per_second: 1.741
+- epoch: 7.97
+- step: 500000
 
 ## Model description
 

logs/events.out.tfevents.1703906177.89bfe0312227.27.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1589211cb662c689753035ddec80074034911793b00e509e94937b37bb9e090a
+size 5099

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:606bd0335ab3b3f558e15ec0b468d5ef4993267b05d0cae2cd6a7594acb376cc
+oid sha256:e9c0967d22d575ceb8571846677a51d1c3b0d58fd127f993400d9cdce46a7fe4
 size 497918592

trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 7.17120045895683,
+  "epoch": 7.968000509952033,
   "eval_steps": 50000,
-  "global_step": 450000,
+  "global_step": 500000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -133,6 +133,20 @@
       "eval_samples_per_second": 112.536,
       "eval_steps_per_second": 1.759,
       "step": 450000
+    },
+    {
+      "epoch": 7.97,
+      "learning_rate": 4.992035186690252e-05,
+      "loss": 0.8933,
+      "step": 500000
+    },
+    {
+      "epoch": 7.97,
+      "eval_loss": 0.8956149220466614,
+      "eval_runtime": 2002.7479,
+      "eval_samples_per_second": 111.404,
+      "eval_steps_per_second": 1.741,
+      "step": 500000
     }
   ],
   "logging_steps": 50000,
@@ -140,7 +154,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 500,
   "save_steps": 50000,
-  "total_flos": 9.4064902889472e+17,
+  "total_flos": 1.04516584169472e+18,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null