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: 0.9041
-- eval_runtime: 1998.7351
-- eval_samples_per_second: 111.628
-- eval_steps_per_second: 1.745
-- epoch: 6.37
-- step: 400000
+- 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
 
 ## Model description
 

logs/events.out.tfevents.1703432183.d9c68bf90493.26.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12d41be54d60e81fa3662705e00a7d3a2e13a04920de647838160bb20b2a65a9
+size 5099

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:138a75cd206a202484cd2a6c4b8e80b2fa7b01d519d7871da738b9518489871c
+oid sha256:606bd0335ab3b3f558e15ec0b468d5ef4993267b05d0cae2cd6a7594acb376cc
 size 497918592

trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 6.374400407961626,
+  "epoch": 7.17120045895683,
   "eval_steps": 50000,
-  "global_step": 400000,
+  "global_step": 450000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -119,6 +119,20 @@
       "eval_samples_per_second": 111.628,
       "eval_steps_per_second": 1.745,
       "step": 400000
+    },
+    {
+      "epoch": 7.17,
+      "learning_rate": 4.9920355054102726e-05,
+      "loss": 0.8994,
+      "step": 450000
+    },
+    {
+      "epoch": 7.17,
+      "eval_loss": 0.9003444910049438,
+      "eval_runtime": 1982.6092,
+      "eval_samples_per_second": 112.536,
+      "eval_steps_per_second": 1.759,
+      "step": 450000
     }
   ],
   "logging_steps": 50000,
@@ -126,7 +140,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 500,
   "save_steps": 50000,
-  "total_flos": 8.3613254270976e+17,
+  "total_flos": 9.4064902889472e+17,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null