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: 0.8780
-- eval_runtime: 1999.9414
-- eval_samples_per_second: 111.561
-- eval_steps_per_second: 1.744
-- epoch: 19.92
-- step: 1250000
+- eval_loss: 0.8783
+- eval_runtime: 1991.7989
+- eval_samples_per_second: 112.017
+- eval_steps_per_second: 1.751
+- epoch: 20.72
+- step: 1300000
 
 ## Model description
 

logs/events.out.tfevents.1705818154.ccf5de59745c.25.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f9cf05ba89bddaf58e3ced915683243eb9e91abeb18e0f528e2ad4053798e24
+size 5099

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:04ffd00e627c19459a67e5941fc71fd1d2ade76087a616b8aa018e0ed786e285
+oid sha256:0e4c34037a32ea169313a062feef6dff06f4e10ff0eca165661cc478ec9832b1
 size 497918592

trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 19.920001274880082,
+  "epoch": 20.716801325875284,
   "eval_steps": 50000,
-  "global_step": 1250000,
+  "global_step": 1300000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -357,6 +357,20 @@
       "eval_samples_per_second": 111.561,
       "eval_steps_per_second": 1.744,
       "step": 1250000
+    },
+    {
+      "epoch": 20.72,
+      "learning_rate": 4.992035186690252e-05,
+      "loss": 0.8356,
+      "step": 1300000
+    },
+    {
+      "epoch": 20.72,
+      "eval_loss": 0.878333330154419,
+      "eval_runtime": 1991.7989,
+      "eval_samples_per_second": 112.017,
+      "eval_steps_per_second": 1.751,
+      "step": 1300000
     }
   ],
   "logging_steps": 50000,
@@ -364,7 +378,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 500,
   "save_steps": 50000,
-  "total_flos": 2.61291411431424e+18,
+  "total_flos": 2.7174306004992e+18,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null