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: 0.8813
-- eval_runtime: 2003.661
-- eval_samples_per_second: 111.354
-- eval_steps_per_second: 1.74
-- epoch: 19.12
-- step: 1200000
+- 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
 
 ## Model description
 

logs/events.out.tfevents.1705756600.1db2a193ed0f.26.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aeb724094c7b4252ff746d4c54760f8820065b561ef23bbda732e9e8d02d3531
+size 5099

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c66f8cbaa7b4022b34fab9545aac3eee47ad1e7bfad0a0c3f863b03566a5e24d
+oid sha256:04ffd00e627c19459a67e5941fc71fd1d2ade76087a616b8aa018e0ed786e285
 size 497918592

trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 19.123201223884877,
+  "epoch": 19.920001274880082,
   "eval_steps": 50000,
-  "global_step": 1200000,
+  "global_step": 1250000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -343,6 +343,20 @@
       "eval_samples_per_second": 111.354,
       "eval_steps_per_second": 1.74,
       "step": 1200000
+    },
+    {
+      "epoch": 19.92,
+      "learning_rate": 4.9920348679702315e-05,
+      "loss": 0.8382,
+      "step": 1250000
+    },
+    {
+      "epoch": 19.92,
+      "eval_loss": 0.8779821991920471,
+      "eval_runtime": 1999.9414,
+      "eval_samples_per_second": 111.561,
+      "eval_steps_per_second": 1.744,
+      "step": 1250000
     }
   ],
   "logging_steps": 50000,
@@ -350,7 +364,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 500,
   "save_steps": 50000,
-  "total_flos": 2.50839730151424e+18,
+  "total_flos": 2.61291411431424e+18,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null