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: 0.8771
-- eval_runtime: 1995.2079
-- eval_samples_per_second: 111.825
+- eval_loss: 0.8785
+- eval_runtime: 1994.3392
+- eval_samples_per_second: 111.874
 - eval_steps_per_second: 1.748
-- epoch: 23.9
-- step: 1500000
+- epoch: 24.7
+- step: 1550000
 
 ## Model description
 

logs/events.out.tfevents.1706414275.bae337cb6ff3.26.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5fbbe8e4efb24b0fe86bc3844d93e9007d685c16aba6b387189e3812a7bb4bd5
+size 5099

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f0541783e22d8ff3ac5569ac1df2fbf083c4b29926687a32b871ac59ce20dc7
+oid sha256:d7c2e9b269aec002f777f3596e10788d6443bfda502ad3980d9dd7d4f4cc9d0c
 size 497918592

trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 23.9040015298561,
+  "epoch": 24.7008015808513,
   "eval_steps": 50000,
-  "global_step": 1500000,
+  "global_step": 1550000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -427,6 +427,20 @@
       "eval_samples_per_second": 111.825,
       "eval_steps_per_second": 1.748,
       "step": 1500000
+    },
+    {
+      "epoch": 24.7,
+      "learning_rate": 4.9920348679702315e-05,
+      "loss": 0.8254,
+      "step": 1550000
+    },
+    {
+      "epoch": 24.7,
+      "eval_loss": 0.8784825205802917,
+      "eval_runtime": 1994.3392,
+      "eval_samples_per_second": 111.874,
+      "eval_steps_per_second": 1.748,
+      "step": 1550000
     }
   ],
   "logging_steps": 50000,
@@ -434,7 +448,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 500,
   "save_steps": 50000,
-  "total_flos": 3.13549687185408e+18,
+  "total_flos": 3.24001335803904e+18,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null