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: 0.9181
-- eval_runtime: 1373.3191
-- eval_samples_per_second: 109.224
-- eval_steps_per_second: 1.707
-- epoch: 9.48
-- step: 400000
+- eval_loss: 0.9149
+- eval_runtime: 1375.6915
+- eval_samples_per_second: 109.036
+- eval_steps_per_second: 1.704
+- epoch: 10.67
+- step: 450000
 
 ## Model description
 

logs/events.out.tfevents.1708053939.b8db41594979.26.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ec921edbc45bb131a96af962a7f4000785f6eade03411f7facd811fb3e4d3bd
+size 5154

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:380c6d61973d72a6f2fb8506f90319b6fc18085e94ed9f13614758ca5090a91a
+oid sha256:a80fe317d4c5fc702b8ebe10cd504d78022508d5ffbf0eb2ff6e81820878b176
 size 497918592

trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 9.48136910969944,
+  "epoch": 10.66654024841187,
   "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": 109.224,
       "eval_steps_per_second": 1.707,
       "step": 400000
+    },
+    {
+      "epoch": 10.67,
+      "learning_rate": 4.940766331658292e-05,
+      "loss": 0.8948,
+      "step": 450000
+    },
+    {
+      "epoch": 10.67,
+      "eval_loss": 0.914903461933136,
+      "eval_runtime": 1375.6915,
+      "eval_samples_per_second": 109.036,
+      "eval_steps_per_second": 1.704,
+      "step": 450000
     }
   ],
   "logging_steps": 50000,
@@ -126,7 +140,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 100,
   "save_steps": 50000,
-  "total_flos": 8.36125095886848e+17,
+  "total_flos": 9.4064086351872e+17,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null