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: 0.9588
-- eval_runtime: 1376.5573
-- eval_samples_per_second: 108.967
-- eval_steps_per_second: 1.703
-- epoch: 3.56
-- step: 150000
+- eval_loss: 0.9440
+- eval_runtime: 1372.4075
+- eval_samples_per_second: 109.297
+- eval_steps_per_second: 1.708
+- epoch: 4.74
+- step: 200000
 
 ## Model description
 

logs/events.out.tfevents.1707188120.9f8b04a8a12f.27.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78095757d924d052f6a0cabf736b3f929c822728ce9e7dcffc693d93e41a7a7e
+size 5154

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:569bc69dea165d5d6cfe12190fa1b33d3707f544b843c3a41ac3a46c44484a09
+oid sha256:e060633c939df2df9ef4e64f7f01d7b40ea23163d698925b3be67518a2a4825b
 size 497918592

trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 3.5555134161372903,
+  "epoch": 4.74068455484972,
   "eval_steps": 50000,
-  "global_step": 150000,
+  "global_step": 200000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -49,6 +49,20 @@
       "eval_samples_per_second": 108.967,
       "eval_steps_per_second": 1.703,
       "step": 150000
+    },
+    {
+      "epoch": 4.74,
+      "learning_rate": 4.9407651464871526e-05,
+      "loss": 0.9592,
+      "step": 200000
+    },
+    {
+      "epoch": 4.74,
+      "eval_loss": 0.944024384021759,
+      "eval_runtime": 1372.4075,
+      "eval_samples_per_second": 109.297,
+      "eval_steps_per_second": 1.708,
+      "step": 200000
     }
   ],
   "logging_steps": 50000,
@@ -56,7 +70,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 100,
   "save_steps": 50000,
-  "total_flos": 3.13547302895616e+17,
+  "total_flos": 4.18063070527488e+17,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null