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: 0.9341
-- eval_runtime: 1371.037
-- eval_samples_per_second: 109.406
+- eval_loss: 0.9278
+- eval_runtime: 1370.7524
+- eval_samples_per_second: 109.429
 - eval_steps_per_second: 1.71
-- epoch: 5.93
-- step: 250000
+- epoch: 7.11
+- step: 300000
 
 ## Model description
 

logs/events.out.tfevents.1707840721.3d7c2fb775b8.26.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26657b4265609dbd747f23010ec98e121811337d0c8f206ba2295767266b7c14
+size 5142

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:165c3a8d32e2177a7f5e1d65c5b7bf467c7ecf6f0f5c9ce58d89844a6eb2fc1b
+oid sha256:817c99b49cf8ff64a8be15c838a54ecbf8a4fc5594cd35f6f42a32968bfdcf15
 size 497918592

trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 5.92585569356215,
+  "epoch": 7.111026832274581,
   "eval_steps": 50000,
-  "global_step": 250000,
+  "global_step": 300000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -77,6 +77,20 @@
       "eval_samples_per_second": 109.406,
       "eval_steps_per_second": 1.71,
       "step": 250000
+    },
+    {
+      "epoch": 7.11,
+      "learning_rate": 4.940766331658292e-05,
+      "loss": 0.9263,
+      "step": 300000
+    },
+    {
+      "epoch": 7.11,
+      "eval_loss": 0.9277684092521667,
+      "eval_runtime": 1370.7524,
+      "eval_samples_per_second": 109.429,
+      "eval_steps_per_second": 1.71,
+      "step": 300000
     }
   ],
   "logging_steps": 50000,
@@ -84,7 +98,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 100,
   "save_steps": 50000,
-  "total_flos": 5.2257883815936e+17,
+  "total_flos": 6.27093560623104e+17,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb10217ea6ee5a53faf925ba15fc624a98562d0ed446408452fcac3eb4a1b18e
+oid sha256:e11847e74c240616571649a97da406725778726648f4a5d5ba652545c0ac20df
 size 4728