End of training

Browse files

Files changed (8) hide show

README.md +4 -1
all_results.json +7 -7
args.bin +1 -1
eval_nbest_predictions.json +2 -2
eval_predictions.json +0 -0
eval_results.json +3 -3
train_results.json +5 -5
trainer_state.json +12 -66

README.md CHANGED Viewed

@@ -2,7 +2,10 @@
 license: apache-2.0
 base_model: albert-base-v2
 tags:
 - generated_from_trainer
 model-index:
 - name: out
   results: []
@@ -13,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 # out
-This model is a fine-tuned version of [albert-base-v2](https://huggingface.co/albert-base-v2) on the None dataset.
 ## Model description

 license: apache-2.0
 base_model: albert-base-v2
 tags:
+- question-answering
 - generated_from_trainer
+datasets:
+- squad
 model-index:
 - name: out
   results: []
 # out
+This model is a fine-tuned version of [albert-base-v2](https://huggingface.co/albert-base-v2) on the squad dataset.
 ## Model description

all_results.json CHANGED Viewed

@@ -1,11 +1,11 @@
 {
-    "epoch": 50.0,
     "eval_samples": 3000,
-    "exact_match": 63.86666666666667,
-    "f1": 73.7236267616498,
-    "train_loss": 0.12967263718868824,
-    "train_runtime": 3347.7202,
     "train_samples": 3000,
-    "train_samples_per_second": 44.807,
-    "train_steps_per_second": 1.404
 }

 {
+    "epoch": 3.0,
     "eval_samples": 3000,
+    "exact_match": 64.2,
+    "f1": 74.31179260848076,
+    "train_loss": 2.188524670071072,
+    "train_runtime": 54.4098,
     "train_samples": 3000,
+    "train_samples_per_second": 165.411,
+    "train_steps_per_second": 0.662
 }

args.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4015dd159607636eb5bec32e4824d97fc96cf9c1a1c298393b8d67049f193c70
 size 5652

 version https://git-lfs.github.com/spec/v1
+oid sha256:c8885ffd4ecc33bd503c0f8a9a0020a0f7bade75a2380de2544b287f02ce1cc7
 size 5652

eval_nbest_predictions.json CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b59372aabc13b14e39dfe745c0ad148227ea05b04ec91bf8240be8d05daeaaeb
-size 13849437

 version https://git-lfs.github.com/spec/v1
+oid sha256:b82a97ed87fdc47a92d9f9cc868907de41476cd54d137c4eec77a44457560143
+size 13662949

eval_predictions.json CHANGED Viewed

The diff for this file is too large to render. See raw diff

eval_results.json CHANGED Viewed

@@ -1,6 +1,6 @@
 {
-    "epoch": 50.0,
     "eval_samples": 3000,
-    "exact_match": 63.86666666666667,
-    "f1": 73.7236267616498
 }

 {
+    "epoch": 3.0,
     "eval_samples": 3000,
+    "exact_match": 64.2,
+    "f1": 74.31179260848076
 }

train_results.json CHANGED Viewed

@@ -1,8 +1,8 @@
 {
-    "epoch": 50.0,
-    "train_loss": 0.12967263718868824,
-    "train_runtime": 3347.7202,
     "train_samples": 3000,
-    "train_samples_per_second": 44.807,
-    "train_steps_per_second": 1.404
 }

 {
+    "epoch": 3.0,
+    "train_loss": 2.188524670071072,
+    "train_runtime": 54.4098,
     "train_samples": 3000,
+    "train_samples_per_second": 165.411,
+    "train_steps_per_second": 0.662
 }

trainer_state.json CHANGED Viewed

@@ -1,82 +1,28 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 50.0,
   "eval_steps": 500,
-  "global_step": 4700,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 5.32,
-      "learning_rate": 4.468085106382979e-05,
-      "loss": 0.867,
-      "step": 500
-    },
-    {
-      "epoch": 10.64,
-      "learning_rate": 3.936170212765958e-05,
-      "loss": 0.1247,
-      "step": 1000
-    },
-    {
-      "epoch": 15.96,
-      "learning_rate": 3.4042553191489365e-05,
-      "loss": 0.069,
-      "step": 1500
-    },
-    {
-      "epoch": 21.28,
-      "learning_rate": 2.8723404255319154e-05,
-      "loss": 0.044,
-      "step": 2000
-    },
-    {
-      "epoch": 26.6,
-      "learning_rate": 2.340425531914894e-05,
-      "loss": 0.0192,
-      "step": 2500
-    },
-    {
-      "epoch": 31.91,
-      "learning_rate": 1.8085106382978724e-05,
-      "loss": 0.0142,
-      "step": 3000
-    },
-    {
-      "epoch": 37.23,
-      "learning_rate": 1.2765957446808511e-05,
-      "loss": 0.0169,
-      "step": 3500
-    },
-    {
-      "epoch": 42.55,
-      "learning_rate": 7.446808510638298e-06,
-      "loss": 0.0163,
-      "step": 4000
-    },
-    {
-      "epoch": 47.87,
-      "learning_rate": 2.1276595744680853e-06,
-      "loss": 0.0219,
-      "step": 4500
-    },
-    {
-      "epoch": 50.0,
-      "step": 4700,
-      "total_flos": 1.044795366144e+17,
-      "train_loss": 0.12967263718868824,
-      "train_runtime": 3347.7202,
-      "train_samples_per_second": 44.807,
-      "train_steps_per_second": 1.404
     }
   ],
   "logging_steps": 500,
-  "max_steps": 4700,
-  "num_train_epochs": 50,
   "save_steps": 500,
-  "total_flos": 1.044795366144e+17,
   "trial_name": null,
   "trial_params": null
 }

 {
   "best_metric": null,
   "best_model_checkpoint": null,
+  "epoch": 3.0,
   "eval_steps": 500,
+  "global_step": 36,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
+      "epoch": 3.0,
+      "step": 36,
+      "total_flos": 149065671168000.0,
+      "train_loss": 2.188524670071072,
+      "train_runtime": 54.4098,
+      "train_samples_per_second": 165.411,
+      "train_steps_per_second": 0.662
     }
   ],
   "logging_steps": 500,
+  "max_steps": 36,
+  "num_train_epochs": 3,
   "save_steps": 500,
+  "total_flos": 149065671168000.0,
   "trial_name": null,
   "trial_params": null
 }