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 +84 -30

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": 36.03333333333333,
-    "f1": 48.263453219658174,
-    "train_loss": 0.2573057787469093,
-    "train_runtime": 1080.3341,
     "train_samples": 3000,
-    "train_samples_per_second": 138.846,
-    "train_steps_per_second": 4.351
 }

 {
+    "epoch": 100.0,
     "eval_samples": 3000,
+    "exact_match": 35.0,
+    "f1": 47.40760446523187,
+    "train_loss": 0.3965238536672389,
+    "train_runtime": 2138.0517,
     "train_samples": 3000,
+    "train_samples_per_second": 140.315,
+    "train_steps_per_second": 4.397
 }

args.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:78ebfbb95cb48deeaf9e5d6ab394813ee2be091b59b5813efedd3396e672d80e
 size 5652

 version https://git-lfs.github.com/spec/v1
+oid sha256:ccc83d31eac4c182e6807f7e9dfe33296af6bb357eec7a4da4f519ef71d2fbd0
 size 5652

eval_nbest_predictions.json CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:016a1097f3c389b69090372f4e9e5a10876bbfdcb7eb3bad7d1c5556d3a0af46
-size 13503411

 version https://git-lfs.github.com/spec/v1
+oid sha256:193e91bbd5318fc8026a67f82b00acffe3890058b1f9f5f790485e349b7414d9
+size 13407354

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": 36.03333333333333,
-    "f1": 48.263453219658174
 }

 {
+    "epoch": 100.0,
     "eval_samples": 3000,
+    "exact_match": 35.0,
+    "f1": 47.40760446523187
 }

train_results.json CHANGED Viewed

@@ -1,8 +1,8 @@
 {
-    "epoch": 50.0,
-    "train_loss": 0.2573057787469093,
-    "train_runtime": 1080.3341,
     "train_samples": 3000,
-    "train_samples_per_second": 138.846,
-    "train_steps_per_second": 4.351
 }

 {
+    "epoch": 100.0,
+    "train_loss": 0.3965238536672389,
+    "train_runtime": 2138.0517,
     "train_samples": 3000,
+    "train_samples_per_second": 140.315,
+    "train_steps_per_second": 4.397
 }

trainer_state.json CHANGED Viewed

@@ -1,82 +1,136 @@
 {
   "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": 0.6855,
       "step": 500
     },
     {
       "epoch": 10.64,
-      "learning_rate": 3.936170212765958e-05,
-      "loss": 0.1069,
       "step": 1000
     },
     {
       "epoch": 15.96,
-      "learning_rate": 3.4042553191489365e-05,
-      "loss": 0.0548,
       "step": 1500
     },
     {
       "epoch": 21.28,
-      "learning_rate": 2.8723404255319154e-05,
-      "loss": 0.0328,
       "step": 2000
     },
     {
       "epoch": 26.6,
-      "learning_rate": 2.340425531914894e-05,
-      "loss": 0.0335,
       "step": 2500
     },
     {
       "epoch": 31.91,
-      "learning_rate": 1.8085106382978724e-05,
-      "loss": 0.0616,
       "step": 3000
     },
     {
       "epoch": 37.23,
-      "learning_rate": 1.2765957446808511e-05,
-      "loss": 0.0913,
       "step": 3500
     },
     {
       "epoch": 42.55,
-      "learning_rate": 7.446808510638298e-06,
-      "loss": 0.182,
       "step": 4000
     },
     {
       "epoch": 47.87,
-      "learning_rate": 2.1276595744680853e-06,
-      "loss": 0.5964,
       "step": 4500
     },
     {
-      "epoch": 50.0,
-      "step": 4700,
-      "total_flos": 2484427852800000.0,
-      "train_loss": 0.2573057787469093,
-      "train_runtime": 1080.3341,
-      "train_samples_per_second": 138.846,
-      "train_steps_per_second": 4.351
     }
   ],
   "logging_steps": 500,
-  "max_steps": 4700,
-  "num_train_epochs": 50,
   "save_steps": 500,
-  "total_flos": 2484427852800000.0,
   "trial_name": null,
   "trial_params": null
 }

 {
   "best_metric": null,
   "best_model_checkpoint": null,
+  "epoch": 100.0,
   "eval_steps": 500,
+  "global_step": 9400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 5.32,
+      "learning_rate": 4.734042553191489e-05,
+      "loss": 0.6879,
       "step": 500
     },
     {
       "epoch": 10.64,
+      "learning_rate": 4.468085106382979e-05,
+      "loss": 0.1213,
       "step": 1000
     },
     {
       "epoch": 15.96,
+      "learning_rate": 4.2021276595744684e-05,
+      "loss": 0.0743,
       "step": 1500
     },
     {
       "epoch": 21.28,
+      "learning_rate": 3.936170212765958e-05,
+      "loss": 0.0487,
       "step": 2000
     },
     {
       "epoch": 26.6,
+      "learning_rate": 3.670212765957447e-05,
+      "loss": 0.0615,
       "step": 2500
     },
     {
       "epoch": 31.91,
+      "learning_rate": 3.4042553191489365e-05,
+      "loss": 0.0804,
       "step": 3000
     },
     {
       "epoch": 37.23,
+      "learning_rate": 3.1382978723404254e-05,
+      "loss": 0.0936,
       "step": 3500
     },
     {
       "epoch": 42.55,
+      "learning_rate": 2.8723404255319154e-05,
+      "loss": 0.1289,
       "step": 4000
     },
     {
       "epoch": 47.87,
+      "learning_rate": 2.6063829787234046e-05,
+      "loss": 0.1842,
       "step": 4500
     },
     {
+      "epoch": 53.19,
+      "learning_rate": 2.340425531914894e-05,
+      "loss": 0.2967,
+      "step": 5000
+    },
+    {
+      "epoch": 58.51,
+      "learning_rate": 2.074468085106383e-05,
+      "loss": 0.394,
+      "step": 5500
+    },
+    {
+      "epoch": 63.83,
+      "learning_rate": 1.8085106382978724e-05,
+      "loss": 0.6998,
+      "step": 6000
+    },
+    {
+      "epoch": 69.15,
+      "learning_rate": 1.5425531914893617e-05,
+      "loss": 0.7916,
+      "step": 6500
+    },
+    {
+      "epoch": 74.47,
+      "learning_rate": 1.2765957446808511e-05,
+      "loss": 0.7954,
+      "step": 7000
+    },
+    {
+      "epoch": 79.79,
+      "learning_rate": 1.0106382978723404e-05,
+      "loss": 0.8401,
+      "step": 7500
+    },
+    {
+      "epoch": 85.11,
+      "learning_rate": 7.446808510638298e-06,
+      "loss": 0.8077,
+      "step": 8000
+    },
+    {
+      "epoch": 90.43,
+      "learning_rate": 4.787234042553191e-06,
+      "loss": 0.6265,
+      "step": 8500
+    },
+    {
+      "epoch": 95.74,
+      "learning_rate": 2.1276595744680853e-06,
+      "loss": 0.511,
+      "step": 9000
+    },
+    {
+      "epoch": 100.0,
+      "step": 9400,
+      "total_flos": 4968855705600000.0,
+      "train_loss": 0.3965238536672389,
+      "train_runtime": 2138.0517,
+      "train_samples_per_second": 140.315,
+      "train_steps_per_second": 4.397
     }
   ],
   "logging_steps": 500,
+  "max_steps": 9400,
+  "num_train_epochs": 100,
   "save_steps": 500,
+  "total_flos": 4968855705600000.0,
   "trial_name": null,
   "trial_params": null
 }