End of training

README.md

@@ -15,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 2.1050
+- Loss: 2.1188
 
 ## Model description
 
@@ -40,7 +40,7 @@ The following hyperparameters were used during training:
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 5
+- num_epochs: 7
 
 ### Training results
 
@@ -51,6 +51,8 @@ The following hyperparameters were used during training:
 | 2.9516        | 3.0   | 30   | 2.5815          |
 | 2.4828        | 4.0   | 40   | 2.1538          |
 | 2.2802        | 5.0   | 50   | 2.1050          |
+| 2.1949        | 6.0   | 60   | 2.1221          |
+| 2.0416        | 7.0   | 70   | 2.1188          |
 
 
 ### Framework versions

logs/events.out.tfevents.1702140651.62a1e4c74a80.42734.11

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97351897983174456fd211c091c9d1d2895c399501d25c3cddac06fd6a6cbf6f
+size 5640

trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 2.105010747909546,
   "best_model_checkpoint": "bert-base-banking77-pt2/checkpoint-50",
-  "epoch": 5.0,
+  "epoch": 7.0,
   "eval_steps": 10,
-  "global_step": 50,
+  "global_step": 70,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -79,20 +79,48 @@
       "step": 50
     },
     {
-      "epoch": 5.0,
-      "step": 50,
-      "total_flos": 3266150400000.0,
-      "train_loss": 5.784983711242676,
-      "train_runtime": 46.2198,
-      "train_samples_per_second": 1.082,
-      "train_steps_per_second": 1.082
+      "epoch": 6.0,
+      "learning_rate": 7.142857142857143e-06,
+      "loss": 2.1949,
+      "step": 60
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 2.1220641136169434,
+      "eval_runtime": 0.161,
+      "eval_samples_per_second": 62.127,
+      "eval_steps_per_second": 12.425,
+      "step": 60
+    },
+    {
+      "epoch": 7.0,
+      "learning_rate": 0.0,
+      "loss": 2.0416,
+      "step": 70
+    },
+    {
+      "epoch": 7.0,
+      "eval_loss": 2.118767023086548,
+      "eval_runtime": 0.1487,
+      "eval_samples_per_second": 67.242,
+      "eval_steps_per_second": 13.448,
+      "step": 70
+    },
+    {
+      "epoch": 7.0,
+      "step": 70,
+      "total_flos": 4572610560000.0,
+      "train_loss": 0.6052134922572545,
+      "train_runtime": 34.1418,
+      "train_samples_per_second": 2.05,
+      "train_steps_per_second": 2.05
     }
   ],
   "logging_steps": 10,
-  "max_steps": 50,
-  "num_train_epochs": 5,
+  "max_steps": 70,
+  "num_train_epochs": 7,
   "save_steps": 10,
-  "total_flos": 3266150400000.0,
+  "total_flos": 4572610560000.0,
   "trial_name": null,
   "trial_params": null
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f0e816bb628d55636c013287b128c2af89853b6c5e028b9f9192a3db21dc0f9f
+oid sha256:3a2655d3b72395d03b486dad0d58093ce519e985274f5d96630ca8646675c264
 size 4600