End of training

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+eval_nbest_predictions.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -33,17 +33,13 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 3e-05
-- train_batch_size: 32
+- learning_rate: 5e-05
+- train_batch_size: 16
 - eval_batch_size: 64
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 5.0
-
-### Training results
-
-
+- num_epochs: 3.0
 
 ### Framework versions
 

all_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 5.0,
+    "eval_exact_match": 0.0,
+    "eval_f1": 0.0,
+    "eval_runtime": 30.7516,
+    "eval_samples": 3934,
+    "eval_samples_per_second": 127.928,
+    "eval_steps_per_second": 2.016,
+    "total_flos": 3.611513123226624e+16,
+    "train_loss": 3.3395631154378256,
+    "train_runtime": 2548.4435,
+    "train_samples": 27643,
+    "train_samples_per_second": 54.235,
+    "train_steps_per_second": 1.695
+}

eval_nbest_predictions.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a3af8db419b6484eb5a0b8e60a90c4304df284034a4732d294273454c5b5272
+size 16376099

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "eval_exact_match": 0.0,
+    "eval_f1": 0.0,
+    "eval_runtime": 30.7516,
+    "eval_samples": 3934,
+    "eval_samples_per_second": 127.928,
+    "eval_steps_per_second": 2.016
+}

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:29a42aa5d63fe277d3bdba1a6180a83ce7bce87d507ab92829bcf2e53a370aa9
+oid sha256:a09ee7199d00164648e34c2ff242af9b5dee3ae2a30c9e0ac2457e08ea7ea2b7
 size 430330672

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 5.0,
+    "total_flos": 3.611513123226624e+16,
+    "train_loss": 3.3395631154378256,
+    "train_runtime": 2548.4435,
+    "train_samples": 27643,
+    "train_samples_per_second": 54.235,
+    "train_steps_per_second": 1.695
+}

trainer_state.json

@@ -0,0 +1,98 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 4320,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.5787037037037037,
+      "grad_norm": 8.216769218444824,
+      "learning_rate": 2.652777777777778e-05,
+      "loss": 4.5636,
+      "step": 500
+    },
+    {
+      "epoch": 1.1574074074074074,
+      "grad_norm": 11.628066062927246,
+      "learning_rate": 2.3055555555555554e-05,
+      "loss": 3.763,
+      "step": 1000
+    },
+    {
+      "epoch": 1.7361111111111112,
+      "grad_norm": 9.473577499389648,
+      "learning_rate": 1.9583333333333333e-05,
+      "loss": 3.4828,
+      "step": 1500
+    },
+    {
+      "epoch": 2.314814814814815,
+      "grad_norm": 10.071398735046387,
+      "learning_rate": 1.6111111111111115e-05,
+      "loss": 3.308,
+      "step": 2000
+    },
+    {
+      "epoch": 2.8935185185185186,
+      "grad_norm": 10.017462730407715,
+      "learning_rate": 1.2638888888888888e-05,
+      "loss": 3.1879,
+      "step": 2500
+    },
+    {
+      "epoch": 3.4722222222222223,
+      "grad_norm": 12.130489349365234,
+      "learning_rate": 9.166666666666668e-06,
+      "loss": 3.0,
+      "step": 3000
+    },
+    {
+      "epoch": 4.050925925925926,
+      "grad_norm": 13.29631233215332,
+      "learning_rate": 5.694444444444445e-06,
+      "loss": 2.9502,
+      "step": 3500
+    },
+    {
+      "epoch": 4.62962962962963,
+      "grad_norm": 10.901876449584961,
+      "learning_rate": 2.222222222222222e-06,
+      "loss": 2.8179,
+      "step": 4000
+    },
+    {
+      "epoch": 5.0,
+      "step": 4320,
+      "total_flos": 3.611513123226624e+16,
+      "train_loss": 3.3395631154378256,
+      "train_runtime": 2548.4435,
+      "train_samples_per_second": 54.235,
+      "train_steps_per_second": 1.695
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 4320,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3.611513123226624e+16,
+  "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:c4ea58a9c9a4a9d3ee7edc102576859985898ca9af4b757ca386aa741f63081c
+oid sha256:9b6eb71d5d8040476b860432bbcca50838baa225a6bab4496ce7359b31657105
 size 5240