Model save

all_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 1.0,
+    "eval_accuracy": 0.5619722863264766,
+    "eval_loss": 2.4340596199035645,
+    "eval_runtime": 13.1565,
+    "eval_samples_per_second": 86.497,
+    "eval_steps_per_second": 10.869,
+    "perplexity": 11.405088550670825,
+    "total_flos": 1.3626163133939712e+16,
+    "train_loss": 2.4788927044784814,
+    "train_runtime": 196.8793,
+    "train_samples": 4558,
+    "train_samples_per_second": 23.151,
+    "train_steps_per_second": 5.79
+}

eval_epoch_1_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 1.0,
+    "eval_accuracy": 0.5619722863264766,
+    "eval_loss": 2.4340596199035645,
+    "eval_runtime": 13.1565,
+    "eval_samples_per_second": 86.497,
+    "eval_steps_per_second": 10.869,
+    "perplexity": 11.405088550670825
+}

special_tokens_map.json

@@ -12,5 +12,6 @@
     "normalized": false,
     "rstrip": false,
     "single_word": false
-  }
+  },
+  "pad_token": "<|end_of_text|>"
 }

tokenizer_config.json

@@ -2058,5 +2058,6 @@
     "attention_mask"
   ],
   "model_max_length": 131072,
+  "pad_token": "<|end_of_text|>",
   "tokenizer_class": "PreTrainedTokenizerFast"
 }

train_epoch_1_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 1.0,
+    "total_flos": 1.3626163133939712e+16,
+    "train_loss": 2.4788927044784814,
+    "train_runtime": 196.8793,
+    "train_samples": 4558,
+    "train_samples_per_second": 23.151,
+    "train_steps_per_second": 5.79
+}

trainer_state.json

@@ -0,0 +1,66 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 1140,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.43859649122807015,
+      "grad_norm": 17.125,
+      "learning_rate": 5.622807017543859e-07,
+      "loss": 2.5341,
+      "step": 500
+    },
+    {
+      "epoch": 0.8771929824561403,
+      "grad_norm": 17.75,
+      "learning_rate": 1.2368421052631579e-07,
+      "loss": 2.4372,
+      "step": 1000
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.5619722863264766,
+      "eval_loss": 2.4340596199035645,
+      "eval_runtime": 13.1971,
+      "eval_samples_per_second": 86.231,
+      "eval_steps_per_second": 10.836,
+      "step": 1140
+    },
+    {
+      "epoch": 1.0,
+      "step": 1140,
+      "total_flos": 1.3626163133939712e+16,
+      "train_loss": 2.4788927044784814,
+      "train_runtime": 196.8793,
+      "train_samples_per_second": 23.151,
+      "train_steps_per_second": 5.79
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1140,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "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": 1.3626163133939712e+16,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}