Upload trainer_state.json with huggingface_hub

trainer_state.json

@@ -0,0 +1,150 @@
+{
+  "best_global_step": 1325,
+  "best_metric": 1.1546313762664795,
+  "best_model_checkpoint": "./mt5_base/indic_loss/hin/checkpoint-1325",
+  "epoch": 7.0,
+  "eval_steps": 500,
+  "global_step": 1855,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_bleu": 10.0106,
+      "eval_gen_len": 19.7482,
+      "eval_loss": 1.312620759010315,
+      "eval_runtime": 20.6438,
+      "eval_samples_per_second": 20.2,
+      "eval_steps_per_second": 2.567,
+      "eval_wer": 0.6794,
+      "step": 265
+    },
+    {
+      "epoch": 1.8867924528301887,
+      "grad_norm": 2.3564841747283936,
+      "learning_rate": 4.529245283018868e-05,
+      "loss": 1.6204,
+      "step": 500
+    },
+    {
+      "epoch": 2.0,
+      "eval_bleu": 11.0265,
+      "eval_gen_len": 19.9784,
+      "eval_loss": 1.295108675956726,
+      "eval_runtime": 19.5034,
+      "eval_samples_per_second": 21.381,
+      "eval_steps_per_second": 2.717,
+      "eval_wer": 0.6523,
+      "step": 530
+    },
+    {
+      "epoch": 3.0,
+      "eval_bleu": 11.233,
+      "eval_gen_len": 19.9928,
+      "eval_loss": 1.1867444515228271,
+      "eval_runtime": 19.4847,
+      "eval_samples_per_second": 21.401,
+      "eval_steps_per_second": 2.72,
+      "eval_wer": 0.6491,
+      "step": 795
+    },
+    {
+      "epoch": 3.7735849056603774,
+      "grad_norm": 0.7981056571006775,
+      "learning_rate": 4.057547169811321e-05,
+      "loss": 0.2735,
+      "step": 1000
+    },
+    {
+      "epoch": 4.0,
+      "eval_bleu": 11.316,
+      "eval_gen_len": 19.9928,
+      "eval_loss": 1.1922030448913574,
+      "eval_runtime": 20.0058,
+      "eval_samples_per_second": 20.844,
+      "eval_steps_per_second": 2.649,
+      "eval_wer": 0.6472,
+      "step": 1060
+    },
+    {
+      "epoch": 5.0,
+      "eval_bleu": 11.3642,
+      "eval_gen_len": 19.9928,
+      "eval_loss": 1.1546313762664795,
+      "eval_runtime": 19.4753,
+      "eval_samples_per_second": 21.412,
+      "eval_steps_per_second": 2.721,
+      "eval_wer": 0.6481,
+      "step": 1325
+    },
+    {
+      "epoch": 5.660377358490566,
+      "grad_norm": 0.6493868827819824,
+      "learning_rate": 3.585849056603774e-05,
+      "loss": 0.1986,
+      "step": 1500
+    },
+    {
+      "epoch": 6.0,
+      "eval_bleu": 11.3562,
+      "eval_gen_len": 19.9928,
+      "eval_loss": 1.1563888788223267,
+      "eval_runtime": 19.4557,
+      "eval_samples_per_second": 21.433,
+      "eval_steps_per_second": 2.724,
+      "eval_wer": 0.648,
+      "step": 1590
+    },
+    {
+      "epoch": 7.0,
+      "eval_bleu": 11.414,
+      "eval_gen_len": 19.9928,
+      "eval_loss": 1.1628665924072266,
+      "eval_runtime": 20.5046,
+      "eval_samples_per_second": 20.337,
+      "eval_steps_per_second": 2.585,
+      "eval_wer": 0.6482,
+      "step": 1855
+    },
+    {
+      "epoch": 7.0,
+      "step": 1855,
+      "total_flos": 2800128684367872.0,
+      "train_loss": 0.5960854666573661,
+      "train_runtime": 583.3703,
+      "train_samples_per_second": 72.681,
+      "train_steps_per_second": 9.085
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 5300,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 20,
+  "save_steps": 50000.0,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 2,
+        "early_stopping_threshold": 0.0
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 2
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2800128684367872.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}