Upload checkpoint-64/trainer_state.json with huggingface_hub

checkpoint-64/trainer_state.json

@@ -0,0 +1,75 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 64,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.15655577299412915,
+      "grad_norm": 8.653885841369629,
+      "learning_rate": 1.5789473684210526e-05,
+      "loss": 22.3789,
+      "step": 10
+    },
+    {
+      "epoch": 0.3131115459882583,
+      "grad_norm": 4.433068752288818,
+      "learning_rate": 2.9823529411764707e-05,
+      "loss": 20.8804,
+      "step": 20
+    },
+    {
+      "epoch": 0.46966731898238745,
+      "grad_norm": 4.180165767669678,
+      "learning_rate": 2.8058823529411766e-05,
+      "loss": 19.2313,
+      "step": 30
+    },
+    {
+      "epoch": 0.6262230919765166,
+      "grad_norm": 4.197498321533203,
+      "learning_rate": 2.6294117647058825e-05,
+      "loss": 18.3825,
+      "step": 40
+    },
+    {
+      "epoch": 0.7827788649706457,
+      "grad_norm": 4.2604594230651855,
+      "learning_rate": 2.452941176470588e-05,
+      "loss": 17.0293,
+      "step": 50
+    },
+    {
+      "epoch": 0.9393346379647749,
+      "grad_norm": 4.613166809082031,
+      "learning_rate": 2.276470588235294e-05,
+      "loss": 15.8548,
+      "step": 60
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 189,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 8582542317502464.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}