Upload folder using huggingface_hub

checkpoints/checkpoint-522/config.json

@@ -0,0 +1,26 @@
+{
+  "architectures": [
+    "RobertaForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.47.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 52000
+}

checkpoints/checkpoint-522/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d64f3897629e62c0dce831ad79624b018b42085b2a415aa7eaabc7ed5e2bc002
+size 504150808

checkpoints/checkpoint-522/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2eb1f38d3f56e901782eb9d22ae16ad232f7b4e2cee75a293057a3aa98267ffb
+size 1008422138

checkpoints/checkpoint-522/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:18236a7cd34ba3dbc0eea4f33905a3b22282c51b43315e421f7a7c4ef9f7a09d
+size 14244

checkpoints/checkpoint-522/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1994053220917f7e6d6befdf004f4d788fdd3b4921010d1cd29b1ed245442fbc
+size 1064

checkpoints/checkpoint-522/trainer_state.json

@@ -0,0 +1,113 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9988041138483617,
+  "eval_steps": 500,
+  "global_step": 522,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.09567089213106912,
+      "grad_norm": 117.45254516601562,
+      "learning_rate": 2.5e-06,
+      "loss": 31905.095,
+      "step": 50
+    },
+    {
+      "epoch": 0.19134178426213824,
+      "grad_norm": 71.91663360595703,
+      "learning_rate": 5e-06,
+      "loss": 2260638924.8,
+      "step": 100
+    },
+    {
+      "epoch": 0.2870126763932074,
+      "grad_norm": 56.18342590332031,
+      "learning_rate": 7.5e-06,
+      "loss": 63.7996,
+      "step": 150
+    },
+    {
+      "epoch": 0.3826835685242765,
+      "grad_norm": 47.14400100708008,
+      "learning_rate": 1e-05,
+      "loss": 12.4659,
+      "step": 200
+    },
+    {
+      "epoch": 0.4783544606553456,
+      "grad_norm": 57.82217025756836,
+      "learning_rate": 1.25e-05,
+      "loss": 9.1207,
+      "step": 250
+    },
+    {
+      "epoch": 0.5740253527864148,
+      "grad_norm": 36.61322021484375,
+      "learning_rate": 1.5e-05,
+      "loss": 8.5922,
+      "step": 300
+    },
+    {
+      "epoch": 0.6696962449174838,
+      "grad_norm": 30.304691314697266,
+      "learning_rate": 1.7500000000000002e-05,
+      "loss": 7.5559,
+      "step": 350
+    },
+    {
+      "epoch": 0.765367137048553,
+      "grad_norm": 24.35045051574707,
+      "learning_rate": 2e-05,
+      "loss": 7.2955,
+      "step": 400
+    },
+    {
+      "epoch": 0.8610380291796221,
+      "grad_norm": 24.114551544189453,
+      "learning_rate": 2.2499999999999998e-05,
+      "loss": 7.2298,
+      "step": 450
+    },
+    {
+      "epoch": 0.9567089213106912,
+      "grad_norm": 22.68138313293457,
+      "learning_rate": 2.5e-05,
+      "loss": 7.5636,
+      "step": 500
+    },
+    {
+      "epoch": 0.9988041138483617,
+      "eval_accuracy": 0.0,
+      "eval_loss": 10.570171356201172,
+      "eval_normalizer": 94012.0,
+      "eval_runtime": 76.7018,
+      "eval_samples_per_second": 696.945,
+      "eval_steps_per_second": 1.369,
+      "step": 522
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 5220,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "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": 4.187953816004198e+16,
+  "train_batch_size": 128,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoints/checkpoint-522/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b90d3ba093dd4889703652a506228505b353e93a789ce9359f2962066d1f58a8
+size 5432