Upload folder using huggingface_hub

checkpoint-6526/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-12,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 6,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.42.0.dev0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 52000
+}

checkpoint-6526/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:699e2857a249d183735c91434c26a89e899c6537c1756602d173ada0ad070df4
+size 334030264

checkpoint-6526/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b3a15595acad769c185b484e2a393eb3a9734a4fc251c35a714a3d9d641d726
+size 668124218

checkpoint-6526/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba43b3891ffb190e8ac90136a7d048386dde7c6a76038f368c400efe74d592f5
+size 14244

checkpoint-6526/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2686d253015eb54437a9b5574438e35e6fd1d2016ae5748f2a8af1e6d20f207
+size 1064

checkpoint-6526/trainer_state.json

@@ -0,0 +1,124 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 6526,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.07661661048115231,
+      "grad_norm": 2.862074851989746,
+      "learning_rate": 4.6169169475942386e-05,
+      "loss": 7.7328,
+      "step": 500
+    },
+    {
+      "epoch": 0.15323322096230463,
+      "grad_norm": 3.115309238433838,
+      "learning_rate": 4.233833895188477e-05,
+      "loss": 6.9672,
+      "step": 1000
+    },
+    {
+      "epoch": 0.22984983144345694,
+      "grad_norm": 4.209897041320801,
+      "learning_rate": 3.850750842782715e-05,
+      "loss": 6.6402,
+      "step": 1500
+    },
+    {
+      "epoch": 0.30646644192460926,
+      "grad_norm": 4.306308746337891,
+      "learning_rate": 3.467667790376954e-05,
+      "loss": 6.4321,
+      "step": 2000
+    },
+    {
+      "epoch": 0.38308305240576157,
+      "grad_norm": 3.8015663623809814,
+      "learning_rate": 3.0845847379711925e-05,
+      "loss": 6.2406,
+      "step": 2500
+    },
+    {
+      "epoch": 0.4596996628869139,
+      "grad_norm": 5.143409252166748,
+      "learning_rate": 2.7015016855654308e-05,
+      "loss": 6.0378,
+      "step": 3000
+    },
+    {
+      "epoch": 0.5363162733680662,
+      "grad_norm": 3.7252533435821533,
+      "learning_rate": 2.318418633159669e-05,
+      "loss": 5.8734,
+      "step": 3500
+    },
+    {
+      "epoch": 0.6129328838492185,
+      "grad_norm": 5.03999137878418,
+      "learning_rate": 1.9353355807539074e-05,
+      "loss": 5.7396,
+      "step": 4000
+    },
+    {
+      "epoch": 0.6895494943303708,
+      "grad_norm": 5.061025142669678,
+      "learning_rate": 1.552252528348146e-05,
+      "loss": 5.6239,
+      "step": 4500
+    },
+    {
+      "epoch": 0.7661661048115231,
+      "grad_norm": 4.358870506286621,
+      "learning_rate": 1.1691694759423844e-05,
+      "loss": 5.5265,
+      "step": 5000
+    },
+    {
+      "epoch": 0.8427827152926755,
+      "grad_norm": 5.286155700683594,
+      "learning_rate": 7.860864235366227e-06,
+      "loss": 5.518,
+      "step": 5500
+    },
+    {
+      "epoch": 0.9193993257738278,
+      "grad_norm": 4.038127422332764,
+      "learning_rate": 4.030033711308612e-06,
+      "loss": 5.4829,
+      "step": 6000
+    },
+    {
+      "epoch": 0.9960159362549801,
+      "grad_norm": 4.4984660148620605,
+      "learning_rate": 1.99203187250996e-07,
+      "loss": 5.4677,
+      "step": 6500
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 6526,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 10000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.3293972209436672e+16,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-6526/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f63bc6d2a7e05a2c895b5ade8d689c832ed422a33e49215d4c2e5ba479ab2168
+size 5112

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-12,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 6,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.42.0.dev0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 52000
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:699e2857a249d183735c91434c26a89e899c6537c1756602d173ada0ad070df4
+size 334030264

runs/Jun23_22-21-46_1e77b35561e4/events.out.tfevents.1719181320.1e77b35561e4.5988.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5ada368fd946ff8057437c57ae1bb01f45d56a2cd6a244ff7681e3c0ad05d77
+size 7853

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f63bc6d2a7e05a2c895b5ade8d689c832ed422a33e49215d4c2e5ba479ab2168
+size 5112