Upload small model

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "./baseline_embedders/roberta-small",
+  "architectures": [
+    "Easyrec"
+  ],
+  "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": 6,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.1",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4327836fbecacda83d9a0d28b1e2c4c1e4ce17ca68f759a7a7d74f168306ac95
+size 485548602

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5fe499d15bcf54c7fad4133ea3a37d96f4be1c0817e01e7a4d9fbcaeac098c2e
+size 242766142

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5ef8982a9e4bbd0d4c210d862929057a001c901e8f1aa424b6676af40bdcd51
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bba7aac7585db212bd20d6513576c33c2fa2901cfca8bdb4fa61008fd2b3683a
+size 1064

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50264": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "padding_side": "right",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "unk_token": "<unk>"
+}

trainer_state.json

@@ -0,0 +1,229 @@
+{
+  "best_metric": 0.01243716301208047,
+  "best_model_checkpoint": "./checkpoints/easyrec-small",
+  "epoch": 1.733531451213472,
+  "eval_steps": 1000,
+  "global_step": 14000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.06191183754333829,
+      "grad_norm": 24.75,
+      "learning_rate": 4.896813604094436e-05,
+      "loss": 3.2576,
+      "step": 500
+    },
+    {
+      "epoch": 0.12382367508667658,
+      "grad_norm": 21.75,
+      "learning_rate": 4.793627208188873e-05,
+      "loss": 2.7834,
+      "step": 1000
+    },
+    {
+      "epoch": 0.18573551263001487,
+      "grad_norm": 21.25,
+      "learning_rate": 4.6904408122833086e-05,
+      "loss": 2.6955,
+      "step": 1500
+    },
+    {
+      "epoch": 0.24764735017335315,
+      "grad_norm": 24.375,
+      "learning_rate": 4.587254416377745e-05,
+      "loss": 2.5928,
+      "step": 2000
+    },
+    {
+      "epoch": 0.30955918771669144,
+      "grad_norm": 27.875,
+      "learning_rate": 4.484068020472182e-05,
+      "loss": 2.5848,
+      "step": 2500
+    },
+    {
+      "epoch": 0.37147102526002973,
+      "grad_norm": 21.625,
+      "learning_rate": 4.3808816245666175e-05,
+      "loss": 2.5582,
+      "step": 3000
+    },
+    {
+      "epoch": 0.433382862803368,
+      "grad_norm": 27.125,
+      "learning_rate": 4.2776952286610534e-05,
+      "loss": 2.5386,
+      "step": 3500
+    },
+    {
+      "epoch": 0.4952947003467063,
+      "grad_norm": 29.625,
+      "learning_rate": 4.17450883275549e-05,
+      "loss": 2.5143,
+      "step": 4000
+    },
+    {
+      "epoch": 0.5572065378900446,
+      "grad_norm": 20.0,
+      "learning_rate": 4.071322436849926e-05,
+      "loss": 2.5071,
+      "step": 4500
+    },
+    {
+      "epoch": 0.6191183754333829,
+      "grad_norm": 26.25,
+      "learning_rate": 3.968136040944362e-05,
+      "loss": 2.4754,
+      "step": 5000
+    },
+    {
+      "epoch": 0.6810302129767212,
+      "grad_norm": 23.0,
+      "learning_rate": 3.864949645038798e-05,
+      "loss": 2.4846,
+      "step": 5500
+    },
+    {
+      "epoch": 0.7429420505200595,
+      "grad_norm": 24.5,
+      "learning_rate": 3.761763249133234e-05,
+      "loss": 2.4806,
+      "step": 6000
+    },
+    {
+      "epoch": 0.8048538880633977,
+      "grad_norm": 24.125,
+      "learning_rate": 3.658576853227671e-05,
+      "loss": 2.4532,
+      "step": 6500
+    },
+    {
+      "epoch": 0.866765725606736,
+      "grad_norm": 24.25,
+      "learning_rate": 3.555390457322107e-05,
+      "loss": 2.4561,
+      "step": 7000
+    },
+    {
+      "epoch": 0.9286775631500743,
+      "grad_norm": 30.75,
+      "learning_rate": 3.452204061416543e-05,
+      "loss": 2.4607,
+      "step": 7500
+    },
+    {
+      "epoch": 0.9905894006934126,
+      "grad_norm": 26.375,
+      "learning_rate": 3.349017665510979e-05,
+      "loss": 2.4332,
+      "step": 8000
+    },
+    {
+      "epoch": 1.052501238236751,
+      "grad_norm": 29.375,
+      "learning_rate": 3.2458312696054156e-05,
+      "loss": 2.4328,
+      "step": 8500
+    },
+    {
+      "epoch": 1.1144130757800892,
+      "grad_norm": 25.0,
+      "learning_rate": 3.1426448736998515e-05,
+      "loss": 2.4362,
+      "step": 9000
+    },
+    {
+      "epoch": 1.1763249133234275,
+      "grad_norm": 24.25,
+      "learning_rate": 3.0394584777942874e-05,
+      "loss": 2.4432,
+      "step": 9500
+    },
+    {
+      "epoch": 1.2382367508667658,
+      "grad_norm": 34.75,
+      "learning_rate": 2.936272081888724e-05,
+      "loss": 2.427,
+      "step": 10000
+    },
+    {
+      "epoch": 1.300148588410104,
+      "grad_norm": 24.5,
+      "learning_rate": 2.83308568598316e-05,
+      "loss": 2.4219,
+      "step": 10500
+    },
+    {
+      "epoch": 1.3620604259534423,
+      "grad_norm": 35.0,
+      "learning_rate": 2.729899290077596e-05,
+      "loss": 2.4213,
+      "step": 11000
+    },
+    {
+      "epoch": 1.4239722634967806,
+      "grad_norm": 28.75,
+      "learning_rate": 2.6267128941720326e-05,
+      "loss": 2.424,
+      "step": 11500
+    },
+    {
+      "epoch": 1.485884101040119,
+      "grad_norm": 26.0,
+      "learning_rate": 2.5235264982664684e-05,
+      "loss": 2.4192,
+      "step": 12000
+    },
+    {
+      "epoch": 1.5477959385834572,
+      "grad_norm": 22.75,
+      "learning_rate": 2.420340102360905e-05,
+      "loss": 2.4032,
+      "step": 12500
+    },
+    {
+      "epoch": 1.6097077761267955,
+      "grad_norm": 35.0,
+      "learning_rate": 2.3171537064553412e-05,
+      "loss": 2.4317,
+      "step": 13000
+    },
+    {
+      "epoch": 1.6716196136701336,
+      "grad_norm": 20.875,
+      "learning_rate": 2.213967310549777e-05,
+      "loss": 2.432,
+      "step": 13500
+    },
+    {
+      "epoch": 1.733531451213472,
+      "grad_norm": 25.625,
+      "learning_rate": 2.1107809146442133e-05,
+      "loss": 2.4309,
+      "step": 14000
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 24228,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 1000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": false,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b7c6049104a9643616ea195fc3a09356190da167a8af115fe5300721aa5a3b35
+size 5240