Upload folder using huggingface_hub

added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "<<ENT>>": 32000,
+  "<<SEP>>": 32001,
+  "[PAD]": 32002
+}

gliner_config.json

@@ -0,0 +1,132 @@
+{
+  "class_token_index": 32000,
+  "dropout": 0.4,
+  "embed_ent_token": false,
+  "encoder_config": {
+    "_name_or_path": "knowledgator/TinyLlama_v1.1-checkpint60000",
+    "add_cross_attention": false,
+    "architectures": [
+      "LlamaForCausalLM"
+    ],
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": 1,
+    "chunk_size_feed_forward": 0,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": 2,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "hidden_act": "silu",
+    "hidden_size": 2048,
+    "id2label": {
+      "0": "LABEL_0",
+      "1": "LABEL_1"
+    },
+    "initializer_range": 0.02,
+    "intermediate_size": 5632,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+      "LABEL_0": 0,
+      "LABEL_1": 1
+    },
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "max_position_embeddings": 2048,
+    "min_length": 0,
+    "model_type": "llama",
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 32,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_hidden_layers": 22,
+    "num_key_value_heads": 4,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_scores": false,
+    "pad_token_id": null,
+    "prefix": null,
+    "pretraining_tp": 1,
+    "problem_type": null,
+    "pruned_heads": {},
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "rms_norm_eps": 1e-05,
+    "rope_scaling": null,
+    "rope_theta": 10000.0,
+    "sep_token_id": null,
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": false,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": "float32",
+    "torchscript": false,
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "use_cache": true,
+    "vocab_size": 32003
+  },
+  "ent_token": "<<ENT>>",
+  "eval_every": 3000,
+  "fine_tune": true,
+  "freeze_token_rep": false,
+  "fuse_layers": false,
+  "has_rnn": true,
+  "hidden_size": 2048,
+  "label_smoothing": 0.0001,
+  "labels_encoder": null,
+  "labels_encoder_config": null,
+  "log_dir": "llama",
+  "loss_alpha": 0.8,
+  "loss_gamma": 2,
+  "loss_reduction": "sum",
+  "lr_encoder": "8e-6",
+  "lr_others": "5e-5",
+  "max_grad_norm": 10.0,
+  "max_len": 1024,
+  "max_neg_type_ratio": 1,
+  "max_types": 100,
+  "max_width": 12,
+  "model_name": "knowledgator/TinyLlama_v1.1-checkpint60000",
+  "model_type": "gliner",
+  "name": "span level gliner",
+  "num_post_fusion_layers": 3,
+  "num_steps": 9000,
+  "post_fusion_schema": "",
+  "prev_path": null,
+  "random_drop": true,
+  "root_dir": "gliner_logs",
+  "save_total_limit": 3,
+  "scheduler_type": "linear",
+  "sep_token": "<<SEP>>",
+  "shuffle_types": true,
+  "size_sup": -1,
+  "span_mode": "markerV0",
+  "subtoken_pooling": "first",
+  "train_batch_size": 2,
+  "train_data": "data.json",
+  "transformers_version": "4.40.2",
+  "val_data_dir": "none",
+  "vocab_size": 32002,
+  "warmup_ratio": 0.1,
+  "weight_decay_encoder": 0.01,
+  "weight_decay_other": 0.01,
+  "words_splitter_type": "whitespace"
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58de35c61d190b23ae1dee40ad5811300aabdab5adae0c0f9cc576b2cf3073f6
+size 4843077658

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,65 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32000": {
+      "content": "<<ENT>>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32001": {
+      "content": "<<SEP>>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32002": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

trainer_state.json

@@ -0,0 +1,113 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.056338028169014,
+  "eval_steps": 500,
+  "global_step": 1200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0880281690140845,
+      "grad_norm": 1525.1461181640625,
+      "learning_rate": 4.166666666666667e-06,
+      "loss": 134.6262,
+      "step": 100
+    },
+    {
+      "epoch": 0.176056338028169,
+      "grad_norm": 2871.249755859375,
+      "learning_rate": 4.62962962962963e-06,
+      "loss": 106.7172,
+      "step": 200
+    },
+    {
+      "epoch": 0.2640845070422535,
+      "grad_norm": 492.1271667480469,
+      "learning_rate": 4.166666666666667e-06,
+      "loss": 102.1769,
+      "step": 300
+    },
+    {
+      "epoch": 0.352112676056338,
+      "grad_norm": 1749.6070556640625,
+      "learning_rate": 3.7037037037037037e-06,
+      "loss": 106.4214,
+      "step": 400
+    },
+    {
+      "epoch": 0.44014084507042256,
+      "grad_norm": 853.5518798828125,
+      "learning_rate": 3.240740740740741e-06,
+      "loss": 92.0699,
+      "step": 500
+    },
+    {
+      "epoch": 0.528169014084507,
+      "grad_norm": 2185.8486328125,
+      "learning_rate": 2.7777777777777783e-06,
+      "loss": 90.0462,
+      "step": 600
+    },
+    {
+      "epoch": 0.6161971830985915,
+      "grad_norm": 411.7020263671875,
+      "learning_rate": 2.314814814814815e-06,
+      "loss": 93.0463,
+      "step": 700
+    },
+    {
+      "epoch": 0.704225352112676,
+      "grad_norm": 764.4384155273438,
+      "learning_rate": 1.8518518518518519e-06,
+      "loss": 86.6424,
+      "step": 800
+    },
+    {
+      "epoch": 0.7922535211267606,
+      "grad_norm": 3891.708251953125,
+      "learning_rate": 1.3888888888888892e-06,
+      "loss": 78.9075,
+      "step": 900
+    },
+    {
+      "epoch": 0.8802816901408451,
+      "grad_norm": 1514.9061279296875,
+      "learning_rate": 9.259259259259259e-07,
+      "loss": 79.3982,
+      "step": 1000
+    },
+    {
+      "epoch": 0.9683098591549296,
+      "grad_norm": 1521.738037109375,
+      "learning_rate": 4.6296296296296297e-07,
+      "loss": 82.1088,
+      "step": 1100
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 197.31683349609375,
+      "eval_runtime": 13.0547,
+      "eval_samples_per_second": 77.367,
+      "eval_steps_per_second": 9.728,
+      "step": 1136
+    },
+    {
+      "epoch": 1.056338028169014,
+      "grad_norm": 260.0885925292969,
+      "learning_rate": 0.0,
+      "loss": 75.2076,
+      "step": 1200
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 1200,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 600,
+  "total_flos": 0.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}