Upload folder using huggingface_hub

config.json

@@ -0,0 +1,59 @@
+{
+  "_name_or_path": "/home/administrator/Desktop/ok/longformer_samsum_finetuned_2/checkpoint-500",
+  "activation_dropout": 0.0,
+  "activation_function": "gelu",
+  "architectures": [
+    "LEDForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "attention_window": [
+    1024,
+    1024,
+    1024,
+    1024,
+    1024,
+    1024
+  ],
+  "bos_token_id": 0,
+  "classif_dropout": 0.0,
+  "classifier_dropout": 0.0,
+  "d_model": 768,
+  "decoder_attention_heads": 12,
+  "decoder_ffn_dim": 3072,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 6,
+  "decoder_start_token_id": 2,
+  "dropout": 0.1,
+  "early_stopping": true,
+  "encoder_attention_heads": 12,
+  "encoder_ffn_dim": 3072,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 6,
+  "eos_token_id": 2,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
+  },
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "length_penalty": 2.0,
+  "max_decoder_position_embeddings": 1024,
+  "max_encoder_position_embeddings": 16384,
+  "max_length": 1024,
+  "min_length": 100,
+  "model_type": "led",
+  "no_repeat_ngram_size": 3,
+  "num_beams": 2,
+  "num_hidden_layers": 6,
+  "pad_token_id": 1,
+  "torch_dtype": "float32",
+  "transformers_version": "4.28.1",
+  "use_cache": false,
+  "vocab_size": 50265
+}

generation_config.json

@@ -0,0 +1,8 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "decoder_start_token_id": 2,
+  "eos_token_id": 2,
+  "pad_token_id": 1,
+  "transformers_version": "4.28.1"
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30a91eb8c3f9ac24b175aaa00dba798e5ddde6f9fcb2b62484cadaec42df5ac1
+size 1294929093

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06a4a60f369f8d3f87a9fc0e1d2fb6e623634535017c1b9a7c2a2aca1dcd9269
+size 647680813

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f361fa170bf2792fbf333010579441581d7dbfc62959abf780784542c844c94
+size 14575

scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1e6f026d9ebc9fb96f5a2dfff631838a77732df31ff67f35f225c89aab64365
+size 557

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30d6d0a2b1c477f98baeea1e0b63b2d20f0fa66cf761e14452e66ce787a4422b
+size 627

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": true,
+    "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 +1,64 @@
+{
+  "add_prefix_space": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "errors": "replace",
+  "mask_token": {
+    "__type": "AddedToken",
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "model_max_length": 16384,
+  "pad_token": {
+    "__type": "AddedToken",
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "tokenizer_class": "LEDTokenizer",
+  "trim_offsets": true,
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

trainer_state.json

@@ -0,0 +1,114 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.977464023893565,
+  "global_step": 3600,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.14,
+      "learning_rate": 4.325278305729025e-05,
+      "loss": 0.5728,
+      "step": 500
+    },
+    {
+      "epoch": 0.14,
+      "eval_loss": 1.762572169303894,
+      "eval_runtime": 157.3465,
+      "eval_samples_per_second": 5.199,
+      "eval_steps_per_second": 5.199,
+      "step": 500
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 3.6464838446918274e-05,
+      "loss": 1.1434,
+      "step": 1000
+    },
+    {
+      "epoch": 0.27,
+      "eval_loss": 1.572243571281433,
+      "eval_runtime": 167.1313,
+      "eval_samples_per_second": 4.894,
+      "eval_steps_per_second": 4.894,
+      "step": 1000
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 2.969046972576704e-05,
+      "loss": 1.1231,
+      "step": 1500
+    },
+    {
+      "epoch": 0.41,
+      "eval_loss": 1.5563775300979614,
+      "eval_runtime": 168.524,
+      "eval_samples_per_second": 4.854,
+      "eval_steps_per_second": 4.854,
+      "step": 1500
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 2.290252511539506e-05,
+      "loss": 1.0814,
+      "step": 2000
+    },
+    {
+      "epoch": 0.54,
+      "eval_loss": 1.530091643333435,
+      "eval_runtime": 160.6191,
+      "eval_samples_per_second": 5.093,
+      "eval_steps_per_second": 5.093,
+      "step": 2000
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 1.611458050502308e-05,
+      "loss": 1.0611,
+      "step": 2500
+    },
+    {
+      "epoch": 0.68,
+      "eval_loss": 1.4997280836105347,
+      "eval_runtime": 164.048,
+      "eval_samples_per_second": 4.986,
+      "eval_steps_per_second": 4.986,
+      "step": 2500
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 9.3266358946511e-06,
+      "loss": 1.0328,
+      "step": 3000
+    },
+    {
+      "epoch": 0.81,
+      "eval_loss": 1.4869426488876343,
+      "eval_runtime": 169.4258,
+      "eval_samples_per_second": 4.828,
+      "eval_steps_per_second": 4.828,
+      "step": 3000
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 2.5386912842791203e-06,
+      "loss": 1.0173,
+      "step": 3500
+    },
+    {
+      "epoch": 0.95,
+      "eval_loss": 1.4691505432128906,
+      "eval_runtime": 155.7447,
+      "eval_samples_per_second": 5.252,
+      "eval_steps_per_second": 5.252,
+      "step": 3500
+    }
+  ],
+  "max_steps": 3683,
+  "num_train_epochs": 1,
+  "total_flos": 7.77658992427008e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe251f1cb2bead961827f60a73a1e2ed9f64515792243f759985804dce8c85c9
+size 3771