feat: Init

Signed-off-by: Diwank Singh Tomer <[email protected]>

config.json

@@ -0,0 +1,70 @@
+{
+  "_name_or_path": "facebook/bart-large-cnn",
+  "_num_labels": 3,
+  "activation_dropout": 0.0,
+  "activation_function": "gelu",
+  "add_final_layer_norm": false,
+  "architectures": [
+    "BartForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "classif_dropout": 0.0,
+  "classifier_dropout": 0.0,
+  "d_model": 1024,
+  "decoder_attention_heads": 16,
+  "decoder_ffn_dim": 4096,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 12,
+  "decoder_start_token_id": 2,
+  "dropout": 0.1,
+  "early_stopping": true,
+  "encoder_attention_heads": 16,
+  "encoder_ffn_dim": 4096,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 12,
+  "eos_token_id": 2,
+  "force_bos_token_to_be_generated": true,
+  "forced_bos_token_id": 0,
+  "forced_eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "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_length": 142,
+  "max_position_embeddings": 1024,
+  "min_length": 56,
+  "model_type": "bart",
+  "no_repeat_ngram_size": 3,
+  "normalize_before": false,
+  "num_beams": 4,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "prefix": " ",
+  "scale_embedding": false,
+  "task_specific_params": {
+    "summarization": {
+      "early_stopping": true,
+      "length_penalty": 2.0,
+      "max_length": 142,
+      "min_length": 56,
+      "no_repeat_ngram_size": 3,
+      "num_beams": 4
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.18.0.dev0",
+  "use_cache": true,
+  "vocab_size": 50265
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b99f877b50285b19d08633eb2d34adf8993b659a79693d6971bfb6a4f3df28c
+size 3250615195

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc783d8b6076fbc086d91664e328ff8b3cd9e51dd7e19961a85d4cdfad80a018
+size 1625551553

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11d6d0afb630612f13df5b83654cfa466c14ef765a035e331c003faa27a0dab0
+size 13483

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:257cb28d0268f763ed33b6fdb435754811871e4ed6b6b5ad3aec68f14a4f99b1
+size 623

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1 @@
+{"errors": "replace", "bos_token": "<s>", "eos_token": "</s>", "sep_token": "</s>", "cls_token": "<s>", "unk_token": "<unk>", "pad_token": "<pad>", "mask_token": "<mask>", "add_prefix_space": false, "trim_offsets": true, "model_max_length": 1024, "special_tokens_map_file": null, "name_or_path": "facebook/bart-large-cnn", "tokenizer_class": "BartTokenizer"}

trainer_state.json

@@ -0,0 +1,216 @@
+{
+  "best_metric": 82.213,
+  "best_model_checkpoint": "/uoa/home/s02sd1/Desktop/Project data/pytorch_project/facebook_26.04/checkpoint-5000",
+  "epoch": 95.23809523809524,
+  "global_step": 8000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 5.95,
+      "learning_rate": 2.8214285714285713e-06,
+      "loss": 0.1312,
+      "step": 500
+    },
+    {
+      "epoch": 11.9,
+      "learning_rate": 2.642857142857143e-06,
+      "loss": 0.046,
+      "step": 1000
+    },
+    {
+      "epoch": 11.9,
+      "eval_gen_len": 189.9754,
+      "eval_loss": 0.0635865107178688,
+      "eval_rouge1": 81.7351,
+      "eval_rouge2": 74.9502,
+      "eval_rougeL": 65.0568,
+      "eval_rougeLsum": 65.0619,
+      "eval_runtime": 20480.7032,
+      "eval_samples_per_second": 0.01,
+      "eval_steps_per_second": 0.001,
+      "step": 1000
+    },
+    {
+      "epoch": 17.86,
+      "learning_rate": 2.4642857142857143e-06,
+      "loss": 0.0227,
+      "step": 1500
+    },
+    {
+      "epoch": 23.81,
+      "learning_rate": 2.2857142857142856e-06,
+      "loss": 0.0126,
+      "step": 2000
+    },
+    {
+      "epoch": 23.81,
+      "eval_gen_len": 208.1773,
+      "eval_loss": 0.061119239777326584,
+      "eval_rouge1": 82.8965,
+      "eval_rouge2": 76.972,
+      "eval_rougeL": 70.043,
+      "eval_rougeLsum": 70.3743,
+      "eval_runtime": 2676.3375,
+      "eval_samples_per_second": 0.076,
+      "eval_steps_per_second": 0.004,
+      "step": 2000
+    },
+    {
+      "epoch": 29.76,
+      "learning_rate": 2.1071428571428572e-06,
+      "loss": 0.0072,
+      "step": 2500
+    },
+    {
+      "epoch": 35.71,
+      "learning_rate": 1.928571428571429e-06,
+      "loss": 0.0048,
+      "step": 3000
+    },
+    {
+      "epoch": 35.71,
+      "eval_gen_len": 206.1478,
+      "eval_loss": 0.07027211785316467,
+      "eval_rouge1": 84.3357,
+      "eval_rouge2": 79.2414,
+      "eval_rougeL": 72.9218,
+      "eval_rougeLsum": 73.2212,
+      "eval_runtime": 2713.1894,
+      "eval_samples_per_second": 0.075,
+      "eval_steps_per_second": 0.004,
+      "step": 3000
+    },
+    {
+      "epoch": 41.67,
+      "learning_rate": 1.7500000000000002e-06,
+      "loss": 0.0033,
+      "step": 3500
+    },
+    {
+      "epoch": 47.62,
+      "learning_rate": 1.5714285714285714e-06,
+      "loss": 0.0025,
+      "step": 4000
+    },
+    {
+      "epoch": 47.62,
+      "eval_gen_len": 210.4483,
+      "eval_loss": 0.06871643662452698,
+      "eval_rouge1": 83.8269,
+      "eval_rouge2": 78.3266,
+      "eval_rougeL": 72.7844,
+      "eval_rougeLsum": 73.1385,
+      "eval_runtime": 3070.1132,
+      "eval_samples_per_second": 0.066,
+      "eval_steps_per_second": 0.004,
+      "step": 4000
+    },
+    {
+      "epoch": 53.57,
+      "learning_rate": 1.392857142857143e-06,
+      "loss": 0.0018,
+      "step": 4500
+    },
+    {
+      "epoch": 59.52,
+      "learning_rate": 1.2142857142857144e-06,
+      "loss": 0.0016,
+      "step": 5000
+    },
+    {
+      "epoch": 59.52,
+      "eval_gen_len": 199.7389,
+      "eval_loss": 0.07927948236465454,
+      "eval_rouge1": 86.8825,
+      "eval_rouge2": 82.213,
+      "eval_rougeL": 77.2112,
+      "eval_rougeLsum": 77.4106,
+      "eval_runtime": 2247.4623,
+      "eval_samples_per_second": 0.09,
+      "eval_steps_per_second": 0.005,
+      "step": 5000
+    },
+    {
+      "epoch": 65.48,
+      "learning_rate": 1.0357142857142857e-06,
+      "loss": 0.0012,
+      "step": 5500
+    },
+    {
+      "epoch": 71.43,
+      "learning_rate": 8.571428571428571e-07,
+      "loss": 0.001,
+      "step": 6000
+    },
+    {
+      "epoch": 71.43,
+      "eval_gen_len": 202.665,
+      "eval_loss": 0.08206681907176971,
+      "eval_rouge1": 86.0452,
+      "eval_rouge2": 81.3296,
+      "eval_rougeL": 75.9829,
+      "eval_rougeLsum": 76.3571,
+      "eval_runtime": 2123.8856,
+      "eval_samples_per_second": 0.096,
+      "eval_steps_per_second": 0.005,
+      "step": 6000
+    },
+    {
+      "epoch": 77.38,
+      "learning_rate": 6.785714285714286e-07,
+      "loss": 0.0009,
+      "step": 6500
+    },
+    {
+      "epoch": 83.33,
+      "learning_rate": 5e-07,
+      "loss": 0.0008,
+      "step": 7000
+    },
+    {
+      "epoch": 83.33,
+      "eval_gen_len": 205.0788,
+      "eval_loss": 0.08218137919902802,
+      "eval_rouge1": 85.9623,
+      "eval_rouge2": 81.1543,
+      "eval_rougeL": 76.8811,
+      "eval_rougeLsum": 77.0526,
+      "eval_runtime": 2090.4257,
+      "eval_samples_per_second": 0.097,
+      "eval_steps_per_second": 0.005,
+      "step": 7000
+    },
+    {
+      "epoch": 89.29,
+      "learning_rate": 3.214285714285714e-07,
+      "loss": 0.0007,
+      "step": 7500
+    },
+    {
+      "epoch": 95.24,
+      "learning_rate": 1.4285714285714285e-07,
+      "loss": 0.0006,
+      "step": 8000
+    },
+    {
+      "epoch": 95.24,
+      "eval_gen_len": 206.7488,
+      "eval_loss": 0.07930376380681992,
+      "eval_rouge1": 85.5313,
+      "eval_rouge2": 80.6524,
+      "eval_rougeL": 75.6534,
+      "eval_rougeLsum": 75.8372,
+      "eval_runtime": 2147.6107,
+      "eval_samples_per_second": 0.095,
+      "eval_steps_per_second": 0.005,
+      "step": 8000
+    }
+  ],
+  "max_steps": 8400,
+  "num_train_epochs": 100,
+  "total_flos": 1.1606068796537242e+17,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5dd3a3c582e2661c8097601d327b6a2a922dc79e782e465fc807e71c62917b3f
+size 3247