Initial commit

config.json

@@ -0,0 +1,58 @@
+{
+  "_name_or_path": "SnypzZz/Llama2-13b-Language-translate",
+  "_num_labels": 3,
+  "activation_dropout": 0.0,
+  "activation_function": "relu",
+  "add_bias_logits": false,
+  "add_final_layer_norm": true,
+  "architectures": [
+    "MBartForConditionalGeneration"
+  ],
+  "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,
+  "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
+  },
+  "max_length": 200,
+  "max_position_embeddings": 1024,
+  "model_type": "mbart",
+  "normalize_before": true,
+  "normalize_embedding": true,
+  "num_beams": 5,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "scale_embedding": true,
+  "static_position_embeddings": false,
+  "tokenizer_class": "MBart50Tokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.33.3",
+  "use_cache": true,
+  "vocab_size": 250054
+}

generation_config.json

@@ -0,0 +1,12 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "decoder_start_token_id": 2,
+  "early_stopping": true,
+  "eos_token_id": 2,
+  "forced_eos_token_id": 2,
+  "max_length": 200,
+  "num_beams": 5,
+  "pad_token_id": 1,
+  "transformers_version": "4.33.3"
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69d0022caf241d5c041bd9fb3bac3e353e97229b3e0fc52b71d100cdcee636c4
+size 4887473390

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de118d5016260363f089bdc5647b2c671987bd412ae71d8b7e6edd393a70a5c7
+size 2444694045

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f2774cf6f031b1ddcfb300bec118eb628a80b6ed8f7fdfdd68c38f06bfe9fc4
+size 14575

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d57d76696b84d28d29b54be2321d6b3c513a1fd7d4a2b2aadaf04e618e13bf2
+size 627

trainer_state.json

@@ -0,0 +1,103 @@
+{
+  "best_metric": 0.033053942024707794,
+  "best_model_checkpoint": "./results/checkpoint-3520",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 5280,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.28,
+      "learning_rate": 4.5265151515151514e-05,
+      "loss": 0.4808,
+      "step": 500
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 4.053030303030303e-05,
+      "loss": 0.0427,
+      "step": 1000
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 3.579545454545455e-05,
+      "loss": 0.0385,
+      "step": 1500
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.03568091243505478,
+      "eval_runtime": 219.2181,
+      "eval_samples_per_second": 51.843,
+      "eval_steps_per_second": 3.243,
+      "step": 1760
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 3.106060606060606e-05,
+      "loss": 0.0309,
+      "step": 2000
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 2.6325757575757575e-05,
+      "loss": 0.0265,
+      "step": 2500
+    },
+    {
+      "epoch": 1.7,
+      "learning_rate": 2.1590909090909093e-05,
+      "loss": 0.0246,
+      "step": 3000
+    },
+    {
+      "epoch": 1.99,
+      "learning_rate": 1.6856060606060605e-05,
+      "loss": 0.0244,
+      "step": 3500
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.033053942024707794,
+      "eval_runtime": 217.1125,
+      "eval_samples_per_second": 52.346,
+      "eval_steps_per_second": 3.275,
+      "step": 3520
+    },
+    {
+      "epoch": 2.27,
+      "learning_rate": 1.2121212121212122e-05,
+      "loss": 0.0145,
+      "step": 4000
+    },
+    {
+      "epoch": 2.56,
+      "learning_rate": 7.386363636363637e-06,
+      "loss": 0.014,
+      "step": 4500
+    },
+    {
+      "epoch": 2.84,
+      "learning_rate": 2.651515151515152e-06,
+      "loss": 0.0135,
+      "step": 5000
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.035611141473054886,
+      "eval_runtime": 217.9599,
+      "eval_samples_per_second": 52.143,
+      "eval_steps_per_second": 3.262,
+      "step": 5280
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 5280,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 2.2877576286437376e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:003a34c80ffed7165ec1d457aadb94f653ad14d1b28f1f40f5c79e0edb3daabe
+size 4027