Upload 8 files

config.json

@@ -0,0 +1,62 @@
+{
+  "_name_or_path": "Helsinki-NLP/opus-mt-en-fr",
+  "_num_labels": 3,
+  "activation_dropout": 0.0,
+  "activation_function": "swish",
+  "add_bias_logits": false,
+  "add_final_layer_norm": false,
+  "architectures": [
+    "MarianMTModel"
+  ],
+  "attention_dropout": 0.0,
+  "bad_words_ids": [
+    [
+      59513
+    ]
+  ],
+  "bos_token_id": 0,
+  "classif_dropout": 0.0,
+  "classifier_dropout": 0.0,
+  "d_model": 512,
+  "decoder_attention_heads": 8,
+  "decoder_ffn_dim": 2048,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 6,
+  "decoder_start_token_id": 59513,
+  "decoder_vocab_size": 59514,
+  "dropout": 0.1,
+  "encoder_attention_heads": 8,
+  "encoder_ffn_dim": 2048,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 6,
+  "eos_token_id": 0,
+  "forced_eos_token_id": 0,
+  "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": 512,
+  "max_position_embeddings": 512,
+  "model_type": "marian",
+  "normalize_before": false,
+  "normalize_embedding": false,
+  "num_beams": 4,
+  "num_hidden_layers": 6,
+  "pad_token_id": 59513,
+  "scale_embedding": true,
+  "share_encoder_decoder_embeddings": true,
+  "static_position_embeddings": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.44.2",
+  "use_cache": true,
+  "vocab_size": 59514
+}

generation_config.json

@@ -0,0 +1,16 @@
+{
+  "bad_words_ids": [
+    [
+      59513
+    ]
+  ],
+  "bos_token_id": 0,
+  "decoder_start_token_id": 59513,
+  "eos_token_id": 0,
+  "forced_eos_token_id": 0,
+  "max_length": 512,
+  "num_beams": 4,
+  "pad_token_id": 59513,
+  "renormalize_logits": true,
+  "transformers_version": "4.44.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c734b2af7bca958db1ff34d7d595008ff39ac98570a9d719190ccfa5a8588ba
+size 298705768

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b535fb342f119ba74ea7d2ca522464dd9dd4bfc63d54c5e2a98366511251198
+size 597081786

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0cf6ce59a2584795ba1dd681747d50816e8ac993572caf2633b4c647a234280e
+size 13990

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:083bf6e13d95564aa9bd6e0608366f263df9af300b588ba059eaef8a5d6e417f
+size 1064

trainer_state.json

@@ -0,0 +1,94 @@
+{
+  "best_metric": 0.21195632219314575,
+  "best_model_checkpoint": "./home/dev15/web/Projects/monitoring_ai/resources/ai/Translation/results/checkpoint-1835",
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 1835,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.24953831732273102,
+      "eval_runtime": 127.7934,
+      "eval_samples_per_second": 11.472,
+      "eval_steps_per_second": 0.72,
+      "step": 367
+    },
+    {
+      "epoch": 1.3623978201634879,
+      "grad_norm": 0.6348655223846436,
+      "learning_rate": 4.3188010899182565e-05,
+      "loss": 0.2975,
+      "step": 500
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.22699691355228424,
+      "eval_runtime": 117.6853,
+      "eval_samples_per_second": 12.457,
+      "eval_steps_per_second": 0.782,
+      "step": 734
+    },
+    {
+      "epoch": 2.7247956403269757,
+      "grad_norm": 0.7137888073921204,
+      "learning_rate": 3.637602179836512e-05,
+      "loss": 0.1989,
+      "step": 1000
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.21688026189804077,
+      "eval_runtime": 115.8928,
+      "eval_samples_per_second": 12.65,
+      "eval_steps_per_second": 0.794,
+      "step": 1101
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.2130550593137741,
+      "eval_runtime": 127.3999,
+      "eval_samples_per_second": 11.507,
+      "eval_steps_per_second": 0.722,
+      "step": 1468
+    },
+    {
+      "epoch": 4.087193460490464,
+      "grad_norm": 0.601416826248169,
+      "learning_rate": 2.9564032697547683e-05,
+      "loss": 0.1552,
+      "step": 1500
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 0.21195632219314575,
+      "eval_runtime": 126.6476,
+      "eval_samples_per_second": 11.575,
+      "eval_steps_per_second": 0.726,
+      "step": 1835
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 3670,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 993561076039680.0,
+  "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 sha256:4dfc76596eef1a56c28bbc35d6c112798959838afd4f203236da1ffb0c93f2f0
+size 5240