Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<sep>": 250100
+}

config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "bigscience/mt0-base",
+  "architectures": [
+    "MT5ForConditionalGeneration"
+  ],
+  "d_ff": 2048,
+  "d_kv": 64,
+  "d_model": 768,
+  "decoder_start_token_id": 0,
+  "dense_act_fn": "gelu_new",
+  "dropout_rate": 0.1,
+  "eos_token_id": 1,
+  "feed_forward_proj": "gated-gelu",
+  "initializer_factor": 1.0,
+  "is_encoder_decoder": true,
+  "is_gated_act": true,
+  "layer_norm_epsilon": 1e-06,
+  "model_type": "mt5",
+  "num_decoder_layers": 12,
+  "num_heads": 12,
+  "num_layers": 12,
+  "output_past": true,
+  "pad_token_id": 0,
+  "relative_attention_max_distance": 128,
+  "relative_attention_num_buckets": 32,
+  "tie_word_embeddings": false,
+  "tokenizer_class": "T5Tokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.24.0",
+  "use_cache": false,
+  "vocab_size": 250112
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48b8c0e3a3d1e157a9d3ad6f4e8c6830c5b19c830a9e05ad2e349a3610810c16
+size 4659378441

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9625cb2d3e183a7c78f1d84c179ecb55f84f9bfc610e9f5ede76a65e17128d5
+size 2329700173

rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ee15039ea3c72c225f3f620b828406a5783283a4c73379c522dde32c166179e
+size 14503

rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d2893e6da068fef79920b2e87c3f01ab40b2b47ade5bfe8d270da9ff587f4e8
+size 14503

rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:abef88134515bcef409206761be15eabd461235c7d38bc194302bdb28854d3cf
+size 14503

rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59df7ed425f92db68a3c7116b1532817d9356258f0d41a3679db0e6998bf5758
+size 14503

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5800d1faec836cfde6e3d86d2933a937c875d282a476e95377a60887e2881dd3
+size 623

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "eos_token": "</s>",
+  "pad_token": "<pad>",
+  "sep_token": "<sep>",
+  "unk_token": "<unk>"
+}

spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef78f86560d809067d12bac6c09f19a462cb3af3f54d2b8acbba26e1433125d6
+size 4309802

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5dd715f65199d1e4a01f2e94c627d658656290f80371a72e5a1c75d4f3c8ab50
+size 16315303

tokenizer_config.json

@@ -0,0 +1,11 @@
+{
+  "additional_special_tokens": null,
+  "eos_token": "</s>",
+  "extra_ids": 0,
+  "name_or_path": "bigscience/mt0-base",
+  "pad_token": "<pad>",
+  "sp_model_kwargs": {},
+  "special_tokens_map_file": "/home/patrick/.cache/torch/transformers/685ac0ca8568ec593a48b61b0a3c272beee9bc194a3c7241d15dcadb5f875e53.f76030f3ec1b96a8199b2593390c610e76ca8028ef3d24680000619ffb646276",
+  "tokenizer_class": "T5Tokenizer",
+  "unk_token": "<unk>"
+}

trainer_state.json

@@ -0,0 +1,102 @@
+{
+  "best_metric": 0.7455043196678162,
+  "best_model_checkpoint": "../Modelos/mt0_AEx_SQAC_SQuAD/checkpoint-500",
+  "epoch": 1.7974854063762908,
+  "global_step": 500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.18,
+      "eval_loss": 1.7613606452941895,
+      "eval_runtime": 39.5031,
+      "eval_samples_per_second": 209.933,
+      "eval_steps_per_second": 13.138,
+      "step": 50
+    },
+    {
+      "epoch": 0.36,
+      "eval_loss": 0.9238205552101135,
+      "eval_runtime": 39.5073,
+      "eval_samples_per_second": 209.91,
+      "eval_steps_per_second": 13.137,
+      "step": 100
+    },
+    {
+      "epoch": 0.54,
+      "eval_loss": 0.8525803089141846,
+      "eval_runtime": 39.507,
+      "eval_samples_per_second": 209.912,
+      "eval_steps_per_second": 13.137,
+      "step": 150
+    },
+    {
+      "epoch": 0.72,
+      "eval_loss": 0.8049641251564026,
+      "eval_runtime": 39.5045,
+      "eval_samples_per_second": 209.925,
+      "eval_steps_per_second": 13.138,
+      "step": 200
+    },
+    {
+      "epoch": 0.9,
+      "eval_loss": 0.7979457974433899,
+      "eval_runtime": 39.5156,
+      "eval_samples_per_second": 209.866,
+      "eval_steps_per_second": 13.134,
+      "step": 250
+    },
+    {
+      "epoch": 1.08,
+      "eval_loss": 0.7720322012901306,
+      "eval_runtime": 39.5061,
+      "eval_samples_per_second": 209.917,
+      "eval_steps_per_second": 13.137,
+      "step": 300
+    },
+    {
+      "epoch": 1.26,
+      "eval_loss": 0.7646297812461853,
+      "eval_runtime": 39.5051,
+      "eval_samples_per_second": 209.922,
+      "eval_steps_per_second": 13.138,
+      "step": 350
+    },
+    {
+      "epoch": 1.44,
+      "eval_loss": 0.7602328658103943,
+      "eval_runtime": 39.5113,
+      "eval_samples_per_second": 209.889,
+      "eval_steps_per_second": 13.135,
+      "step": 400
+    },
+    {
+      "epoch": 1.62,
+      "eval_loss": 0.7440393567085266,
+      "eval_runtime": 39.4994,
+      "eval_samples_per_second": 209.953,
+      "eval_steps_per_second": 13.139,
+      "step": 450
+    },
+    {
+      "epoch": 1.8,
+      "learning_rate": 2.0023980815347724e-05,
+      "loss": 1.1345,
+      "step": 500
+    },
+    {
+      "epoch": 1.8,
+      "eval_loss": 0.7455043196678162,
+      "eval_runtime": 39.4715,
+      "eval_samples_per_second": 210.101,
+      "eval_steps_per_second": 13.149,
+      "step": 500
+    }
+  ],
+  "max_steps": 834,
+  "num_train_epochs": 3,
+  "total_flos": 1.1026777058679194e+17,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2ff9bb33751c9b8d47393b680ffee8acec8cc5bf883492aac09dfbcb82215db
+size 3503