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:cd25ae198fd503d1e9356efcbbbb7f88e49d82c0562f497fccd30a34dab29fc7
+size 4113249

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67a3f27c319d7ec03877937f09d08fd01719177bab377d20f3453f0e3a3c7fb3
+size 2329700173

rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63955a0ac4359a334e12adc10f842b5046064396ad558b4ec942c12c997ed56c
+size 14503

rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:caae46c356cf6ce26e6653b4ed99aa5f8328a84d872e40f2a8edeb8789a5ab7e
+size 14503

rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:316827f015de35908b2819f8f2c582571fde5305330233c3e5b02ff8c5f7a9af
+size 14503

rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aca604aab6271ec581512844ad01378311573bbcafdd60df05dec4e61e37ff4a
+size 14503

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25b8b5ece814b33028413f4cd3bf290b6c11cd986a2c5019cdcabc548ac2f291
+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 +1,220 @@
+{
+  "best_metric": 0.8784255981445312,
+  "best_model_checkpoint": "../Modelos/mt0_QG_SQAC_SQuAD 17-11-22_10:03:48/checkpoint-1200",
+  "epoch": 2.9976617303195634,
+  "global_step": 1200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.12,
+      "eval_loss": 1.0145061016082764,
+      "eval_runtime": 65.3999,
+      "eval_samples_per_second": 190.122,
+      "eval_steps_per_second": 11.896,
+      "step": 50
+    },
+    {
+      "epoch": 0.25,
+      "eval_loss": 0.9660477638244629,
+      "eval_runtime": 65.4002,
+      "eval_samples_per_second": 190.122,
+      "eval_steps_per_second": 11.896,
+      "step": 100
+    },
+    {
+      "epoch": 0.37,
+      "eval_loss": 0.9502729773521423,
+      "eval_runtime": 65.4029,
+      "eval_samples_per_second": 190.114,
+      "eval_steps_per_second": 11.895,
+      "step": 150
+    },
+    {
+      "epoch": 0.5,
+      "eval_loss": 0.9393932819366455,
+      "eval_runtime": 65.4026,
+      "eval_samples_per_second": 190.115,
+      "eval_steps_per_second": 11.896,
+      "step": 200
+    },
+    {
+      "epoch": 0.62,
+      "eval_loss": 0.9244149923324585,
+      "eval_runtime": 65.4024,
+      "eval_samples_per_second": 190.115,
+      "eval_steps_per_second": 11.896,
+      "step": 250
+    },
+    {
+      "epoch": 0.75,
+      "eval_loss": 0.912540078163147,
+      "eval_runtime": 65.4032,
+      "eval_samples_per_second": 190.113,
+      "eval_steps_per_second": 11.895,
+      "step": 300
+    },
+    {
+      "epoch": 0.87,
+      "eval_loss": 0.9208225607872009,
+      "eval_runtime": 65.4136,
+      "eval_samples_per_second": 190.083,
+      "eval_steps_per_second": 11.894,
+      "step": 350
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.907939076423645,
+      "eval_runtime": 65.3953,
+      "eval_samples_per_second": 190.136,
+      "eval_steps_per_second": 11.897,
+      "step": 400
+    },
+    {
+      "epoch": 1.12,
+      "eval_loss": 0.903082013130188,
+      "eval_runtime": 65.3937,
+      "eval_samples_per_second": 190.141,
+      "eval_steps_per_second": 11.897,
+      "step": 450
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 0.001,
+      "loss": 1.1491,
+      "step": 500
+    },
+    {
+      "epoch": 1.25,
+      "eval_loss": 0.8966090083122253,
+      "eval_runtime": 65.4073,
+      "eval_samples_per_second": 190.101,
+      "eval_steps_per_second": 11.895,
+      "step": 500
+    },
+    {
+      "epoch": 1.37,
+      "eval_loss": 0.8984885215759277,
+      "eval_runtime": 65.3845,
+      "eval_samples_per_second": 190.167,
+      "eval_steps_per_second": 11.899,
+      "step": 550
+    },
+    {
+      "epoch": 1.5,
+      "eval_loss": 0.8956364393234253,
+      "eval_runtime": 65.3948,
+      "eval_samples_per_second": 190.137,
+      "eval_steps_per_second": 11.897,
+      "step": 600
+    },
+    {
+      "epoch": 1.62,
+      "eval_loss": 0.8861657381057739,
+      "eval_runtime": 65.3936,
+      "eval_samples_per_second": 190.141,
+      "eval_steps_per_second": 11.897,
+      "step": 650
+    },
+    {
+      "epoch": 1.75,
+      "eval_loss": 0.8837835788726807,
+      "eval_runtime": 65.4055,
+      "eval_samples_per_second": 190.106,
+      "eval_steps_per_second": 11.895,
+      "step": 700
+    },
+    {
+      "epoch": 1.87,
+      "eval_loss": 0.875281035900116,
+      "eval_runtime": 65.3939,
+      "eval_samples_per_second": 190.14,
+      "eval_steps_per_second": 11.897,
+      "step": 750
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.889029860496521,
+      "eval_runtime": 65.4822,
+      "eval_samples_per_second": 189.884,
+      "eval_steps_per_second": 11.881,
+      "step": 800
+    },
+    {
+      "epoch": 2.12,
+      "eval_loss": 0.9000933766365051,
+      "eval_runtime": 65.3866,
+      "eval_samples_per_second": 190.161,
+      "eval_steps_per_second": 11.898,
+      "step": 850
+    },
+    {
+      "epoch": 2.25,
+      "eval_loss": 0.897091805934906,
+      "eval_runtime": 65.4252,
+      "eval_samples_per_second": 190.049,
+      "eval_steps_per_second": 11.891,
+      "step": 900
+    },
+    {
+      "epoch": 2.37,
+      "eval_loss": 0.8837863206863403,
+      "eval_runtime": 65.4877,
+      "eval_samples_per_second": 189.868,
+      "eval_steps_per_second": 11.88,
+      "step": 950
+    },
+    {
+      "epoch": 2.5,
+      "learning_rate": 0.001,
+      "loss": 0.7877,
+      "step": 1000
+    },
+    {
+      "epoch": 2.5,
+      "eval_loss": 0.8839919567108154,
+      "eval_runtime": 65.4142,
+      "eval_samples_per_second": 190.081,
+      "eval_steps_per_second": 11.893,
+      "step": 1000
+    },
+    {
+      "epoch": 2.62,
+      "eval_loss": 0.8844324350357056,
+      "eval_runtime": 65.4264,
+      "eval_samples_per_second": 190.046,
+      "eval_steps_per_second": 11.891,
+      "step": 1050
+    },
+    {
+      "epoch": 2.75,
+      "eval_loss": 0.8891133666038513,
+      "eval_runtime": 65.4136,
+      "eval_samples_per_second": 190.083,
+      "eval_steps_per_second": 11.894,
+      "step": 1100
+    },
+    {
+      "epoch": 2.87,
+      "eval_loss": 0.8817307949066162,
+      "eval_runtime": 65.4132,
+      "eval_samples_per_second": 190.084,
+      "eval_steps_per_second": 11.894,
+      "step": 1150
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.8784255981445312,
+      "eval_runtime": 65.4323,
+      "eval_samples_per_second": 190.029,
+      "eval_steps_per_second": 11.89,
+      "step": 1200
+    }
+  ],
+  "max_steps": 1200,
+  "num_train_epochs": 3,
+  "total_flos": 3.392579398501663e+17,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69c5068595dda35bafef084ebca25a3dd1673c204e12b4a88b480fc1872289a4
+size 3503