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 sha256:9c172f1f2a169e05a9dcc2caa4be4d611ca8b4899440c9d0d0874182ede73750
+size 4112993

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a55adc479ac0c24c1c7efea54fc7408ec235c3d384da5c04f15c89d94230358
+size 2329700173

rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6869f5284e10a6c59fc199e4e2d68d78430c207924824f5e4e8524233fe3ae08
+size 14503

rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf5987826b0c1217e52e3cdeb488b37e5ee19886a3746f797b0b2411c7527850
+size 14503

rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15ed61387946d0e39c8bc40a5aef6ebff7ceeb8193cc990259c748b467f5cc4f
+size 14503

rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:669a4c5c7b800878497363f5ff946837d81e73118c917f5081d28fd6881ea5f2
+size 14503

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e776ba8847ec76d0ca532462cffc1f500ef4a9687512fab8db2a8efbaf2bb7f9
+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 +1,96 @@
+{
+  "best_metric": 0.7840239405632019,
+  "best_model_checkpoint": "../Modelos/mt0_QG_SQAC_17nov/checkpoint-150",
+  "epoch": 2.578723404255319,
+  "global_step": 150,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.26,
+      "eval_loss": 1.069141149520874,
+      "eval_runtime": 12.1119,
+      "eval_samples_per_second": 153.898,
+      "eval_steps_per_second": 4.871,
+      "step": 15
+    },
+    {
+      "epoch": 0.51,
+      "eval_loss": 0.8770672678947449,
+      "eval_runtime": 12.1543,
+      "eval_samples_per_second": 153.361,
+      "eval_steps_per_second": 4.854,
+      "step": 30
+    },
+    {
+      "epoch": 0.77,
+      "eval_loss": 0.8665398955345154,
+      "eval_runtime": 12.151,
+      "eval_samples_per_second": 153.404,
+      "eval_steps_per_second": 4.856,
+      "step": 45
+    },
+    {
+      "epoch": 1.03,
+      "eval_loss": 0.8232021927833557,
+      "eval_runtime": 12.1575,
+      "eval_samples_per_second": 153.321,
+      "eval_steps_per_second": 4.853,
+      "step": 60
+    },
+    {
+      "epoch": 1.29,
+      "eval_loss": 0.8209449648857117,
+      "eval_runtime": 12.1503,
+      "eval_samples_per_second": 153.412,
+      "eval_steps_per_second": 4.856,
+      "step": 75
+    },
+    {
+      "epoch": 1.54,
+      "eval_loss": 0.8008891940116882,
+      "eval_runtime": 12.1479,
+      "eval_samples_per_second": 153.442,
+      "eval_steps_per_second": 4.857,
+      "step": 90
+    },
+    {
+      "epoch": 1.8,
+      "eval_loss": 0.8004308938980103,
+      "eval_runtime": 12.1495,
+      "eval_samples_per_second": 153.422,
+      "eval_steps_per_second": 4.856,
+      "step": 105
+    },
+    {
+      "epoch": 2.07,
+      "eval_loss": 0.7951616644859314,
+      "eval_runtime": 12.1513,
+      "eval_samples_per_second": 153.399,
+      "eval_steps_per_second": 4.855,
+      "step": 120
+    },
+    {
+      "epoch": 2.32,
+      "eval_loss": 0.8101497292518616,
+      "eval_runtime": 12.1552,
+      "eval_samples_per_second": 153.35,
+      "eval_steps_per_second": 4.854,
+      "step": 135
+    },
+    {
+      "epoch": 2.58,
+      "eval_loss": 0.7840239405632019,
+      "eval_runtime": 12.152,
+      "eval_samples_per_second": 153.39,
+      "eval_steps_per_second": 4.855,
+      "step": 150
+    }
+  ],
+  "max_steps": 174,
+  "num_train_epochs": 3,
+  "total_flos": 4.649421175888282e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3115fa9a909001823c2cd3de68066cba8c53f59eeb3cf52c54541844fe61191
+size 3503