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

config.json

@@ -0,0 +1,33 @@
+{
+  "_name_or_path": "bigscience/bloomz-560m",
+  "apply_residual_connection_post_layernorm": false,
+  "architectures": [
+    "BloomForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "attention_softmax_in_fp32": true,
+  "bias_dropout_fusion": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_dropout": 0.0,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "masked_softmax_fusion": true,
+  "model_type": "bloom",
+  "n_head": 16,
+  "n_inner": null,
+  "n_layer": 24,
+  "offset_alibi": 100,
+  "pad_token_id": 3,
+  "pretraining_tp": 1,
+  "seq_length": 2048,
+  "skip_bias_add": true,
+  "skip_bias_add_qkv": false,
+  "slow_but_exact": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.24.0",
+  "unk_token_id": 0,
+  "use_cache": false,
+  "vocab_size": 250880
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87974670cf57269a4f3045c001061d8ac43bd0f5e524ef5c8ea58fab4bdb6140
+size 4473887005

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76b54bd63bbbf37dba6755f66ac07436603ba4fd781c08607f5e8370fa656ca9
+size 2236955191

rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e383661921e7831f060f03f5d38f9d4ad9c73bce8cea9d114953228543d4fa9
+size 14503

rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e383661921e7831f060f03f5d38f9d4ad9c73bce8cea9d114953228543d4fa9
+size 14503

rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e383661921e7831f060f03f5d38f9d4ad9c73bce8cea9d114953228543d4fa9
+size 14503

rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e383661921e7831f060f03f5d38f9d4ad9c73bce8cea9d114953228543d4fa9
+size 14503

scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c1d33dc95e779d3b74ba8c487374b98679f5268cf1a246a10c7de96feaf43e7
+size 559

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:408e9bf4f42231f0886ca1c161b762fa989b5a039f745dfb11b99483aa3d48cc
+size 623

special_tokens_map.json

@@ -0,0 +1,5 @@
+{
+  "eos_token": "</s>",
+  "pad_token": "<pad>",
+  "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 sha256:99cc999819aaabf74898a252863b10d86fbcd86e8b3f65c118ff334ff85c5ea5
+size 16315121

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 +1,188 @@
+{
+  "best_metric": 3.0374205112457275,
+  "best_model_checkpoint": "../Modelos/bloomz_AEx_SQAC_SQuAD/checkpoint-1000",
+  "epoch": 0.898069151324652,
+  "global_step": 1000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.04,
+      "eval_loss": 5.792993068695068,
+      "eval_runtime": 79.9398,
+      "eval_samples_per_second": 103.741,
+      "eval_steps_per_second": 25.945,
+      "step": 50
+    },
+    {
+      "epoch": 0.09,
+      "eval_loss": 4.746491432189941,
+      "eval_runtime": 79.9383,
+      "eval_samples_per_second": 103.743,
+      "eval_steps_per_second": 25.945,
+      "step": 100
+    },
+    {
+      "epoch": 0.13,
+      "eval_loss": 4.1346588134765625,
+      "eval_runtime": 79.9476,
+      "eval_samples_per_second": 103.73,
+      "eval_steps_per_second": 25.942,
+      "step": 150
+    },
+    {
+      "epoch": 0.18,
+      "eval_loss": 3.8906848430633545,
+      "eval_runtime": 79.9385,
+      "eval_samples_per_second": 103.742,
+      "eval_steps_per_second": 25.945,
+      "step": 200
+    },
+    {
+      "epoch": 0.22,
+      "eval_loss": 3.7085936069488525,
+      "eval_runtime": 79.9395,
+      "eval_samples_per_second": 103.741,
+      "eval_steps_per_second": 25.945,
+      "step": 250
+    },
+    {
+      "epoch": 0.27,
+      "eval_loss": 3.563627004623413,
+      "eval_runtime": 79.9406,
+      "eval_samples_per_second": 103.74,
+      "eval_steps_per_second": 25.944,
+      "step": 300
+    },
+    {
+      "epoch": 0.31,
+      "eval_loss": 3.4549553394317627,
+      "eval_runtime": 79.9322,
+      "eval_samples_per_second": 103.75,
+      "eval_steps_per_second": 25.947,
+      "step": 350
+    },
+    {
+      "epoch": 0.36,
+      "eval_loss": 3.3643569946289062,
+      "eval_runtime": 79.932,
+      "eval_samples_per_second": 103.751,
+      "eval_steps_per_second": 25.947,
+      "step": 400
+    },
+    {
+      "epoch": 0.4,
+      "eval_loss": 3.3192312717437744,
+      "eval_runtime": 79.9445,
+      "eval_samples_per_second": 103.734,
+      "eval_steps_per_second": 25.943,
+      "step": 450
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 4.2572626534890685e-05,
+      "loss": 4.1989,
+      "step": 500
+    },
+    {
+      "epoch": 0.45,
+      "eval_loss": 3.2668206691741943,
+      "eval_runtime": 79.9572,
+      "eval_samples_per_second": 103.718,
+      "eval_steps_per_second": 25.939,
+      "step": 500
+    },
+    {
+      "epoch": 0.49,
+      "eval_loss": 3.2073845863342285,
+      "eval_runtime": 79.9534,
+      "eval_samples_per_second": 103.723,
+      "eval_steps_per_second": 25.94,
+      "step": 550
+    },
+    {
+      "epoch": 0.54,
+      "eval_loss": 3.1692163944244385,
+      "eval_runtime": 79.94,
+      "eval_samples_per_second": 103.74,
+      "eval_steps_per_second": 25.944,
+      "step": 600
+    },
+    {
+      "epoch": 0.58,
+      "eval_loss": 3.1374781131744385,
+      "eval_runtime": 79.9406,
+      "eval_samples_per_second": 103.74,
+      "eval_steps_per_second": 25.944,
+      "step": 650
+    },
+    {
+      "epoch": 0.63,
+      "eval_loss": 3.1055877208709717,
+      "eval_runtime": 79.926,
+      "eval_samples_per_second": 103.758,
+      "eval_steps_per_second": 25.949,
+      "step": 700
+    },
+    {
+      "epoch": 0.67,
+      "eval_loss": 3.0914928913116455,
+      "eval_runtime": 79.9363,
+      "eval_samples_per_second": 103.745,
+      "eval_steps_per_second": 25.946,
+      "step": 750
+    },
+    {
+      "epoch": 0.72,
+      "eval_loss": 3.0823092460632324,
+      "eval_runtime": 79.9387,
+      "eval_samples_per_second": 103.742,
+      "eval_steps_per_second": 25.945,
+      "step": 800
+    },
+    {
+      "epoch": 0.76,
+      "eval_loss": 3.05977463722229,
+      "eval_runtime": 79.9397,
+      "eval_samples_per_second": 103.741,
+      "eval_steps_per_second": 25.945,
+      "step": 850
+    },
+    {
+      "epoch": 0.81,
+      "eval_loss": 3.0491394996643066,
+      "eval_runtime": 79.9347,
+      "eval_samples_per_second": 103.747,
+      "eval_steps_per_second": 25.946,
+      "step": 900
+    },
+    {
+      "epoch": 0.85,
+      "eval_loss": 3.039747953414917,
+      "eval_runtime": 79.9452,
+      "eval_samples_per_second": 103.734,
+      "eval_steps_per_second": 25.943,
+      "step": 950
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 3.508535489667565e-05,
+      "loss": 2.7285,
+      "step": 1000
+    },
+    {
+      "epoch": 0.9,
+      "eval_loss": 3.0374205112457275,
+      "eval_runtime": 79.9218,
+      "eval_samples_per_second": 103.764,
+      "eval_steps_per_second": 25.95,
+      "step": 1000
+    }
+  ],
+  "max_steps": 3339,
+  "num_train_epochs": 3,
+  "total_flos": 4.618973186359296e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ea004d57a203b0f803bfc67eaaed00c2c77fcc2fca3a3f0d8c0ca8c3cee9490
+size 3375