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 sha256:1e8399a68c19342ff7b873d4fbf5e7d913f0942ff1ee69a5a950e1400df4397d
+size 4473887005

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc6b437d8d30f884c44c1ed5ac24696366bfcf817133e91e848fdf7c96482bf9
+size 2236955191

rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30864463f0e79bfa76eac32ba4b8b05ef3102cc20cc4d723bc93890205750132
+size 14503

rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30864463f0e79bfa76eac32ba4b8b05ef3102cc20cc4d723bc93890205750132
+size 14503

rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30864463f0e79bfa76eac32ba4b8b05ef3102cc20cc4d723bc93890205750132
+size 14503

rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30864463f0e79bfa76eac32ba4b8b05ef3102cc20cc4d723bc93890205750132
+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 sha256:0b4c7fed41a175170048a40e12d0a23c5b281883b1275a46ed963b55ff28543e
+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": 3.1014273166656494,
+  "best_model_checkpoint": "../Modelos/bloomz_AEx_SQUAD 16-11-22_14:58:43/checkpoint-1000",
+  "epoch": 1.0787327266599258,
+  "global_step": 1000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.05,
+      "eval_loss": 5.220151424407959,
+      "eval_runtime": 62.5146,
+      "eval_samples_per_second": 109.095,
+      "eval_steps_per_second": 27.274,
+      "step": 50
+    },
+    {
+      "epoch": 0.11,
+      "eval_loss": 4.333649158477783,
+      "eval_runtime": 62.5129,
+      "eval_samples_per_second": 109.097,
+      "eval_steps_per_second": 27.274,
+      "step": 100
+    },
+    {
+      "epoch": 0.16,
+      "eval_loss": 3.8862874507904053,
+      "eval_runtime": 62.5283,
+      "eval_samples_per_second": 109.071,
+      "eval_steps_per_second": 27.268,
+      "step": 150
+    },
+    {
+      "epoch": 0.22,
+      "eval_loss": 3.6269617080688477,
+      "eval_runtime": 62.5217,
+      "eval_samples_per_second": 109.082,
+      "eval_steps_per_second": 27.271,
+      "step": 200
+    },
+    {
+      "epoch": 0.27,
+      "eval_loss": 3.50032639503479,
+      "eval_runtime": 62.5086,
+      "eval_samples_per_second": 109.105,
+      "eval_steps_per_second": 27.276,
+      "step": 250
+    },
+    {
+      "epoch": 0.32,
+      "eval_loss": 3.3939645290374756,
+      "eval_runtime": 62.5177,
+      "eval_samples_per_second": 109.089,
+      "eval_steps_per_second": 27.272,
+      "step": 300
+    },
+    {
+      "epoch": 0.38,
+      "eval_loss": 3.3134140968322754,
+      "eval_runtime": 62.5154,
+      "eval_samples_per_second": 109.093,
+      "eval_steps_per_second": 27.273,
+      "step": 350
+    },
+    {
+      "epoch": 0.43,
+      "eval_loss": 3.228942394256592,
+      "eval_runtime": 62.5039,
+      "eval_samples_per_second": 109.113,
+      "eval_steps_per_second": 27.278,
+      "step": 400
+    },
+    {
+      "epoch": 0.49,
+      "eval_loss": 3.2036657333374023,
+      "eval_runtime": 62.5162,
+      "eval_samples_per_second": 109.092,
+      "eval_steps_per_second": 27.273,
+      "step": 450
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 4.108234448040274e-05,
+      "loss": 3.8523,
+      "step": 500
+    },
+    {
+      "epoch": 0.54,
+      "eval_loss": 3.1620962619781494,
+      "eval_runtime": 62.5012,
+      "eval_samples_per_second": 109.118,
+      "eval_steps_per_second": 27.279,
+      "step": 500
+    },
+    {
+      "epoch": 0.59,
+      "eval_loss": 3.128020763397217,
+      "eval_runtime": 62.5236,
+      "eval_samples_per_second": 109.079,
+      "eval_steps_per_second": 27.27,
+      "step": 550
+    },
+    {
+      "epoch": 0.65,
+      "eval_loss": 3.0899899005889893,
+      "eval_runtime": 62.5266,
+      "eval_samples_per_second": 109.074,
+      "eval_steps_per_second": 27.268,
+      "step": 600
+    },
+    {
+      "epoch": 0.7,
+      "eval_loss": 3.073817729949951,
+      "eval_runtime": 62.5093,
+      "eval_samples_per_second": 109.104,
+      "eval_steps_per_second": 27.276,
+      "step": 650
+    },
+    {
+      "epoch": 0.75,
+      "eval_loss": 3.0438177585601807,
+      "eval_runtime": 62.5327,
+      "eval_samples_per_second": 109.063,
+      "eval_steps_per_second": 27.266,
+      "step": 700
+    },
+    {
+      "epoch": 0.81,
+      "eval_loss": 3.0443129539489746,
+      "eval_runtime": 62.5242,
+      "eval_samples_per_second": 109.078,
+      "eval_steps_per_second": 27.269,
+      "step": 750
+    },
+    {
+      "epoch": 0.86,
+      "eval_loss": 3.044921636581421,
+      "eval_runtime": 62.5248,
+      "eval_samples_per_second": 109.077,
+      "eval_steps_per_second": 27.269,
+      "step": 800
+    },
+    {
+      "epoch": 0.92,
+      "eval_loss": 3.0547332763671875,
+      "eval_runtime": 62.5038,
+      "eval_samples_per_second": 109.113,
+      "eval_steps_per_second": 27.278,
+      "step": 850
+    },
+    {
+      "epoch": 0.97,
+      "eval_loss": 3.041879415512085,
+      "eval_runtime": 62.5198,
+      "eval_samples_per_second": 109.086,
+      "eval_steps_per_second": 27.271,
+      "step": 900
+    },
+    {
+      "epoch": 1.02,
+      "eval_loss": 3.113288640975952,
+      "eval_runtime": 62.5071,
+      "eval_samples_per_second": 109.108,
+      "eval_steps_per_second": 27.277,
+      "step": 950
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 3.209277238403452e-05,
+      "loss": 2.4796,
+      "step": 1000
+    },
+    {
+      "epoch": 1.08,
+      "eval_loss": 3.1014273166656494,
+      "eval_runtime": 62.5073,
+      "eval_samples_per_second": 109.107,
+      "eval_steps_per_second": 27.277,
+      "step": 1000
+    }
+  ],
+  "max_steps": 2781,
+  "num_train_epochs": 3,
+  "total_flos": 4.377761810061722e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54b2bd221b8cede013a4d6672239964e939ac947d7a33f881132187d00517906
+size 3439