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 sha256:1dba951fc12d4d59b0513ec5abb87517761dfa87ac24cea048a0f69dcc68f0f1
+size 4473887005

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3951518c27b8f27b152c7a56771d616456bc79239908f658e3fdb23fc79e0870
+size 2236955191

rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62d41fa6662602ededfc4b7984d27ddf54962906079944f4a744895f11dfd2c3
+size 14503

rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62d41fa6662602ededfc4b7984d27ddf54962906079944f4a744895f11dfd2c3
+size 14503

rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62d41fa6662602ededfc4b7984d27ddf54962906079944f4a744895f11dfd2c3
+size 14503

rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62d41fa6662602ededfc4b7984d27ddf54962906079944f4a744895f11dfd2c3
+size 14503

scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee93335b2ab1a563d177a39e51162be7dd783cda93f834403e8af2fcc64cec35
+size 559

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c05906570ee58416eabc79277782f85527fdcbfa82bc26a295aacc1c286c5881
+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 +1,80 @@
+{
+  "best_metric": 3.9313628673553467,
+  "best_model_checkpoint": "../Modelos/bloomz_AEx_SQAC 16-11-22_14:21:54/checkpoint-300",
+  "epoch": 2.1502347417840375,
+  "global_step": 400,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.27,
+      "eval_loss": 6.168238639831543,
+      "eval_runtime": 17.1513,
+      "eval_samples_per_second": 85.883,
+      "eval_steps_per_second": 21.514,
+      "step": 50
+    },
+    {
+      "epoch": 0.54,
+      "eval_loss": 4.979750633239746,
+      "eval_runtime": 17.1449,
+      "eval_samples_per_second": 85.915,
+      "eval_steps_per_second": 21.522,
+      "step": 100
+    },
+    {
+      "epoch": 0.8,
+      "eval_loss": 4.440313816070557,
+      "eval_runtime": 17.1447,
+      "eval_samples_per_second": 85.916,
+      "eval_steps_per_second": 21.523,
+      "step": 150
+    },
+    {
+      "epoch": 1.08,
+      "eval_loss": 4.214320659637451,
+      "eval_runtime": 17.1475,
+      "eval_samples_per_second": 85.902,
+      "eval_steps_per_second": 21.519,
+      "step": 200
+    },
+    {
+      "epoch": 1.34,
+      "eval_loss": 4.072711944580078,
+      "eval_runtime": 17.1405,
+      "eval_samples_per_second": 85.937,
+      "eval_steps_per_second": 21.528,
+      "step": 250
+    },
+    {
+      "epoch": 1.61,
+      "eval_loss": 3.9313628673553467,
+      "eval_runtime": 17.1398,
+      "eval_samples_per_second": 85.94,
+      "eval_steps_per_second": 21.529,
+      "step": 300
+    },
+    {
+      "epoch": 1.88,
+      "eval_loss": 3.891813039779663,
+      "eval_runtime": 17.1459,
+      "eval_samples_per_second": 85.91,
+      "eval_steps_per_second": 21.521,
+      "step": 350
+    },
+    {
+      "epoch": 2.15,
+      "eval_loss": 3.935412883758545,
+      "eval_runtime": 17.1444,
+      "eval_samples_per_second": 85.917,
+      "eval_steps_per_second": 21.523,
+      "step": 400
+    }
+  ],
+  "max_steps": 558,
+  "num_train_epochs": 3,
+  "total_flos": 2.3467769487949824e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85a5fe1ff5a4cb0750f685136f3df86de8aa5728a86ae1d262109be55faa612b
+size 3439