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 sha256:1dcff6a3d630c4c13681a8b621ff6cee2bf76c2f19e48a912e2754c28d7297c0
+size 4473887005

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a591b4342d8ef8764f105e28eb2fbc8028082292784ff1509666ef67d0b0a827
+size 2236955191

rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f9733db299f85727654ada1e2241c2b4f64948c1fd868b50f2037c2a0349da2
+size 14503

rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f9733db299f85727654ada1e2241c2b4f64948c1fd868b50f2037c2a0349da2
+size 14503

rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f9733db299f85727654ada1e2241c2b4f64948c1fd868b50f2037c2a0349da2
+size 14503

rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f9733db299f85727654ada1e2241c2b4f64948c1fd868b50f2037c2a0349da2
+size 14503

scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b838f0433c07ccf0fd0a2f03fffb3f0170c8c2458131915e5a364a398fd1d5e5
+size 559

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a08b9adf106911fc2e182ae6656b8abce43d1afb99699b698f9062e19ba094b8
+size 623

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": "<pad>",
+  "sep_token": "<sep>",
+  "unk_token": "<unk>"
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cda9706ed3faa12fdd7096c3fde8757c8965743f9e9f51727beda97379faa25d
+size 14500625

tokenizer_config.json

@@ -0,0 +1,11 @@
+{
+  "add_prefix_space": false,
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "name_or_path": "bigscience/bloomz-560m",
+  "pad_token": "<pad>",
+  "padding_side": "left",
+  "special_tokens_map_file": null,
+  "tokenizer_class": "BloomTokenizer",
+  "unk_token": "<unk>"
+}

trainer_state.json

@@ -0,0 +1,102 @@
+{
+  "best_metric": 4.831347465515137,
+  "best_model_checkpoint": "../Modelos/bloomz_QG_SQAC/checkpoint-500",
+  "epoch": 2.1362064378824157,
+  "global_step": 500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.21,
+      "eval_loss": 2.7793376445770264,
+      "eval_runtime": 20.3109,
+      "eval_samples_per_second": 91.773,
+      "eval_steps_per_second": 22.943,
+      "step": 50
+    },
+    {
+      "epoch": 0.43,
+      "eval_loss": 2.788100004196167,
+      "eval_runtime": 20.2982,
+      "eval_samples_per_second": 91.831,
+      "eval_steps_per_second": 22.958,
+      "step": 100
+    },
+    {
+      "epoch": 0.64,
+      "eval_loss": 2.8279426097869873,
+      "eval_runtime": 20.2933,
+      "eval_samples_per_second": 91.853,
+      "eval_steps_per_second": 22.963,
+      "step": 150
+    },
+    {
+      "epoch": 0.85,
+      "eval_loss": 2.9520726203918457,
+      "eval_runtime": 20.2902,
+      "eval_samples_per_second": 91.867,
+      "eval_steps_per_second": 22.967,
+      "step": 200
+    },
+    {
+      "epoch": 1.07,
+      "eval_loss": 3.2829296588897705,
+      "eval_runtime": 20.2882,
+      "eval_samples_per_second": 91.876,
+      "eval_steps_per_second": 22.969,
+      "step": 250
+    },
+    {
+      "epoch": 1.28,
+      "eval_loss": 3.4829185009002686,
+      "eval_runtime": 20.2739,
+      "eval_samples_per_second": 91.941,
+      "eval_steps_per_second": 22.985,
+      "step": 300
+    },
+    {
+      "epoch": 1.49,
+      "eval_loss": 3.754530191421509,
+      "eval_runtime": 20.2683,
+      "eval_samples_per_second": 91.966,
+      "eval_steps_per_second": 22.992,
+      "step": 350
+    },
+    {
+      "epoch": 1.71,
+      "eval_loss": 4.005397319793701,
+      "eval_runtime": 20.2851,
+      "eval_samples_per_second": 91.89,
+      "eval_steps_per_second": 22.972,
+      "step": 400
+    },
+    {
+      "epoch": 1.92,
+      "eval_loss": 4.178648471832275,
+      "eval_runtime": 20.2975,
+      "eval_samples_per_second": 91.834,
+      "eval_steps_per_second": 22.958,
+      "step": 450
+    },
+    {
+      "epoch": 2.14,
+      "learning_rate": 1.4529914529914531e-05,
+      "loss": 1.5184,
+      "step": 500
+    },
+    {
+      "epoch": 2.14,
+      "eval_loss": 4.831347465515137,
+      "eval_runtime": 20.2914,
+      "eval_samples_per_second": 91.861,
+      "eval_steps_per_second": 22.965,
+      "step": 500
+    }
+  ],
+  "max_steps": 702,
+  "num_train_epochs": 3,
+  "total_flos": 2.725676440354816e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9444ad589534a91716b2f191ff3d6f05c0f1018ec0696f30b8f7f8499add7fd4
+size 3375