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 sha256:4447fee48f069c6047a5a29474cbd68cc71f70ff34ad5fdbccba9612d99ac19c
+size 4473887005

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6aa8bdb89d1b45ab96ffb2c06b2d2aaa7d3923ca9c0088645dd4d86dd31eedcb
+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 sha256:6bf8bd84900cf9ecf97a7c4233b10db46601ffd7a843aca39d4b4c230674b320
+size 559

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:120967f00ec5a36a6bdf1cfe33a2e733b6d7378519cd04ce15c15c45cec5f274
+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": 2.7185754776000977,
+  "best_model_checkpoint": "../Modelos/bloomz_QG_SQUAD/checkpoint-500",
+  "epoch": 0.36531348463400154,
+  "global_step": 500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.04,
+      "eval_loss": 2.8082664012908936,
+      "eval_runtime": 75.8818,
+      "eval_samples_per_second": 139.296,
+      "eval_steps_per_second": 34.83,
+      "step": 50
+    },
+    {
+      "epoch": 0.07,
+      "eval_loss": 2.692033290863037,
+      "eval_runtime": 75.8713,
+      "eval_samples_per_second": 139.315,
+      "eval_steps_per_second": 34.835,
+      "step": 100
+    },
+    {
+      "epoch": 0.11,
+      "eval_loss": 2.698404312133789,
+      "eval_runtime": 75.8537,
+      "eval_samples_per_second": 139.347,
+      "eval_steps_per_second": 34.843,
+      "step": 150
+    },
+    {
+      "epoch": 0.15,
+      "eval_loss": 2.6990063190460205,
+      "eval_runtime": 75.8436,
+      "eval_samples_per_second": 139.366,
+      "eval_steps_per_second": 34.848,
+      "step": 200
+    },
+    {
+      "epoch": 0.18,
+      "eval_loss": 2.6953232288360596,
+      "eval_runtime": 75.859,
+      "eval_samples_per_second": 139.337,
+      "eval_steps_per_second": 34.841,
+      "step": 250
+    },
+    {
+      "epoch": 0.22,
+      "eval_loss": 2.6985721588134766,
+      "eval_runtime": 75.8584,
+      "eval_samples_per_second": 139.339,
+      "eval_steps_per_second": 34.841,
+      "step": 300
+    },
+    {
+      "epoch": 0.26,
+      "eval_loss": 2.703632116317749,
+      "eval_runtime": 75.8692,
+      "eval_samples_per_second": 139.319,
+      "eval_steps_per_second": 34.836,
+      "step": 350
+    },
+    {
+      "epoch": 0.29,
+      "eval_loss": 2.713385581970215,
+      "eval_runtime": 75.8665,
+      "eval_samples_per_second": 139.324,
+      "eval_steps_per_second": 34.838,
+      "step": 400
+    },
+    {
+      "epoch": 0.33,
+      "eval_loss": 2.7052266597747803,
+      "eval_runtime": 75.8449,
+      "eval_samples_per_second": 139.363,
+      "eval_steps_per_second": 34.847,
+      "step": 450
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 4.395711500974659e-05,
+      "loss": 2.3203,
+      "step": 500
+    },
+    {
+      "epoch": 0.37,
+      "eval_loss": 2.7185754776000977,
+      "eval_runtime": 75.8537,
+      "eval_samples_per_second": 139.347,
+      "eval_steps_per_second": 34.843,
+      "step": 500
+    }
+  ],
+  "max_steps": 4104,
+  "num_train_epochs": 3,
+  "total_flos": 1.65432208130048e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6bd67622c9b43e9cec952f64a0c16f5edaa94d1c9dd42a00d5dad7b965fc4747
+size 3375