Upload folder using huggingface_hub

README.md

@@ -0,0 +1,72 @@
+---
+language:
+- en
+license: apache-2.0
+base_model: JackFram/llama-160m
+tags:
+- generated_from_trainer
+datasets:
+- glue
+metrics:
+- accuracy
+model-index:
+- name: llama-160m-qnli
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    dataset:
+      name: GLUE QNLI
+      type: glue
+      args: qnli
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.5149185429251327
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# llama-160m-qnli
+
+This model is a fine-tuned version of [JackFram/llama-160m](https://huggingface.co/JackFram/llama-160m) on the GLUE QNLI dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.8172
+- Accuracy: 0.5149
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 2e-05
+- train_batch_size: 32
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 5.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.31.0
+- Pytorch 2.0.1+cu117
+- Datasets 2.18.0
+- Tokenizers 0.13.3

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 5.0,
+    "eval_accuracy": 0.5149185429251327,
+    "eval_loss": 0.8172348141670227,
+    "eval_runtime": 14.0334,
+    "eval_samples": 5463,
+    "eval_samples_per_second": 389.287,
+    "eval_steps_per_second": 48.67,
+    "train_loss": 0.8148820433153492,
+    "train_runtime": 3646.2431,
+    "train_samples": 104743,
+    "train_samples_per_second": 143.631,
+    "train_steps_per_second": 4.49
+}

config.json

@@ -0,0 +1,36 @@
+{
+  "_name_or_path": "JackFram/llama-160m",
+  "architectures": [
+    "LlamaForSequenceClassification"
+  ],
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "finetuning_task": "qnli",
+  "hidden_act": "silu",
+  "hidden_size": 768,
+  "id2label": {
+    "0": "entailment",
+    "1": "not_entailment"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "entailment": 0,
+    "not_entailment": 1
+  },
+  "max_position_embeddings": 2048,
+  "model_type": "llama",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "num_key_value_heads": 12,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "problem_type": "single_label_classification",
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.31.0",
+  "use_cache": true,
+  "vocab_size": 32000
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 5.0,
+    "eval_accuracy": 0.5149185429251327,
+    "eval_loss": 0.8172348141670227,
+    "eval_runtime": 14.0334,
+    "eval_samples": 5463,
+    "eval_samples_per_second": 389.287,
+    "eval_steps_per_second": 48.67
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:580c7882d8485ac1723ff8081ab5321ad283674c81fd022461739dc4c134ab77
+size 551414329

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "</s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,33 @@
+{
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": false,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 5.0,
+    "train_loss": 0.8148820433153492,
+    "train_runtime": 3646.2431,
+    "train_samples": 104743,
+    "train_samples_per_second": 143.631,
+    "train_steps_per_second": 4.49
+}

trainer_state.json

@@ -0,0 +1,217 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 5.0,
+  "global_step": 16370,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.938912645082468e-05,
+      "loss": 0.8164,
+      "step": 500
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.8778252901649362e-05,
+      "loss": 0.8115,
+      "step": 1000
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1.816737935247404e-05,
+      "loss": 0.8157,
+      "step": 1500
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 1.755650580329872e-05,
+      "loss": 0.8115,
+      "step": 2000
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 1.69456322541234e-05,
+      "loss": 0.813,
+      "step": 2500
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 1.6334758704948076e-05,
+      "loss": 0.8195,
+      "step": 3000
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 1.5723885155772757e-05,
+      "loss": 0.8159,
+      "step": 3500
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 1.5113011606597437e-05,
+      "loss": 0.817,
+      "step": 4000
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 1.4502138057422115e-05,
+      "loss": 0.8126,
+      "step": 4500
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 1.3891264508246794e-05,
+      "loss": 0.8166,
+      "step": 5000
+    },
+    {
+      "epoch": 1.68,
+      "learning_rate": 1.3280390959071474e-05,
+      "loss": 0.8129,
+      "step": 5500
+    },
+    {
+      "epoch": 1.83,
+      "learning_rate": 1.2669517409896153e-05,
+      "loss": 0.816,
+      "step": 6000
+    },
+    {
+      "epoch": 1.99,
+      "learning_rate": 1.2058643860720831e-05,
+      "loss": 0.8149,
+      "step": 6500
+    },
+    {
+      "epoch": 2.14,
+      "learning_rate": 1.1447770311545512e-05,
+      "loss": 0.8151,
+      "step": 7000
+    },
+    {
+      "epoch": 2.29,
+      "learning_rate": 1.083689676237019e-05,
+      "loss": 0.817,
+      "step": 7500
+    },
+    {
+      "epoch": 2.44,
+      "learning_rate": 1.0226023213194869e-05,
+      "loss": 0.8087,
+      "step": 8000
+    },
+    {
+      "epoch": 2.6,
+      "learning_rate": 9.615149664019549e-06,
+      "loss": 0.8124,
+      "step": 8500
+    },
+    {
+      "epoch": 2.75,
+      "learning_rate": 9.004276114844227e-06,
+      "loss": 0.8164,
+      "step": 9000
+    },
+    {
+      "epoch": 2.9,
+      "learning_rate": 8.393402565668908e-06,
+      "loss": 0.8146,
+      "step": 9500
+    },
+    {
+      "epoch": 3.05,
+      "learning_rate": 7.782529016493586e-06,
+      "loss": 0.8202,
+      "step": 10000
+    },
+    {
+      "epoch": 3.21,
+      "learning_rate": 7.171655467318266e-06,
+      "loss": 0.8123,
+      "step": 10500
+    },
+    {
+      "epoch": 3.36,
+      "learning_rate": 6.560781918142944e-06,
+      "loss": 0.8136,
+      "step": 11000
+    },
+    {
+      "epoch": 3.51,
+      "learning_rate": 5.949908368967624e-06,
+      "loss": 0.8131,
+      "step": 11500
+    },
+    {
+      "epoch": 3.67,
+      "learning_rate": 5.339034819792304e-06,
+      "loss": 0.8264,
+      "step": 12000
+    },
+    {
+      "epoch": 3.82,
+      "learning_rate": 4.728161270616982e-06,
+      "loss": 0.8086,
+      "step": 12500
+    },
+    {
+      "epoch": 3.97,
+      "learning_rate": 4.117287721441662e-06,
+      "loss": 0.8162,
+      "step": 13000
+    },
+    {
+      "epoch": 4.12,
+      "learning_rate": 3.506414172266341e-06,
+      "loss": 0.8159,
+      "step": 13500
+    },
+    {
+      "epoch": 4.28,
+      "learning_rate": 2.8955406230910206e-06,
+      "loss": 0.8139,
+      "step": 14000
+    },
+    {
+      "epoch": 4.43,
+      "learning_rate": 2.2846670739156996e-06,
+      "loss": 0.8151,
+      "step": 14500
+    },
+    {
+      "epoch": 4.58,
+      "learning_rate": 1.6737935247403788e-06,
+      "loss": 0.8118,
+      "step": 15000
+    },
+    {
+      "epoch": 4.73,
+      "learning_rate": 1.0629199755650582e-06,
+      "loss": 0.8212,
+      "step": 15500
+    },
+    {
+      "epoch": 4.89,
+      "learning_rate": 4.5204642638973736e-07,
+      "loss": 0.8104,
+      "step": 16000
+    },
+    {
+      "epoch": 5.0,
+      "step": 16370,
+      "total_flos": 4.555745093910528e+16,
+      "train_loss": 0.8148820433153492,
+      "train_runtime": 3646.2431,
+      "train_samples_per_second": 143.631,
+      "train_steps_per_second": 4.49
+    }
+  ],
+  "max_steps": 16370,
+  "num_train_epochs": 5,
+  "total_flos": 4.555745093910528e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e2a15a1f92edc3a39ae45c0e4f9e5151280e249d75ddf869530996cf8e02aa1
+size 3963