End of training

README.md

@@ -0,0 +1,53 @@
+---
+library_name: transformers
+license: bigscience-bloom-rail-1.0
+base_model: bigscience/bloom-1b7
+tags:
+- generated_from_trainer
+model-index:
+- name: output
+  results: []
+---
+
+<!-- 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. -->
+
+# output
+
+This model is a fine-tuned version of [bigscience/bloom-1b7](https://huggingface.co/bigscience/bloom-1b7) on an unknown dataset.
+
+## 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: 2
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 2
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.45.2
+- Pytorch 2.5.1+cu121
+- Datasets 3.2.0
+- Tokenizers 0.20.3

config.json

@@ -0,0 +1,33 @@
+{
+  "_name_or_path": "bigscience/bloom-1b7",
+  "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": 2048,
+  "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": 2,
+  "seq_length": 4096,
+  "skip_bias_add": true,
+  "skip_bias_add_qkv": false,
+  "slow_but_exact": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.45.2",
+  "unk_token_id": 0,
+  "use_cache": true,
+  "vocab_size": 250880
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 3,
+  "transformers_version": "4.45.2"
+}

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da8a41d9fcd8e19a0f17a90a95f6e0992294f5deb2098e80363ce4b2bc54e728
+size 4942483896

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f82b7fb86733f420d35e51af2d7e37c6bb499ce6fa2d1e89a96bcd159cab9201
+size 1947186192

model.safetensors.index.json

@@ -0,0 +1,300 @@
+{
+  "metadata": {
+    "total_size": 6889635840
+  },
+  "weight_map": {
+    "transformer.h.0.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.0.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.0.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.0.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.0.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.0.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.0.self_attention.dense.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.0.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.0.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.0.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.1.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.1.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.1.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.1.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.1.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.1.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.1.self_attention.dense.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.1.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.1.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.1.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.10.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.10.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.10.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.10.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.10.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.10.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.10.self_attention.dense.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.10.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.10.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.10.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.11.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.11.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.11.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.11.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.11.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.11.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.11.self_attention.dense.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.11.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.11.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.11.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.12.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.12.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.12.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.12.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.12.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.12.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.12.self_attention.dense.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.12.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.12.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.12.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.13.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.13.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.13.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.13.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.13.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.13.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.13.self_attention.dense.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.13.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.13.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.13.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.14.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.14.mlp.dense_4h_to_h.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.14.mlp.dense_4h_to_h.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.14.mlp.dense_h_to_4h.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.14.mlp.dense_h_to_4h.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.14.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.14.self_attention.dense.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.14.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.14.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.14.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.15.input_layernorm.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.15.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.15.mlp.dense_4h_to_h.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.15.mlp.dense_4h_to_h.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.15.mlp.dense_h_to_4h.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.15.mlp.dense_h_to_4h.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.15.post_attention_layernorm.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.15.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.15.self_attention.dense.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.15.self_attention.dense.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.15.self_attention.query_key_value.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.15.self_attention.query_key_value.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.16.input_layernorm.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.16.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.16.mlp.dense_4h_to_h.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.16.mlp.dense_4h_to_h.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.16.mlp.dense_h_to_4h.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.16.mlp.dense_h_to_4h.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.16.post_attention_layernorm.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.16.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.16.self_attention.dense.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.16.self_attention.dense.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.16.self_attention.query_key_value.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.16.self_attention.query_key_value.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.17.input_layernorm.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.17.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.17.mlp.dense_4h_to_h.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.17.mlp.dense_4h_to_h.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.17.mlp.dense_h_to_4h.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.17.mlp.dense_h_to_4h.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.17.post_attention_layernorm.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.17.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.17.self_attention.dense.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.17.self_attention.dense.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.17.self_attention.query_key_value.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.17.self_attention.query_key_value.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.18.input_layernorm.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.18.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.18.mlp.dense_4h_to_h.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.18.mlp.dense_4h_to_h.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.18.mlp.dense_h_to_4h.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.18.mlp.dense_h_to_4h.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.18.post_attention_layernorm.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.18.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.18.self_attention.dense.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.18.self_attention.dense.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.18.self_attention.query_key_value.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.18.self_attention.query_key_value.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.19.input_layernorm.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.19.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.19.mlp.dense_4h_to_h.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.19.mlp.dense_4h_to_h.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.19.mlp.dense_h_to_4h.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.19.mlp.dense_h_to_4h.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.19.post_attention_layernorm.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.19.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.19.self_attention.dense.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.19.self_attention.dense.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.19.self_attention.query_key_value.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.19.self_attention.query_key_value.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.2.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.2.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.2.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.2.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.2.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.2.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.2.self_attention.dense.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.2.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.2.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.2.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.20.input_layernorm.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.20.mlp.dense_4h_to_h.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.20.mlp.dense_4h_to_h.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.20.mlp.dense_h_to_4h.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.20.mlp.dense_h_to_4h.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.20.post_attention_layernorm.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.20.self_attention.dense.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.20.self_attention.dense.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.20.self_attention.query_key_value.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.20.self_attention.query_key_value.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.21.input_layernorm.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.21.mlp.dense_4h_to_h.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.21.mlp.dense_4h_to_h.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.21.mlp.dense_h_to_4h.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.21.mlp.dense_h_to_4h.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.21.post_attention_layernorm.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.21.self_attention.dense.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.21.self_attention.dense.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.21.self_attention.query_key_value.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.21.self_attention.query_key_value.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.22.input_layernorm.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.22.mlp.dense_4h_to_h.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.22.mlp.dense_4h_to_h.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.22.mlp.dense_h_to_4h.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.22.mlp.dense_h_to_4h.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.22.post_attention_layernorm.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.22.self_attention.dense.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.22.self_attention.dense.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.22.self_attention.query_key_value.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.22.self_attention.query_key_value.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.23.input_layernorm.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.23.mlp.dense_4h_to_h.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.23.mlp.dense_4h_to_h.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.23.mlp.dense_h_to_4h.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.23.mlp.dense_h_to_4h.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.23.post_attention_layernorm.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.23.self_attention.dense.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.23.self_attention.dense.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.23.self_attention.query_key_value.bias": "model-00002-of-00002.safetensors",
+    "transformer.h.23.self_attention.query_key_value.weight": "model-00002-of-00002.safetensors",
+    "transformer.h.3.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.3.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.3.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.3.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.3.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.3.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.3.self_attention.dense.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.3.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.3.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.3.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.4.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.4.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.4.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.4.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.4.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.4.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.4.self_attention.dense.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.4.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.4.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.4.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.5.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.5.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.5.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.5.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.5.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.5.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.5.self_attention.dense.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.5.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.5.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.5.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.6.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.6.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.6.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.6.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.6.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.6.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.6.self_attention.dense.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.6.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.6.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.6.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.7.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.7.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.7.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.7.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.7.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.7.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.7.self_attention.dense.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.7.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.7.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.7.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.8.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.8.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.8.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.8.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.8.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.8.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.8.self_attention.dense.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.8.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.8.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.8.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.9.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.9.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.9.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.9.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.9.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.9.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.9.self_attention.dense.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.9.self_attention.dense.weight": "model-00001-of-00002.safetensors",
+    "transformer.h.9.self_attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "transformer.h.9.self_attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "transformer.ln_f.bias": "model-00002-of-00002.safetensors",
+    "transformer.ln_f.weight": "model-00002-of-00002.safetensors",
+    "transformer.word_embeddings.weight": "model-00001-of-00002.safetensors",
+    "transformer.word_embeddings_layernorm.bias": "model-00001-of-00002.safetensors",
+    "transformer.word_embeddings_layernorm.weight": "model-00001-of-00002.safetensors"
+  }
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dfd7735c563d248a2e55c816f25be7105bbc1803a7f17d65242fbaff48e4e8d6
+size 5176