End of training

README.md

@@ -0,0 +1,51 @@
+---
+license: bigscience-bloom-rail-1.0
+base_model: bigscience/bloomz-560m
+tags:
+- generated_from_trainer
+model-index:
+- name: BLOOM560mfinetune
+  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. -->
+
+# BLOOM560mfinetune
+
+This model is a fine-tuned version of [bigscience/bloomz-560m](https://huggingface.co/bigscience/bloomz-560m) 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: 5
+- 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 4.35.2
+- Pytorch 2.1.0+cu121
+- Tokenizers 0.15.0

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": "4.35.2",
+  "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": "4.35.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e5f61fbbfd5dd09a703695971850088e7f6f4f4478493726eb2a18b447cd38e
+size 2236892304

runs/Dec16_18-59-21_5c865fdaac76/events.out.tfevents.1702753176.5c865fdaac76.1170.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a396992f7649f9d38238e787a645c72ade5a458c8081ae740f43314261c93c6b
+size 4325

runs/Dec16_19-02-14_5c865fdaac76/events.out.tfevents.1702753338.5c865fdaac76.1170.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c18a2ffa2dedc6e560844ee310ad9e573e479a4a81cba36dbc4526957b9c6843
+size 4325

runs/Dec16_19-09-23_5c865fdaac76/events.out.tfevents.1702753781.5c865fdaac76.1170.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24e390ceff93bc1136c9376fd4696d477480e8ea9ded3b25ded0073cbd222f77
+size 4348

runs/Dec16_19-10-15_5c865fdaac76/events.out.tfevents.1702753828.5c865fdaac76.1170.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:368a10dca87875f3ef8ada810114731a54554054ec5b46936f190ee1f71373d8
+size 4348

runs/Dec16_19-10-15_5c865fdaac76/events.out.tfevents.1702753881.5c865fdaac76.1170.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3df52e8b973c7d1a5f94a21fe3b16e178ded492c0aa35ff3a528bc06d50ed7a9
+size 4859

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4300c248e1b3d2b373ab8874b1a2de6586588c9953bf5250665c26a7dc538bf2
+size 4600