End of training

README.md

@@ -0,0 +1,52 @@
+---
+license: bigscience-bloom-rail-1.0
+base_model: bigscience/bloom-560m
+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-560m](https://huggingface.co/bigscience/bloom-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: 4
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 3
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.35.2
+- Pytorch 2.1.0+cu118
+- Datasets 2.15.0
+- Tokenizers 0.15.0

config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "bigscience/bloom-560m",
+  "apply_residual_connection_post_layernorm": false,
+  "architectures": [
+    "BloomForQuestionAnswering"
+  ],
+  "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,
+  "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
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57f68eafcbf0ee480c6cf4f18e98b1cc1a836bb0986476e481fa68e729771c53
+size 2236900656

runs/Dec04_07-20-25_b5678de53ffb/events.out.tfevents.1701674426.b5678de53ffb.329.19

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4af8444301bcfe16e52f455efa56fa51b1c38e03b253cb8e2016ace4d449136
+size 4288

runs/Dec04_07-21-27_b5678de53ffb/events.out.tfevents.1701674488.b5678de53ffb.329.20

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3adc612b136812ef5bf775f038ae10c62b136c9ff0b647d5e57119414b7bc0f8
+size 4288

runs/Dec04_07-22-29_b5678de53ffb/events.out.tfevents.1701674550.b5678de53ffb.329.21

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2f3b85e52ee6da836ea0f0a22b003b943af54a6b24c5a90a493f5fce441da0d
+size 4288

runs/Dec04_07-23-54_b5678de53ffb/events.out.tfevents.1701674635.b5678de53ffb.329.22

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67c3636312acf259d6900c193af96aa92729629c2385544a4a2a79796e4c54a2
+size 4288

runs/Dec04_07-24-53_b5678de53ffb/events.out.tfevents.1701674694.b5678de53ffb.329.23

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9016c53ab6fc0790e484902320753bbb9c6695a7f59cb6150c5f4b61d202558a
+size 4288

runs/Dec04_07-25-42_b5678de53ffb/events.out.tfevents.1701674743.b5678de53ffb.329.24

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d166238d4e305385ad1b237501ea5fb51744d4d8fc597f22f6ffc499f25ff4ad
+size 4288

runs/Dec04_07-26-56_b5678de53ffb/events.out.tfevents.1701674817.b5678de53ffb.329.25

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56e0e951cdd5b4cdbdc64dcf1aaf316de28aa83db84b93211b8f273703b1f36d
+size 4288

runs/Dec04_07-31-54_b5678de53ffb/events.out.tfevents.1701675115.b5678de53ffb.329.26

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ea1d5b3b72f9426b0ccaebed344060f52a285d2d22ee979f88636ad021440ce
+size 4288

runs/Dec04_07-42-56_b5678de53ffb/events.out.tfevents.1701675778.b5678de53ffb.329.27

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c8e92bc5b10bebe2e7c25a532283849f9d0604eb1aec861bcd24c50958408eb
+size 4288

runs/Dec04_07-44-08_b5678de53ffb/events.out.tfevents.1701675849.b5678de53ffb.329.28

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8051a0400e9678474f3e807a21e88ee9070c88ef36f2d9039147b547719e3782
+size 4288

runs/Dec04_07-45-08_b5678de53ffb/events.out.tfevents.1701675909.b5678de53ffb.329.29

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b62c6bdb774b743f1e1e0c4a57f14d6ff8b0f0fdbe69ef615b2fc6b4997d5a6
+size 4288

runs/Dec04_07-46-28_b5678de53ffb/events.out.tfevents.1701675989.b5678de53ffb.329.30

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d54479cdc08b33e16b132840bfe51ee1c5a8f9ab6cf2ce0d8e0c324bf43aa552
+size 4636

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f86579123abaa130ae5a054c447e4f15c8257d4b64baca37271d6fe02c65122b
+size 4536