Training in progress, step 500

.gitignore

@@ -0,0 +1 @@
+checkpoint-*/

config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "bigscience/bloom-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,
+  "skip_bias_add": true,
+  "skip_bias_add_qkv": false,
+  "slow_but_exact": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.26.1",
+  "unk_token_id": 0,
+  "use_cache": true,
+  "vocab_size": 250880
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a81bcfee1360add359316ee5632e6df5b6ccfc768a460b76a108360f8e8d809b
+size 2236957537

runs/Mar05_09-45-13_56e36e7b7882/1678009527.170599/events.out.tfevents.1678009527.56e36e7b7882.23.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f20c4c01df1155a671f3091da074b6531ca6c71ddce0aaf56b82732a4fd00be4
+size 5712

runs/Mar05_09-45-13_56e36e7b7882/events.out.tfevents.1678009527.56e36e7b7882.23.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ba20ce638e32abc50fa2414e6dc070c9859fa1d6e9b47bcc51e4cfc95ab49d0
+size 4134

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e83131af70b79227a36a55e9052642e5168c4d254e086ee3d38dad790d566c6
+size 3515