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": "4.28.1",
+  "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:aab3f1e54ae40849f1811d5bb468c52559eca411e14a27eea175754d8a4fa23a
+size 2236957537

runs/May10_03-33-12_db1b118ecdff/1683689598.3057995/events.out.tfevents.1683689598.db1b118ecdff.11494.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ade337d4b94c4fd34aac3d64b25b3854b2441948b162246b1117171a60c720c
+size 5921

runs/May10_03-33-12_db1b118ecdff/events.out.tfevents.1683689598.db1b118ecdff.11494.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dcc236cb2aa71ca96b6b14dc395483772b4dcc10cfd47e2c2a9a1a4323252437
+size 4157

runs/May10_04-04-33_db1b118ecdff/1683691477.9994946/events.out.tfevents.1683691477.db1b118ecdff.21248.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78451cef206d04c21dffed328071fa43d90a82f3478c0400b07a45db7fcff560
+size 5921

runs/May10_04-04-33_db1b118ecdff/events.out.tfevents.1683691477.db1b118ecdff.21248.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35fb88eb917ad45d8136d7cadc8bd41b276d6d59cb99a628fbdbeeefd140f426
+size 4314

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98232ae878bbea8989f6b65b95fc07624cf9421977f9c182c73ccad4a9971dba
+size 3643