End of training

.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": "4.23.1",
+  "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 sha256:324723d9b710c9bfe70600a443c0f3856006c6eced1de70c4d9cda5344200f86
+size 2236955191

runs/Oct12_15-17-25_129-146-2-127/1665587928.888287/events.out.tfevents.1665587928.129-146-2-127.57735.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22e378938d51b426226f235c78806f8bcb7cde5749b98e8df66a6e596b41d60a
+size 5499

runs/Oct12_15-17-25_129-146-2-127/events.out.tfevents.1665587928.129-146-2-127.57735.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab8fc038557d0ae68b12e0809612dec6f3ec14e4c1355e819a79c258302b8f51
+size 5506

runs/Oct12_15-17-25_129-146-2-127/events.out.tfevents.1665599375.129-146-2-127.57735.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d089323d398235b3a2fc5b3b78ad6a54ff524bfa2db0a75169111bea4f9905f0
+size 316

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ff82b069d720121cdf01d22b5441ad115b67acf245eeb46c2aa1016dffd80af
+size 3375