Training in progress, step 500

.gitignore

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

config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "sai1881/bloom-560m-finetuned-wikitext2",
+  "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 sha256:8f8589679c0b46c12ba7e3f83cf782d429d0d948bb48b6e3994295bec8b8bc57
+size 2236957537

runs/Mar05_12-25-57_c7843030fc65/1678019164.9435043/events.out.tfevents.1678019164.c7843030fc65.1449.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ee3ef627e909847cd6716b790d27e810e5df25555efd85fad4b7143dcee8610
+size 5763

runs/Mar05_12-25-57_c7843030fc65/events.out.tfevents.1678019164.c7843030fc65.1449.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eeaa6f4034268b25f1b65b8cb2acbc52f30475e3b6ac5f4c52332408278fa3c7
+size 40

runs/Mar05_12-30-42_c7843030fc65/1678019455.4800444/events.out.tfevents.1678019455.c7843030fc65.26640.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cdfac6f88a1f85edd716721a15db7d4d9321196b47185557edb468f92ba4a0df
+size 5763

runs/Mar05_12-30-42_c7843030fc65/events.out.tfevents.1678019455.c7843030fc65.26640.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b162d2cb14a4f1d021ab31160333eb4d86840084cbd98dc23e3c123e04f84482
+size 4225

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d37c65d7d449b725705b8ed5433f5df74592439a220d04f51ec940a1617ed93
+size 3579