Training in progress, step 1000

.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": "4.23.0.dev0",
+  "unk_token_id": 0,
+  "use_cache": false,
+  "vocab_size": 250880
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c46bffb69e8b2bf7ed94a5eeb5e323b74436c9caaf3d5351eb993840e5b3568
+size 2236955191

runs/Sep30_15-00-19_068c02ccd435/1664550039.1394022/events.out.tfevents.1664550039.068c02ccd435.8420.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd9c94720c6bf0a0e47b546e75dbdccf89f784b11169542a635e4a051978cffa
+size 5631

runs/Sep30_15-00-19_068c02ccd435/events.out.tfevents.1664550039.068c02ccd435.8420.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0717937bfa193dbd89b463eacb910741c165464d0776fc8caf531a43e8bee69
+size 6052

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f42fdf494e0a32cf233fa0bd144c9deb6dcd0613e2aa971242aba05e5e315f43
+size 3439