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": "4.22.2",
+  "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 sha256:11768c7fe493e8065dd0ca59b9798cb1527bc0e3173ced11afc55ec982d79bfc
+size 2236955191

runs/Sep29_09-45-54_24881d5bb7d9/1664444783.5254514/events.out.tfevents.1664444783.24881d5bb7d9.67.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98ba1d2609d850cc5efae52c6f91751625c5373acba32c47abafbcc279e9d571
+size 5536

runs/Sep29_09-45-54_24881d5bb7d9/events.out.tfevents.1664444783.24881d5bb7d9.67.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3653c9c3dd1daa0de0dd527e3ef4d412729d29b7103467aee03dc77a4c610387
+size 6761

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3ca1270fa659f5d93d95926b2555dbdf78f9e3c110d0dfc11035041e2d8ef54
+size 3375