Training in progress, step 1000

.gitignore

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

config.json

@@ -0,0 +1,33 @@
+{
+  "_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,
+  "seq_length": 2048,
+  "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 sha256:865bd4647cf846e66b118c6f4321f3f38ebde9ed61fcd8747454586f8da05d11
+size 2236955191

runs/Sep27_15-57-31_87092e62ca23/1664294270.7428637/events.out.tfevents.1664294270.87092e62ca23.68.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36ff5de6cb3fdaa19ee018cc9adbe78aa48d7a7b6344fab3be8f101060ad38cf
+size 5539

runs/Sep27_15-57-31_87092e62ca23/events.out.tfevents.1664294270.87092e62ca23.68.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54bc2e0b032842b3a0b6eb552f7ed0c2093ca95a591817134a912fde89e66a41
+size 6786

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98345e8443fe4d9e49e7c4e4864372c2601be91b67caf34065bcb49b591bd8a9
+size 3375