Training in progress, step 500

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

.gitignore

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

config.json

@@ -0,0 +1,33 @@
+{
+  "_name_or_path": "bigscience/bloom-1b7",
+  "apply_residual_connection_post_layernorm": false,
+  "architectures": [
+    "BloomForQuestionAnswering"
+  ],
+  "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": 2048,
+  "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": 2,
+  "seq_length": 4096,
+  "skip_bias_add": true,
+  "skip_bias_add_qkv": false,
+  "slow_but_exact": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.30.0",
+  "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 sha256:4dfd67ce3cf667311a8e21b62ef5c9977ea034f446abca90da6271c9526e002d
+size 6889753753

runs/Sep14_04-21-40_d97de422e39e/events.out.tfevents.1694665308.d97de422e39e.2883.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d8f20962a9831ab49a1d3409f3ecd69c8185011a03f7c6a493e8c5ca55c4520
+size 4116

runs/Sep14_04-41-45_d97de422e39e/events.out.tfevents.1694666512.d97de422e39e.9616.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f14670d20788cd2f2478d10e355f4b223866a9b1ff39e9eccac65847d683f11e
+size 4116

runs/Sep14_04-42-59_d97de422e39e/events.out.tfevents.1694666589.d97de422e39e.9616.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7962f4d17e52ed8646db3e4d2181ef004f5bf3b8df3a7c62b1d28b34d4b06689
+size 88

runs/Sep14_04-48-09_d97de422e39e/events.out.tfevents.1694666897.d97de422e39e.10855.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bec44e4ad5e0b294ae75b4b1738a0e3333ca97178150bbc21b16e484b4c225fd
+size 4114

runs/Sep14_04-52-23_d97de422e39e/events.out.tfevents.1694667150.d97de422e39e.12924.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c03ba58cd1c63958f09d10caaa821e73f18d853c5df47cbdfe8b2ef10066e421
+size 4114

runs/Sep14_05-06-51_d97de422e39e/events.out.tfevents.1694668024.d97de422e39e.15562.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:792e77dd1ddc53273ffcadd3b83f379dda369634215b30c24f55e5848865dc27
+size 4114

runs/Sep14_05-15-25_d97de422e39e/events.out.tfevents.1694668538.d97de422e39e.19379.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67f47455655842b7162f7c65352cdefd2eb9ec419743d38907784140768f199d
+size 4113

runs/Sep14_05-22-29_d97de422e39e/events.out.tfevents.1694668953.d97de422e39e.21770.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ae6102b676808c6912049d359abbd67ace1cf2ce302d8e6e277b52c03101802
+size 4113

runs/Sep14_05-34-20_d97de422e39e/events.out.tfevents.1694669665.d97de422e39e.25178.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19adfa0199ab5b7db7beb90ebe43492e9eccb84695ef8a36b2d457dad09d4a6e
+size 4293

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca14b8c20c5b1a08fdaa9011dd7b026c613f20ada2d9fcf42397be659b707f1a
+size 14500733

tokenizer_config.json

@@ -0,0 +1,11 @@
+{
+  "add_prefix_space": false,
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "padding_side": "left",
+  "tokenizer_class": "BloomTokenizer",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:213975b916961de09ad7c3e52a6b0202a5342e0fbda6bcf276c7845dc4b27753
+size 3899