Training in progress, step 200

.gitattributes

@@ -32,3 +32,4 @@ 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 +1,32 @@
+{
+  "_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": "4.24.0",
+  "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:a91d70c37f0ba70807f7e0db3a85a1d3653a3c52bf8f32dbb05a722dbe53539d
+size 2236957537

runs/Dec09_14-52-19_068c02ccd435/1670597550.6602793/events.out.tfevents.1670597550.068c02ccd435.2119.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58c4533ed5a4a9e2d77b37db57d9e40b4052d07d7ae9037b1dede371abac4b5a
+size 5559

runs/Dec09_14-52-19_068c02ccd435/events.out.tfevents.1670597550.068c02ccd435.2119.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb14c8dc0c4b041bf848e37a817b58df070b2a43ec3eca9a89f1eaef4c95924d
+size 3899

runs/Dec09_14-55-11_068c02ccd435/1670597718.0387008/events.out.tfevents.1670597718.068c02ccd435.6360.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af92ddabc2d3e99bbb04a3b619c67becee0a6e0f8deda520adab12e13352ceba
+size 5559

runs/Dec09_14-55-11_068c02ccd435/events.out.tfevents.1670597718.068c02ccd435.6360.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8eb92320c2d524a5f8cd596ebc867c20058845c6049e65ad31baa012b75ae47
+size 4479

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 sha256:8f6efc66e73f1fd69da4f436e48befb519fdff3fe18910850c1d41bd862293a5
+size 14500443

tokenizer_config.json

@@ -0,0 +1,11 @@
+{
+  "add_prefix_space": false,
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "name_or_path": "bigscience/bloom-560m",
+  "pad_token": "<pad>",
+  "padding_side": "left",
+  "special_tokens_map_file": null,
+  "tokenizer_class": "BloomTokenizer",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a86d4935b690af21ab60a6727dbd40c0e2938232b20ccf388e66e5620d30c38e
+size 3451