Training in progress, step 10000

.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": true,
+  "vocab_size": 50000
+}

logs/1668478610.235192/events.out.tfevents.1668478610.tristan-olm-training-a100-80.3467.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2a5e30f0832e1f8db1f7b2a3eacfc68559118dafe0bdd18e813aac7c81c8df9
+size 5483

logs/1668479899.5517724/events.out.tfevents.1668479899.tristan-olm-training-a100-80.9564.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:637b88b2d98fd5f38121f719a7d28e0abebbe90aafb050a541df78b979b901e4
+size 5483

logs/events.out.tfevents.1668478610.tristan-olm-training-a100-80.3467.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a89e162b0eac22863d4c060fa6d3949c2ff3c7a6ea6836f356e08899d9164590
+size 3835

logs/events.out.tfevents.1668479899.tristan-olm-training-a100-80.9564.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b369fa71abc395263ebedb93d619df9859b3efd8b0844fc901a80548351b501
+size 19532

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ab114f60c21d16db2dea35d850479b81563bc0e41d85f57d4f2727d026d4247
+size 1414153057

special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

tokenizer_config.json

@@ -0,0 +1,14 @@
+{
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "name_or_path": "Tristan/olm-tokenizer",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "special_tokens_map_file": null,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6624c1c0d61902ce1b0205b75fbf67896abe88423fd25ea4a32bf3a01f58d5eb
+size 3387