rm --cached *

.gitattributes

@@ -1,34 +0,0 @@
-*.7z filter=lfs diff=lfs merge=lfs -text
-*.arrow filter=lfs diff=lfs merge=lfs -text
-*.bin filter=lfs diff=lfs merge=lfs -text
-*.bz2 filter=lfs diff=lfs merge=lfs -text
-*.ftz filter=lfs diff=lfs merge=lfs -text
-*.gz filter=lfs diff=lfs merge=lfs -text
-*.h5 filter=lfs diff=lfs merge=lfs -text
-*.joblib filter=lfs diff=lfs merge=lfs -text
-*.lfs.* filter=lfs diff=lfs merge=lfs -text
-*.mlmodel filter=lfs diff=lfs merge=lfs -text
-*.model filter=lfs diff=lfs merge=lfs -text
-*.msgpack filter=lfs diff=lfs merge=lfs -text
-*.npy filter=lfs diff=lfs merge=lfs -text
-*.npz filter=lfs diff=lfs merge=lfs -text
-*.onnx filter=lfs diff=lfs merge=lfs -text
-*.ot filter=lfs diff=lfs merge=lfs -text
-*.parquet filter=lfs diff=lfs merge=lfs -text
-*.pb filter=lfs diff=lfs merge=lfs -text
-*.pickle filter=lfs diff=lfs merge=lfs -text
-*.pkl filter=lfs diff=lfs merge=lfs -text
-*.pt filter=lfs diff=lfs merge=lfs -text
-*.pth filter=lfs diff=lfs merge=lfs -text
-*.rar filter=lfs diff=lfs merge=lfs -text
-*.safetensors filter=lfs diff=lfs merge=lfs -text
-saved_model/**/* filter=lfs diff=lfs merge=lfs -text
-*.tar.* filter=lfs diff=lfs merge=lfs -text
-*.tflite filter=lfs diff=lfs merge=lfs -text
-*.tgz filter=lfs diff=lfs merge=lfs -text
-*.wasm filter=lfs diff=lfs merge=lfs -text
-*.xz 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

@@ -1,10 +0,0 @@
-word_embeddings_layernorm.pt
-checkpoint-20000/
-checkpoint-25000/
-checkpoint-15000/
-eval_results.json
-checkpoint-10000/
-all_results.json
-word_embeddings.pt
-checkpoint-5000/
-train_results.json

config.json

@@ -1,38 +0,0 @@
-{
-  "_name_or_path": "bigscience/bloom-1b1",
-  "adapters": {
-    "adapters": {},
-    "config_map": {},
-    "fusion_config_map": {},
-    "fusions": {}
-  },
-  "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": 1536,
-  "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": "float16",
-  "transformers_version": "4.20.0.dev0",
-  "unk_token_id": 0,
-  "use_cache": true,
-  "vocab_size": 250880
-}

pytorch_model.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:ee70856c4a53d34dc9a2624bab4f8cc1b5533d5c32825a1a9f375d17584001d4
-size 2130668779

special_tokens_map.json

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

tokenizer.json

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:8f6efc66e73f1fd69da4f436e48befb519fdff3fe18910850c1d41bd862293a5
-size 14500443

tokenizer_config.json

@@ -1 +0,0 @@
-{"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>", "pad_token": "<pad>", "add_prefix_space": false, "name_or_path": "bigscience/bloom-1b1", "special_tokens_map_file": null, "padding_side": "left", "tokenizer_class": "BloomTokenizer"}

trainer_state.json

@@ -1,125 +0,0 @@
-{
-  "best_metric": 2.68359375,
-  "best_model_checkpoint": "/home/zhengxinyong/outputs/bloom-1b1_de_continual-pretrain_100000samples_-1vocab_original/checkpoint-25000",
-  "epoch": 2.7475546763380594,
-  "global_step": 25000,
-  "is_hyper_param_search": false,
-  "is_local_process_zero": true,
-  "is_world_process_zero": true,
-  "log_history": [
-    {
-      "epoch": 0.27,
-      "learning_rate": 0.0001,
-      "loss": 3.1701,
-      "step": 2500
-    },
-    {
-      "epoch": 0.55,
-      "learning_rate": 0.0001,
-      "loss": 2.8341,
-      "step": 5000
-    },
-    {
-      "epoch": 0.55,
-      "eval_loss": 2.873046875,
-      "eval_runtime": 3.4814,
-      "eval_samples_per_second": 230.94,
-      "eval_steps_per_second": 29.011,
-      "step": 5000
-    },
-    {
-      "epoch": 0.82,
-      "learning_rate": 0.0001,
-      "loss": 2.7255,
-      "step": 7500
-    },
-    {
-      "epoch": 1.1,
-      "learning_rate": 0.0001,
-      "loss": 2.5869,
-      "step": 10000
-    },
-    {
-      "epoch": 1.1,
-      "eval_loss": 2.759765625,
-      "eval_runtime": 3.473,
-      "eval_samples_per_second": 231.499,
-      "eval_steps_per_second": 29.081,
-      "step": 10000
-    },
-    {
-      "epoch": 1.37,
-      "learning_rate": 0.0001,
-      "loss": 2.4538,
-      "step": 12500
-    },
-    {
-      "epoch": 1.65,
-      "learning_rate": 0.0001,
-      "loss": 2.4623,
-      "step": 15000
-    },
-    {
-      "epoch": 1.65,
-      "eval_loss": 2.705078125,
-      "eval_runtime": 3.4584,
-      "eval_samples_per_second": 232.479,
-      "eval_steps_per_second": 29.204,
-      "step": 15000
-    },
-    {
-      "epoch": 1.92,
-      "learning_rate": 0.0001,
-      "loss": 2.4534,
-      "step": 17500
-    },
-    {
-      "epoch": 2.2,
-      "learning_rate": 0.0001,
-      "loss": 2.2463,
-      "step": 20000
-    },
-    {
-      "epoch": 2.2,
-      "eval_loss": 2.712890625,
-      "eval_runtime": 3.4672,
-      "eval_samples_per_second": 231.886,
-      "eval_steps_per_second": 29.13,
-      "step": 20000
-    },
-    {
-      "epoch": 2.47,
-      "learning_rate": 0.0001,
-      "loss": 2.2084,
-      "step": 22500
-    },
-    {
-      "epoch": 2.75,
-      "learning_rate": 0.0001,
-      "loss": 2.2451,
-      "step": 25000
-    },
-    {
-      "epoch": 2.75,
-      "eval_loss": 2.68359375,
-      "eval_runtime": 3.4826,
-      "eval_samples_per_second": 230.861,
-      "eval_steps_per_second": 29.001,
-      "step": 25000
-    },
-    {
-      "epoch": 2.75,
-      "step": 25000,
-      "total_flos": 8.355380415011226e+17,
-      "train_loss": 2.53857546875,
-      "train_runtime": 4808.8208,
-      "train_samples_per_second": 41.59,
-      "train_steps_per_second": 5.199
-    }
-  ],
-  "max_steps": 25000,
-  "num_train_epochs": 3,
-  "total_flos": 8.355380415011226e+17,
-  "trial_name": null,
-  "trial_params": null
-}

training_args.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:d9434ced7df591cdb6202bc169b46edd7b46a94996ac179a0c6056b7f66df194
-size 4399