rm --cached *

.gitattributes

@@ -1,33 +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
-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

@@ -1,15 +0,0 @@
-checkpoint-*/
-*/pilot_*/
-pilot_*/
-checkpoint-*/
-*/pilot_*/
-pilot_*/
-checkpoint-*/
-*/pilot_*/
-pilot_*/
-checkpoint-*/
-*/pilot_*/
-pilot_*/
-checkpoint-*/
-*/pilot_*/
-pilot_*/

all_results.json

@@ -1,14 +0,0 @@
-{
-    "epoch": 2.13,
-    "eval_loss": 2.2437143325805664,
-    "eval_runtime": 482.5676,
-    "eval_samples": 4608,
-    "eval_samples_per_second": 9.549,
-    "eval_steps_per_second": 4.774,
-    "perplexity": 9.428286120634498,
-    "train_loss": 2.3864154296875,
-    "train_runtime": 60699.5161,
-    "train_samples": 94080,
-    "train_samples_per_second": 3.295,
-    "train_steps_per_second": 0.412
-}

config.json

@@ -1,39 +0,0 @@
-{
-  "_name_or_path": "bigscience/bloom-350m",
-  "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": 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": "4.20.0.dev0",
-  "unk_token_id": 0,
-  "use_cache": true,
-  "vocab_size": 250880
-}

eval_results.json

@@ -1,9 +0,0 @@
-{
-    "epoch": 2.13,
-    "eval_loss": 2.2437143325805664,
-    "eval_runtime": 482.5676,
-    "eval_samples": 4608,
-    "eval_samples_per_second": 9.549,
-    "eval_steps_per_second": 4.774,
-    "perplexity": 9.428286120634498
-}

pytorch_model.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:cef1be9a44e7ab905acaed1238738e494279ad43f8d0412d49dff23d3c7aed63
-size 2236955191

special_tokens_map.json

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

tatoeba-az-en-results.txt

@@ -1,7 +0,0 @@
-==================================================
-Tatoeba Results (200 pairs of az-en)
-==================================================
-Model: /users/zyong2/data/zyong2/bigscience/data/processed/024/bloom-350m_az_fish_100000samples_-1vocab_original-frozen
-[tensor(0.0150)]
-1.50 ± 0.00
-==================================================

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-350m", "special_tokens_map_file": null, "padding_side": "left", "tokenizer_class": "BloomTokenizer"}

train_results.json

@@ -1,8 +0,0 @@
-{
-    "epoch": 2.13,
-    "train_loss": 2.3864154296875,
-    "train_runtime": 60699.5161,
-    "train_samples": 94080,
-    "train_samples_per_second": 3.295,
-    "train_steps_per_second": 0.412
-}

trainer_state.json

@@ -1,125 +0,0 @@
-{
-  "best_metric": 2.2437143325805664,
-  "best_model_checkpoint": "/users/zyong2/data/zyong2/bigscience/data/processed/024/bloom-350m_az_fish_100000samples_-1vocab_original-frozen/checkpoint-25000",
-  "epoch": 2.1258503401360542,
-  "global_step": 25000,
-  "is_hyper_param_search": false,
-  "is_local_process_zero": true,
-  "is_world_process_zero": true,
-  "log_history": [
-    {
-      "epoch": 0.21,
-      "learning_rate": 9e-05,
-      "loss": 2.9924,
-      "step": 2500
-    },
-    {
-      "epoch": 0.43,
-      "learning_rate": 8e-05,
-      "loss": 2.5627,
-      "step": 5000
-    },
-    {
-      "epoch": 0.43,
-      "eval_loss": 2.5240488052368164,
-      "eval_runtime": 484.0815,
-      "eval_samples_per_second": 9.519,
-      "eval_steps_per_second": 4.76,
-      "step": 5000
-    },
-    {
-      "epoch": 0.64,
-      "learning_rate": 7e-05,
-      "loss": 2.4428,
-      "step": 7500
-    },
-    {
-      "epoch": 0.85,
-      "learning_rate": 6e-05,
-      "loss": 2.3709,
-      "step": 10000
-    },
-    {
-      "epoch": 0.85,
-      "eval_loss": 2.3797976970672607,
-      "eval_runtime": 484.2796,
-      "eval_samples_per_second": 9.515,
-      "eval_steps_per_second": 4.758,
-      "step": 10000
-    },
-    {
-      "epoch": 1.06,
-      "learning_rate": 5e-05,
-      "loss": 2.3225,
-      "step": 12500
-    },
-    {
-      "epoch": 1.28,
-      "learning_rate": 4e-05,
-      "loss": 2.2726,
-      "step": 15000
-    },
-    {
-      "epoch": 1.28,
-      "eval_loss": 2.3043975830078125,
-      "eval_runtime": 483.9345,
-      "eval_samples_per_second": 9.522,
-      "eval_steps_per_second": 4.761,
-      "step": 15000
-    },
-    {
-      "epoch": 1.49,
-      "learning_rate": 3e-05,
-      "loss": 2.2479,
-      "step": 17500
-    },
-    {
-      "epoch": 1.7,
-      "learning_rate": 2e-05,
-      "loss": 2.2341,
-      "step": 20000
-    },
-    {
-      "epoch": 1.7,
-      "eval_loss": 2.264699935913086,
-      "eval_runtime": 483.6102,
-      "eval_samples_per_second": 9.528,
-      "eval_steps_per_second": 4.764,
-      "step": 20000
-    },
-    {
-      "epoch": 1.91,
-      "learning_rate": 1e-05,
-      "loss": 2.2163,
-      "step": 22500
-    },
-    {
-      "epoch": 2.13,
-      "learning_rate": 0.0,
-      "loss": 2.2019,
-      "step": 25000
-    },
-    {
-      "epoch": 2.13,
-      "eval_loss": 2.2437143325805664,
-      "eval_runtime": 482.513,
-      "eval_samples_per_second": 9.55,
-      "eval_steps_per_second": 4.775,
-      "step": 25000
-    },
-    {
-      "epoch": 2.13,
-      "step": 25000,
-      "total_flos": 3.714827943936e+17,
-      "train_loss": 2.3864154296875,
-      "train_runtime": 60699.5161,
-      "train_samples_per_second": 3.295,
-      "train_steps_per_second": 0.412
-    }
-  ],
-  "max_steps": 25000,
-  "num_train_epochs": 3,
-  "total_flos": 3.714827943936e+17,
-  "trial_name": null,
-  "trial_params": null
-}

training_args.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:6581263b77f2005bb58dd0d702f7326a24b98a7257c0931e421b8398bc0be4b1
-size 3375

wikiann-az-results.txt

@@ -1,8 +0,0 @@
-==================================================
-Results WikiANN-az
-==================================================
-Model: /users/zyong2/data/zyong2/bigscience/data/processed/024/bloom-350m_az_fish_100000samples_-1vocab_original-frozen/
-[0.11019153464175929, 0.15776699029126215, 0.08903508771929824, 0.11444492070295757, 0.1271064034665383]
-11.97
-2.26
-==================================================

word_embeddings.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:174ed618237771e5906be0e8d70c568de63633f3bb5e8a1e303bbdbaeaedc1ca
-size 1027605867

word_embeddings_layernorm.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:10917f86841a4f322406bd72ba2e4ae8e4780aaf462c98a76eca01e0c5fbc893
-size 9703