Push to HF hub

.gitattributes

@@ -0,0 +1,33 @@
+*.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

@@ -0,0 +1,12 @@
+pilot_wikiann-az/
+checkpoint-15000/
+word_embeddings.pt
+eval_results.json
+checkpoint-5000/
+word_embeddings_layernorm.pt
+all_results.json
+train_results.json
+checkpoint-25000/
+wikiann-az-results.txt
+checkpoint-20000/
+checkpoint-10000/

config.json

@@ -0,0 +1,39 @@
+{
+  "_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
+}

pytorch_diff.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0091b1a5642a01858d1aa1bc7b003758b297a937b04c17d14c9625fe10e3714c
+size 22506685

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b18bfd59140ba8bcdf1bc69cd403d6fc06514a00bba834982ab9f804932a0c23
+size 2236955191

special_tokens_map.json

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

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 @@
+{"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"}

trainer_state.json

@@ -0,0 +1,135 @@
+{
+  "best_metric": 2.3477182388305664,
+  "best_model_checkpoint": "/users/zyong2/data/zyong2/bigscience/data/processed/024/bloom-350m_az_sft_10000samples_-1vocab_original-frozen/checkpoint-25000",
+  "epoch": 19.856519150625125,
+  "global_step": 25000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.99,
+      "l1_reg_loss": 0.0,
+      "learning_rate": 9e-05,
+      "loss": 3.1946,
+      "step": 2500
+    },
+    {
+      "epoch": 3.97,
+      "l1_reg_loss": 0.0001,
+      "learning_rate": 8e-05,
+      "loss": 2.6396,
+      "step": 5000
+    },
+    {
+      "epoch": 3.97,
+      "eval_loss": 2.5872137546539307,
+      "eval_runtime": 514.4581,
+      "eval_samples_per_second": 9.536,
+      "eval_steps_per_second": 4.768,
+      "step": 5000
+    },
+    {
+      "epoch": 5.96,
+      "l1_reg_loss": 0.0001,
+      "learning_rate": 7e-05,
+      "loss": 2.4815,
+      "step": 7500
+    },
+    {
+      "epoch": 7.94,
+      "l1_reg_loss": 0.0001,
+      "learning_rate": 6e-05,
+      "loss": 2.3898,
+      "step": 10000
+    },
+    {
+      "epoch": 7.94,
+      "eval_loss": 2.439215898513794,
+      "eval_runtime": 514.6109,
+      "eval_samples_per_second": 9.533,
+      "eval_steps_per_second": 4.767,
+      "step": 10000
+    },
+    {
+      "epoch": 9.93,
+      "l1_reg_loss": 0.0001,
+      "learning_rate": 5e-05,
+      "loss": 2.3298,
+      "step": 12500
+    },
+    {
+      "epoch": 11.91,
+      "l1_reg_loss": 0.0001,
+      "learning_rate": 4e-05,
+      "loss": 2.287,
+      "step": 15000
+    },
+    {
+      "epoch": 11.91,
+      "eval_loss": 2.3796885013580322,
+      "eval_runtime": 514.3961,
+      "eval_samples_per_second": 9.537,
+      "eval_steps_per_second": 4.769,
+      "step": 15000
+    },
+    {
+      "epoch": 13.9,
+      "l1_reg_loss": 0.0001,
+      "learning_rate": 3e-05,
+      "loss": 2.254,
+      "step": 17500
+    },
+    {
+      "epoch": 15.89,
+      "l1_reg_loss": 0.0001,
+      "learning_rate": 2e-05,
+      "loss": 2.2339,
+      "step": 20000
+    },
+    {
+      "epoch": 15.89,
+      "eval_loss": 2.354508399963379,
+      "eval_runtime": 514.4981,
+      "eval_samples_per_second": 9.536,
+      "eval_steps_per_second": 4.768,
+      "step": 20000
+    },
+    {
+      "epoch": 17.87,
+      "l1_reg_loss": 0.0001,
+      "learning_rate": 1e-05,
+      "loss": 2.2184,
+      "step": 22500
+    },
+    {
+      "epoch": 19.86,
+      "l1_reg_loss": 0.0001,
+      "learning_rate": 0.0,
+      "loss": 2.21,
+      "step": 25000
+    },
+    {
+      "epoch": 19.86,
+      "eval_loss": 2.3477182388305664,
+      "eval_runtime": 514.3805,
+      "eval_samples_per_second": 9.538,
+      "eval_steps_per_second": 4.769,
+      "step": 25000
+    },
+    {
+      "epoch": 19.86,
+      "step": 25000,
+      "total_flos": 3.7165924872093696e+17,
+      "train_loss": 2.42385498046875,
+      "train_runtime": 61408.2472,
+      "train_samples_per_second": 3.257,
+      "train_steps_per_second": 0.407
+    }
+  ],
+  "max_steps": 25000,
+  "num_train_epochs": 20,
+  "total_flos": 3.7165924872093696e+17,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b10603cd710f3bcfa48f2004adff9c85427b634f98a7c029323c0d19e2a90d87
+size 3375