Push to HF hub

.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 +1,10 @@
+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

@@ -0,0 +1,38 @@
+{
+  "_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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f87161263e62b214dfeb85b6639e304ef4ba85047c9b9eeb92a9f6f2921bf0e1
+size 2130668779

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-1b1", "special_tokens_map_file": null, "padding_side": "left", "tokenizer_class": "BloomTokenizer"}

trainer_state.json

@@ -0,0 +1,125 @@
+{
+  "best_metric": 1.734375,
+  "best_model_checkpoint": "/home/zhengxinyong/outputs/bloom-1b1_ru_continual-pretrain_100000samples_-1vocab_original/checkpoint-25000",
+  "epoch": 1.4637002341920375,
+  "global_step": 25000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.0001,
+      "loss": 2.2756,
+      "step": 2500
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 0.0001,
+      "loss": 2.0005,
+      "step": 5000
+    },
+    {
+      "epoch": 0.29,
+      "eval_loss": 1.9326171875,
+      "eval_runtime": 5.8642,
+      "eval_samples_per_second": 232.428,
+      "eval_steps_per_second": 29.16,
+      "step": 5000
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.0001,
+      "loss": 1.9088,
+      "step": 7500
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 0.0001,
+      "loss": 1.8653,
+      "step": 10000
+    },
+    {
+      "epoch": 0.59,
+      "eval_loss": 1.8349609375,
+      "eval_runtime": 5.8764,
+      "eval_samples_per_second": 231.946,
+      "eval_steps_per_second": 29.1,
+      "step": 10000
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.0001,
+      "loss": 1.8281,
+      "step": 12500
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 0.0001,
+      "loss": 1.7953,
+      "step": 15000
+    },
+    {
+      "epoch": 0.88,
+      "eval_loss": 1.7861328125,
+      "eval_runtime": 5.856,
+      "eval_samples_per_second": 232.753,
+      "eval_steps_per_second": 29.201,
+      "step": 15000
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 0.0001,
+      "loss": 1.7593,
+      "step": 17500
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 0.0001,
+      "loss": 1.6602,
+      "step": 20000
+    },
+    {
+      "epoch": 1.17,
+      "eval_loss": 1.7548828125,
+      "eval_runtime": 5.8587,
+      "eval_samples_per_second": 232.645,
+      "eval_steps_per_second": 29.187,
+      "step": 20000
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 0.0001,
+      "loss": 1.672,
+      "step": 22500
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 0.0001,
+      "loss": 1.6639,
+      "step": 25000
+    },
+    {
+      "epoch": 1.46,
+      "eval_loss": 1.734375,
+      "eval_runtime": 5.8469,
+      "eval_samples_per_second": 233.117,
+      "eval_steps_per_second": 29.246,
+      "step": 25000
+    },
+    {
+      "epoch": 1.46,
+      "step": 25000,
+      "total_flos": 8.355380415011226e+17,
+      "train_loss": 1.84288763671875,
+      "train_runtime": 4774.5297,
+      "train_samples_per_second": 41.889,
+      "train_steps_per_second": 5.236
+    }
+  ],
+  "max_steps": 25000,
+  "num_train_epochs": 2,
+  "total_flos": 8.355380415011226e+17,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b1fc4799d19f9cf812846bc0319e58fba92051b415fdd82bfff5aa88e054b3d
+size 4399