init

.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

.ipynb_checkpoints/README-checkpoint.md

@@ -0,0 +1,9 @@
+# Bloom 1B7 LightNovel ZH_CN
+
+BigScience Large Open-science Open-access Multilingual Language Model with 1.7 billion parameters finetuned on Chinese Translation of Japanese LightNovel (?)
+
+**WARN: Inferior to pre-trained models**
+
+Checkpoint Merging is highly recommended.
+
+> Trained by Rorical

.ipynb_checkpoints/config-checkpoint.json

@@ -0,0 +1,33 @@
+{
+  "_name_or_path": "train",
+  "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": 2048,
+  "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": 2,
+  "seq_length": 4096,
+  "skip_bias_add": true,
+  "skip_bias_add_qkv": false,
+  "slow_but_exact": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.26.1",
+  "unk_token_id": 0,
+  "use_cache": true,
+  "vocab_size": 250880
+}

.ipynb_checkpoints/generation_config-checkpoint.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 3,
+  "transformers_version": "4.26.1"
+}

.ipynb_checkpoints/special_tokens_map-checkpoint.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
+}

.ipynb_checkpoints/trainer_state-checkpoint.json

@@ -0,0 +1,40 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.1422453249640382,
+  "global_step": 4351,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03,
+      "learning_rate": 9.880633522535375e-07,
+      "loss": 3.095,
+      "step": 1000
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 9.86918398092553e-07,
+      "loss": 3.1041,
+      "step": 2000
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 9.857217434943726e-07,
+      "loss": 3.0942,
+      "step": 3000
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 9.84473515518409e-07,
+      "loss": 3.0985,
+      "step": 4000
+    }
+  ],
+  "max_steps": 305880,
+  "num_train_epochs": 10,
+  "total_flos": 1.577214365663232e+16,
+  "trial_name": null,
+  "trial_params": null
+}

README.md

@@ -0,0 +1,9 @@
+# Bloom 1B7 LightNovel ZH_CN
+
+BigScience Large Open-science Open-access Multilingual Language Model with 1.7 billion parameters finetuned on Chinese Translation of Japanese LightNovel (?)
+
+**WARN: Inferior to pre-trained models**
+
+Checkpoint Merging is highly recommended.
+
+> Trained by Rorical

config.json

@@ -0,0 +1,33 @@
+{
+  "_name_or_path": "bloom-1b7-lightnovel",
+  "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": 2048,
+  "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": 2,
+  "seq_length": 4096,
+  "skip_bias_add": true,
+  "skip_bias_add_qkv": false,
+  "slow_but_exact": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.26.1",
+  "unk_token_id": 0,
+  "use_cache": true,
+  "vocab_size": 250880
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 3,
+  "transformers_version": "4.26.1"
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02ef085fe37a106a3fb692691cb9e642f8861180f11d31306ad41e900d06546e
+size 6889734991

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
+}

tokenizer.json

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

tokenizer_config.json

@@ -0,0 +1,12 @@
+{
+  "add_prefix_space": false,
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "model_max_length": 1000000000000000019884624838656,
+  "name_or_path": "train",
+  "pad_token": "<pad>",
+  "padding_side": "left",
+  "special_tokens_map_file": null,
+  "tokenizer_class": "BloomTokenizer",
+  "unk_token": "<unk>"
+}

trainer_state.json

@@ -0,0 +1,40 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.1422453249640382,
+  "global_step": 4351,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03,
+      "learning_rate": 9.880633522535375e-07,
+      "loss": 3.095,
+      "step": 1000
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 9.86918398092553e-07,
+      "loss": 3.1041,
+      "step": 2000
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 9.857217434943726e-07,
+      "loss": 3.0942,
+      "step": 3000
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 9.84473515518409e-07,
+      "loss": 3.0985,
+      "step": 4000
+    }
+  ],
+  "max_steps": 305880,
+  "num_train_epochs": 10,
+  "total_flos": 1.577214365663232e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd3e23e8982cbd944a396a304da401f14fb0be60847f84735dc33e767e222044
+size 3439