merge with original checkpoint

.ipynb_checkpoints/README-checkpoint.md

@@ -1,9 +0,0 @@
-# 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

@@ -1,33 +0,0 @@
-{
-  "_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

@@ -1,7 +0,0 @@
-{
-  "_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

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

.ipynb_checkpoints/trainer_state-checkpoint.json

@@ -1,40 +0,0 @@
-{
-  "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
-}

config.json

@@ -26,7 +26,7 @@
   "skip_bias_add_qkv": false,
   "slow_but_exact": false,
   "torch_dtype": "float32",
-  "transformers_version": "4.26.1",
+  "transformers_version": "4.26.0",
   "unk_token_id": 0,
   "use_cache": true,
   "vocab_size": 250880

generation_config.json

@@ -3,5 +3,5 @@
   "bos_token_id": 1,
   "eos_token_id": 2,
   "pad_token_id": 3,
-  "transformers_version": "4.26.1"
+  "transformers_version": "4.26.0"
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:02ef085fe37a106a3fb692691cb9e642f8861180f11d31306ad41e900d06546e
+oid sha256:ebdc1aa009b64e273ef3c22b6dfd7f68808593b98257d945b4637719f258b858
 size 6889734991