初始化项目，由ModelHub XC社区提供模型

Model: CLMBR/binding-c-command-transformer-0 Source: Original Platform
2026-05-13 00:06:34 +08:00
commit ebb5822657
449 changed files with 2795966 additions and 0 deletions
--- a/.gitattributes
+++ b/.gitattributes
@@ -0,0 +1,35 @@
+*.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
+*.ckpt 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
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* 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
--- a/README.md
+++ b/README.md
@@ -0,0 +1,94 @@
+---
+tags:
+- generated_from_trainer
+model-index:
+- name: binding-c-command-transformer-0
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# binding-c-command-transformer-0
+
+This model is a fine-tuned version of [](https://huggingface.co/) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 3.8623
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-05
+- train_batch_size: 32
+- eval_batch_size: 32
+- seed: 0
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- training_steps: 3052726
+
+### Training results
+
+| Training Loss | Epoch | Step    | Validation Loss |
+|:-------------:|:-----:|:-------:|:---------------:|
+| 4.2256        | 0.03  | 76320   | 4.1939          |
+| 4.0197        | 1.03  | 152640  | 4.0263          |
+| 3.9124        | 0.03  | 228960  | 3.9521          |
+| 3.8474        | 1.03  | 305280  | 3.9113          |
+| 3.7939        | 0.03  | 381600  | 3.8862          |
+| 3.7531        | 1.03  | 457920  | 3.8701          |
+| 3.7234        | 0.03  | 534240  | 3.8589          |
+| 3.6922        | 1.03  | 610560  | 3.8521          |
+| 3.6629        | 0.03  | 686880  | 3.8485          |
+| 3.6356        | 1.03  | 763200  | 3.8451          |
+| 3.6128        | 0.03  | 839520  | 3.8436          |
+| 3.5929        | 1.03  | 915840  | 3.8429          |
+| 3.574         | 0.03  | 992160  | 3.8428          |
+| 3.5508        | 1.03  | 1068480 | 3.8433          |
+| 3.5355        | 0.03  | 1144800 | 3.8435          |
+| 3.5278        | 1.03  | 1221120 | 3.8453          |
+| 3.5109        | 0.03  | 1297440 | 3.8459          |
+| 3.4986        | 0.03  | 1373760 | 3.8483          |
+| 3.4819        | 1.03  | 1450080 | 3.8498          |
+| 3.4765        | 0.03  | 1526400 | 3.8518          |
+| 3.4654        | 0.03  | 1602720 | 3.8523          |
+| 3.4555        | 1.03  | 1679040 | 3.8527          |
+| 3.4499        | 0.03  | 1755360 | 3.8555          |
+| 3.4399        | 0.03  | 1831680 | 3.8558          |
+| 3.4253        | 0.03  | 1908000 | 3.8577          |
+| 3.4113        | 1.03  | 1984320 | 3.8580          |
+| 3.4005        | 0.03  | 2060640 | 3.8599          |
+| 3.3919        | 1.03  | 2136960 | 3.8617          |
+| 3.3804        | 0.03  | 2213280 | 3.8617          |
+| 3.3655        | 0.03  | 2289600 | 3.8638          |
+| 3.3548        | 1.03  | 2365920 | 3.8634          |
+| 3.353         | 0.03  | 2442240 | 3.8643          |
+| 3.3392        | 1.03  | 2518560 | 3.8654          |
+| 3.3291        | 0.03  | 2594880 | 3.8651          |
+| 3.3208        | 1.03  | 2671200 | 3.8650          |
+| 3.3177        | 0.03  | 2747520 | 3.8656          |
+| 3.3077        | 0.03  | 2823840 | 3.8655          |
+| 3.3017        | 0.03  | 2900160 | 3.8646          |
+| 3.3002        | 1.03  | 2976480 | 3.8635          |
+| 3.2939        | 0.02  | 3052726 | 3.8623          |
+
+
+### Framework versions
+
+- Transformers 4.33.3
+- Pytorch 2.0.1
+- Datasets 2.12.0
+- Tokenizers 0.13.3
--- a/checkpoint-1068480/config.json
+++ b/checkpoint-1068480/config.json
@@ -0,0 +1,28 @@
+{
+  "_remove_final_layer_norm": false,
+  "activation_function": "relu",
+  "architectures": [
+    "OPTForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 2,
+  "do_layer_norm_before": true,
+  "dropout": 0.1,
+  "enable_bias": true,
+  "eos_token_id": 2,
+  "ffn_dim": 768,
+  "hidden_size": 768,
+  "init_std": 0.02,
+  "layer_norm_elementwise_affine": true,
+  "layerdrop": 0.0,
+  "max_position_embeddings": 512,
+  "model_type": "opt",
+  "num_attention_heads": 8,
+  "num_hidden_layers": 8,
+  "pad_token_id": 1,
+  "torch_dtype": "float32",
+  "transformers_version": "4.33.3",
+  "use_cache": true,
+  "vocab_size": 50002,
+  "word_embed_proj_dim": 768
+}
--- a/checkpoint-1068480/generation_config.json
+++ b/checkpoint-1068480/generation_config.json
@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 2,
+  "eos_token_id": 2,
+  "pad_token_id": 1,
+  "transformers_version": "4.33.3"
+}
--- a/checkpoint-1068480/optimizer.pt
+++ b/checkpoint-1068480/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06e0dfbb48bdf11ac8760d0045c24d442c67f87590a1812ea28c31cfe5acc4b0
+size 537476677
--- a/checkpoint-1068480/pytorch_model.bin
+++ b/checkpoint-1068480/pytorch_model.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1481d73040db51918c8a6e67f5d1427b459750089b98aef9deffe3e5232eb985
+size 268727709
--- a/checkpoint-1068480/rng_state.pth
+++ b/checkpoint-1068480/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4fe953f11c8ec724e637e5635e620d806c837324aeb9487a93cdc3b604d0a80
+size 14511
--- a/checkpoint-1068480/scheduler.pt
+++ b/checkpoint-1068480/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:669fc6711ce5de4dc8f34684671b00f9a9a4235d3a385d716c7747dee089d1ad
+size 627
--- a/checkpoint-1068480/special_tokens_map.json
+++ b/checkpoint-1068480/special_tokens_map.json
@@ -0,0 +1,5 @@
+{
+  "eos_token": "<eos>",
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
+}
--- a/checkpoint-1068480/tokenizer.json
+++ b/checkpoint-1068480/tokenizer.json
--- a/checkpoint-1068480/tokenizer_config.json
+++ b/checkpoint-1068480/tokenizer_config.json
@@ -0,0 +1,12 @@
+{
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<eos>",
+  "max_length": null,
+  "model_max_length": 512,
+  "pad_to_multiple_of": null,
+  "pad_token": "<pad>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "unk_token": "<unk>"
+}
--- a/checkpoint-1068480/trainer_state.json
+++ b/checkpoint-1068480/trainer_state.json
--- a/checkpoint-1068480/training_args.bin
+++ b/checkpoint-1068480/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5229138d9ed9691255edbe60222383e9e3ae145c84102f7a2fef5dab3f7c7ec
+size 4283
--- a/checkpoint-1144800/config.json
+++ b/checkpoint-1144800/config.json
@@ -0,0 +1,28 @@
+{
+  "_remove_final_layer_norm": false,
+  "activation_function": "relu",
+  "architectures": [
+    "OPTForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 2,
+  "do_layer_norm_before": true,
+  "dropout": 0.1,
+  "enable_bias": true,
+  "eos_token_id": 2,
+  "ffn_dim": 768,
+  "hidden_size": 768,
+  "init_std": 0.02,
+  "layer_norm_elementwise_affine": true,
+  "layerdrop": 0.0,
+  "max_position_embeddings": 512,
+  "model_type": "opt",
+  "num_attention_heads": 8,
+  "num_hidden_layers": 8,
+  "pad_token_id": 1,
+  "torch_dtype": "float32",
+  "transformers_version": "4.33.3",
+  "use_cache": true,
+  "vocab_size": 50002,
+  "word_embed_proj_dim": 768
+}
--- a/checkpoint-1144800/generation_config.json
+++ b/checkpoint-1144800/generation_config.json
@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 2,
+  "eos_token_id": 2,
+  "pad_token_id": 1,
+  "transformers_version": "4.33.3"
+}
--- a/checkpoint-1144800/optimizer.pt
+++ b/checkpoint-1144800/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:861abde63c41a20e8de27a36c1d1ef0d6f0fcf7d19f5445290aa7d20a6f024d2
+size 537476677
--- a/checkpoint-1144800/pytorch_model.bin
+++ b/checkpoint-1144800/pytorch_model.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06504965383b02ad79060984ad602da203fa22610647645c7d1c392eb27ddac6
+size 268727709
--- a/checkpoint-1144800/rng_state.pth
+++ b/checkpoint-1144800/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a25646f48be545d3e982392672f05d2c39b66dbb0924151cc573f966c20c8c8
+size 14511
--- a/checkpoint-1144800/scheduler.pt
+++ b/checkpoint-1144800/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:991874359691c2217a027160df38c8e34fee145755af1e5cfc66e845b3b8a830
+size 627
--- a/checkpoint-1144800/special_tokens_map.json
+++ b/checkpoint-1144800/special_tokens_map.json
@@ -0,0 +1,5 @@
+{
+  "eos_token": "<eos>",
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
+}
--- a/checkpoint-1144800/tokenizer.json
+++ b/checkpoint-1144800/tokenizer.json
--- a/checkpoint-1144800/tokenizer_config.json
+++ b/checkpoint-1144800/tokenizer_config.json
@@ -0,0 +1,12 @@
+{
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<eos>",
+  "max_length": null,
+  "model_max_length": 512,
+  "pad_to_multiple_of": null,
+  "pad_token": "<pad>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "unk_token": "<unk>"
+}
--- a/checkpoint-1144800/trainer_state.json
+++ b/checkpoint-1144800/trainer_state.json
--- a/checkpoint-1144800/training_args.bin
+++ b/checkpoint-1144800/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1652c334a334b4c980df90255117f883f4b9e88406c1245f824406c5b1314d92
+size 4283
--- a/checkpoint-1221120/config.json
+++ b/checkpoint-1221120/config.json
@@ -0,0 +1,28 @@
+{
+  "_remove_final_layer_norm": false,
+  "activation_function": "relu",
+  "architectures": [
+    "OPTForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 2,
+  "do_layer_norm_before": true,
+  "dropout": 0.1,
+  "enable_bias": true,
+  "eos_token_id": 2,
+  "ffn_dim": 768,
+  "hidden_size": 768,
+  "init_std": 0.02,
+  "layer_norm_elementwise_affine": true,
+  "layerdrop": 0.0,
+  "max_position_embeddings": 512,
+  "model_type": "opt",
+  "num_attention_heads": 8,
+  "num_hidden_layers": 8,
+  "pad_token_id": 1,
+  "torch_dtype": "float32",
+  "transformers_version": "4.33.3",
+  "use_cache": true,
+  "vocab_size": 50002,
+  "word_embed_proj_dim": 768
+}
--- a/checkpoint-1221120/generation_config.json
+++ b/checkpoint-1221120/generation_config.json
@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 2,
+  "eos_token_id": 2,
+  "pad_token_id": 1,
+  "transformers_version": "4.33.3"
+}
--- a/checkpoint-1221120/optimizer.pt
+++ b/checkpoint-1221120/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c5cd390ae390e9ae59dd3a1701d1022817e11b3d55df83a92594b1ac62367f4
+size 537476677
--- a/checkpoint-1221120/pytorch_model.bin
+++ b/checkpoint-1221120/pytorch_model.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:273c3abf65ea8a460129a20def64065167ed87ca2f743c6dad692fff0d038fb8
+size 268727709
--- a/checkpoint-1221120/rng_state.pth
+++ b/checkpoint-1221120/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c3d46a5d8105fd6efb14de0ba8fafeca0fa12292c512cb6e2232a2676b2030d
+size 14511
--- a/checkpoint-1221120/scheduler.pt
+++ b/checkpoint-1221120/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d06a6bfbe036b1d7476af1641f9e10bb33caa7016386fcd078043563b4bd86b
+size 627
--- a/checkpoint-1221120/special_tokens_map.json
+++ b/checkpoint-1221120/special_tokens_map.json
@@ -0,0 +1,5 @@
+{
+  "eos_token": "<eos>",
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
+}
--- a/checkpoint-1221120/tokenizer.json
+++ b/checkpoint-1221120/tokenizer.json
--- a/checkpoint-1221120/tokenizer_config.json
+++ b/checkpoint-1221120/tokenizer_config.json
@@ -0,0 +1,12 @@
+{
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<eos>",
+  "max_length": null,
+  "model_max_length": 512,
+  "pad_to_multiple_of": null,
+  "pad_token": "<pad>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "unk_token": "<unk>"
+}
--- a/checkpoint-1221120/trainer_state.json
+++ b/checkpoint-1221120/trainer_state.json
--- a/checkpoint-1221120/training_args.bin
+++ b/checkpoint-1221120/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1652c334a334b4c980df90255117f883f4b9e88406c1245f824406c5b1314d92
+size 4283
--- a/checkpoint-1297440/config.json
+++ b/checkpoint-1297440/config.json
@@ -0,0 +1,28 @@
+{
+  "_remove_final_layer_norm": false,
+  "activation_function": "relu",
+  "architectures": [
+    "OPTForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 2,
+  "do_layer_norm_before": true,
+  "dropout": 0.1,
+  "enable_bias": true,
+  "eos_token_id": 2,
+  "ffn_dim": 768,
+  "hidden_size": 768,
+  "init_std": 0.02,
+  "layer_norm_elementwise_affine": true,
+  "layerdrop": 0.0,
+  "max_position_embeddings": 512,
+  "model_type": "opt",
+  "num_attention_heads": 8,
+  "num_hidden_layers": 8,
+  "pad_token_id": 1,
+  "torch_dtype": "float32",
+  "transformers_version": "4.33.3",
+  "use_cache": true,
+  "vocab_size": 50002,
+  "word_embed_proj_dim": 768
+}
--- a/checkpoint-1297440/generation_config.json
+++ b/checkpoint-1297440/generation_config.json
@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 2,
+  "eos_token_id": 2,
+  "pad_token_id": 1,
+  "transformers_version": "4.33.3"
+}
--- a/checkpoint-1297440/optimizer.pt
+++ b/checkpoint-1297440/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4d48c8fa4315b9ab0457cc1f00a11169ff120ea4abae36422ab33a5b918dcc5
+size 537476677
--- a/checkpoint-1297440/pytorch_model.bin
+++ b/checkpoint-1297440/pytorch_model.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a381d621e2a988ecf2e8516e7958efd3fff60cb2d299a27430fa359b923f6d0a
+size 268727709
--- a/checkpoint-1297440/rng_state.pth
+++ b/checkpoint-1297440/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94b4aba0ec230354eb5315807b409a61c7b962fe62f1af4aa35378f0e5610e9a
+size 14511
--- a/checkpoint-1297440/scheduler.pt
+++ b/checkpoint-1297440/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba66efed1afd681fe0a25b3382b25ce7a059165f5b8144dbb1444c2335af9876
+size 627
--- a/checkpoint-1297440/special_tokens_map.json
+++ b/checkpoint-1297440/special_tokens_map.json
@@ -0,0 +1,5 @@
+{
+  "eos_token": "<eos>",
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
+}
--- a/checkpoint-1297440/tokenizer.json
+++ b/checkpoint-1297440/tokenizer.json
--- a/checkpoint-1297440/tokenizer_config.json
+++ b/checkpoint-1297440/tokenizer_config.json
@@ -0,0 +1,12 @@
+{
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<eos>",
+  "max_length": null,
+  "model_max_length": 512,
+  "pad_to_multiple_of": null,
+  "pad_token": "<pad>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "unk_token": "<unk>"
+}
--- a/checkpoint-1297440/trainer_state.json
+++ b/checkpoint-1297440/trainer_state.json
--- a/checkpoint-1297440/training_args.bin
+++ b/checkpoint-1297440/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad5f89b0419003305a2dc4fa64e75300d77bf8a7c979bdde9222346a4029724f
+size 4283
--- a/checkpoint-1373760/config.json
+++ b/checkpoint-1373760/config.json
@@ -0,0 +1,28 @@
+{
+  "_remove_final_layer_norm": false,
+  "activation_function": "relu",
+  "architectures": [
+    "OPTForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 2,
+  "do_layer_norm_before": true,
+  "dropout": 0.1,
+  "enable_bias": true,
+  "eos_token_id": 2,
+  "ffn_dim": 768,
+  "hidden_size": 768,
+  "init_std": 0.02,
+  "layer_norm_elementwise_affine": true,
+  "layerdrop": 0.0,
+  "max_position_embeddings": 512,
+  "model_type": "opt",
+  "num_attention_heads": 8,
+  "num_hidden_layers": 8,
+  "pad_token_id": 1,
+  "torch_dtype": "float32",
+  "transformers_version": "4.33.3",
+  "use_cache": true,
+  "vocab_size": 50002,
+  "word_embed_proj_dim": 768
+}
--- a/checkpoint-1373760/generation_config.json
+++ b/checkpoint-1373760/generation_config.json
@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 2,
+  "eos_token_id": 2,
+  "pad_token_id": 1,
+  "transformers_version": "4.33.3"
+}
--- a/checkpoint-1373760/optimizer.pt
+++ b/checkpoint-1373760/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41294bc14ebb53179131f6cdabc1e0f89c0f5a807d861a4340d97737b2a2a1d4
+size 537476677
--- a/checkpoint-1373760/pytorch_model.bin
+++ b/checkpoint-1373760/pytorch_model.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4d35b53b9660df2ecdb6de7c752b56db9f2970a083e2aadedc8f67373c0eaad
+size 268727709
--- a/checkpoint-1373760/rng_state.pth
+++ b/checkpoint-1373760/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a57d741e3cb18402e2be0de3ed994347c9a9d7c0b6ffc626c9711364636822e
+size 14511
--- a/checkpoint-1373760/scheduler.pt
+++ b/checkpoint-1373760/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4cc11c09c8254d06ee87c9b64c88187bf80ee83d649216f0b87383686a546cef
+size 627
--- a/checkpoint-1373760/special_tokens_map.json
+++ b/checkpoint-1373760/special_tokens_map.json
@@ -0,0 +1,5 @@
+{
+  "eos_token": "<eos>",
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
+}
--- a/checkpoint-1373760/tokenizer.json
+++ b/checkpoint-1373760/tokenizer.json
--- a/checkpoint-1373760/tokenizer_config.json
+++ b/checkpoint-1373760/tokenizer_config.json
@@ -0,0 +1,12 @@
+{
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<eos>",
+  "max_length": null,
+  "model_max_length": 512,
+  "pad_to_multiple_of": null,
+  "pad_token": "<pad>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "unk_token": "<unk>"
+}
--- a/checkpoint-1373760/trainer_state.json
+++ b/checkpoint-1373760/trainer_state.json
--- a/checkpoint-1373760/training_args.bin
+++ b/checkpoint-1373760/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3bd6a13ea616b506f6177ad9a11b2f499ad09d181ad6ec3c3975974b8013f99
+size 4283
--- a/checkpoint-1450080/config.json
+++ b/checkpoint-1450080/config.json
@@ -0,0 +1,28 @@
+{
+  "_remove_final_layer_norm": false,
+  "activation_function": "relu",
+  "architectures": [
+    "OPTForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 2,
+  "do_layer_norm_before": true,
+  "dropout": 0.1,
+  "enable_bias": true,
+  "eos_token_id": 2,
+  "ffn_dim": 768,
+  "hidden_size": 768,
+  "init_std": 0.02,
+  "layer_norm_elementwise_affine": true,
+  "layerdrop": 0.0,
+  "max_position_embeddings": 512,
+  "model_type": "opt",
+  "num_attention_heads": 8,
+  "num_hidden_layers": 8,
+  "pad_token_id": 1,
+  "torch_dtype": "float32",
+  "transformers_version": "4.33.3",
+  "use_cache": true,
+  "vocab_size": 50002,
+  "word_embed_proj_dim": 768
+}
--- a/checkpoint-1450080/generation_config.json
+++ b/checkpoint-1450080/generation_config.json
@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 2,
+  "eos_token_id": 2,
+  "pad_token_id": 1,
+  "transformers_version": "4.33.3"
+}
--- a/checkpoint-1450080/optimizer.pt
+++ b/checkpoint-1450080/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d7fdd38c3541ca72338ea84c3a6e87a876398710215df9ac498b13f8db1274f
+size 537476677
--- a/checkpoint-1450080/pytorch_model.bin
+++ b/checkpoint-1450080/pytorch_model.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9cd740ae904c75c009773edeaf036f7dc3f38ad6ceabd5e372c53a23213c4168
+size 268727709
--- a/checkpoint-1450080/rng_state.pth
+++ b/checkpoint-1450080/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8acd149b37df738cea73e2a77e1c43f09e19b3c0c93fea767bb0c444a06c0e70
+size 14511
--- a/checkpoint-1450080/scheduler.pt
+++ b/checkpoint-1450080/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bcbdbb3f93cb7bafa1e3e23b4e3b22d7c72bc4cdd0935f9079d8b35600aa9e0b
+size 627
--- a/checkpoint-1450080/special_tokens_map.json
+++ b/checkpoint-1450080/special_tokens_map.json
@@ -0,0 +1,5 @@
+{
+  "eos_token": "<eos>",
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
+}
--- a/checkpoint-1450080/tokenizer.json
+++ b/checkpoint-1450080/tokenizer.json
--- a/checkpoint-1450080/tokenizer_config.json
+++ b/checkpoint-1450080/tokenizer_config.json
@@ -0,0 +1,12 @@
+{
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<eos>",
+  "max_length": null,
+  "model_max_length": 512,
+  "pad_to_multiple_of": null,
+  "pad_token": "<pad>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "unk_token": "<unk>"
+}
--- a/checkpoint-1450080/trainer_state.json
+++ b/checkpoint-1450080/trainer_state.json
--- a/checkpoint-1450080/training_args.bin
+++ b/checkpoint-1450080/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3bd6a13ea616b506f6177ad9a11b2f499ad09d181ad6ec3c3975974b8013f99
+size 4283
--- a/checkpoint-152640/config.json
+++ b/checkpoint-152640/config.json
@@ -0,0 +1,28 @@
+{
+  "_remove_final_layer_norm": false,
+  "activation_function": "relu",
+  "architectures": [
+    "OPTForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 2,
+  "do_layer_norm_before": true,
+  "dropout": 0.1,
+  "enable_bias": true,
+  "eos_token_id": 2,
+  "ffn_dim": 768,
+  "hidden_size": 768,
+  "init_std": 0.02,
+  "layer_norm_elementwise_affine": true,
+  "layerdrop": 0.0,
+  "max_position_embeddings": 512,
+  "model_type": "opt",
+  "num_attention_heads": 8,
+  "num_hidden_layers": 8,
+  "pad_token_id": 1,
+  "torch_dtype": "float32",
+  "transformers_version": "4.33.3",
+  "use_cache": true,
+  "vocab_size": 50002,
+  "word_embed_proj_dim": 768
+}
--- a/checkpoint-152640/generation_config.json
+++ b/checkpoint-152640/generation_config.json
@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 2,
+  "eos_token_id": 2,
+  "pad_token_id": 1,
+  "transformers_version": "4.33.3"
+}
--- a/checkpoint-152640/optimizer.pt
+++ b/checkpoint-152640/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8a8fcfede49f446a2d317c17e40320633a9a77ed197051d13ef57b42e76ce9d
+size 537476677
--- a/checkpoint-152640/pytorch_model.bin
+++ b/checkpoint-152640/pytorch_model.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c04b29530adf964a35e2f0b459a20636f94cb18a322bce3e5fce4de19d27bf6
+size 268727709
--- a/checkpoint-152640/rng_state.pth
+++ b/checkpoint-152640/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:285be4bb9d931265abea162b1a5d0ab2ad5240d3058bcb71325cb562494be067
+size 14511
--- a/checkpoint-152640/scheduler.pt
+++ b/checkpoint-152640/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6c5323fc8fae82b83eafaf3bb1a976887bef291e41ff85dcba601b508b96a45
+size 627
--- a/checkpoint-152640/special_tokens_map.json
+++ b/checkpoint-152640/special_tokens_map.json
@@ -0,0 +1,5 @@
+{
+  "eos_token": "<eos>",
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
+}
--- a/checkpoint-152640/tokenizer.json
+++ b/checkpoint-152640/tokenizer.json
--- a/checkpoint-152640/tokenizer_config.json
+++ b/checkpoint-152640/tokenizer_config.json
@@ -0,0 +1,12 @@
+{
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<eos>",
+  "max_length": null,
+  "model_max_length": 512,
+  "pad_to_multiple_of": null,
+  "pad_token": "<pad>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "unk_token": "<unk>"
+}
--- a/checkpoint-152640/trainer_state.json
+++ b/checkpoint-152640/trainer_state.json
--- a/checkpoint-152640/training_args.bin
+++ b/checkpoint-152640/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a91d2b0a38436f5afc3421ea38cc33a6e13ce6f6369a89f61bb1730476270d44
+size 4283
--- a/checkpoint-1526400/config.json
+++ b/checkpoint-1526400/config.json
@@ -0,0 +1,28 @@
+{
+  "_remove_final_layer_norm": false,
+  "activation_function": "relu",
+  "architectures": [
+    "OPTForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 2,
+  "do_layer_norm_before": true,
+  "dropout": 0.1,
+  "enable_bias": true,
+  "eos_token_id": 2,
+  "ffn_dim": 768,
+  "hidden_size": 768,
+  "init_std": 0.02,
+  "layer_norm_elementwise_affine": true,
+  "layerdrop": 0.0,
+  "max_position_embeddings": 512,
+  "model_type": "opt",
+  "num_attention_heads": 8,
+  "num_hidden_layers": 8,
+  "pad_token_id": 1,
+  "torch_dtype": "float32",
+  "transformers_version": "4.33.3",
+  "use_cache": true,
+  "vocab_size": 50002,
+  "word_embed_proj_dim": 768
+}
--- a/checkpoint-1526400/generation_config.json
+++ b/checkpoint-1526400/generation_config.json
@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 2,
+  "eos_token_id": 2,
+  "pad_token_id": 1,
+  "transformers_version": "4.33.3"
+}
--- a/checkpoint-1526400/optimizer.pt
+++ b/checkpoint-1526400/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f310440aa665dbf1657df09f3166cfefeab13ee09874e8d172e6d072e7cf2bd7
+size 537476677
--- a/checkpoint-1526400/pytorch_model.bin
+++ b/checkpoint-1526400/pytorch_model.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:094fe9a99ce5808138a0dff61364659b420888b536e9f71ef44dd29990269e93
+size 268727709
--- a/checkpoint-1526400/rng_state.pth
+++ b/checkpoint-1526400/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7de44cf345d19d914f7c9973e799750f05ae4508d8c4a825a43aa49b81a6419
+size 14511
--- a/checkpoint-1526400/scheduler.pt
+++ b/checkpoint-1526400/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd1dc78dfa4f7f434796c31bc3d5f9dfe6949a9ef1e9e97ba700ccb44f8f5584
+size 627
--- a/checkpoint-1526400/special_tokens_map.json
+++ b/checkpoint-1526400/special_tokens_map.json
@@ -0,0 +1,5 @@
+{
+  "eos_token": "<eos>",
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
+}
--- a/checkpoint-1526400/tokenizer.json
+++ b/checkpoint-1526400/tokenizer.json
--- a/checkpoint-1526400/tokenizer_config.json
+++ b/checkpoint-1526400/tokenizer_config.json
@@ -0,0 +1,12 @@
+{
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<eos>",
+  "max_length": null,
+  "model_max_length": 512,
+  "pad_to_multiple_of": null,
+  "pad_token": "<pad>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "unk_token": "<unk>"
+}
--- a/checkpoint-1526400/trainer_state.json
+++ b/checkpoint-1526400/trainer_state.json
--- a/checkpoint-1526400/training_args.bin
+++ b/checkpoint-1526400/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b11486d528b04eedfbd63e8e6ebe12b486e55b0a9db5da90a72266596c8b4b1b
+size 4283
--- a/checkpoint-1602720/config.json
+++ b/checkpoint-1602720/config.json
@@ -0,0 +1,28 @@
+{
+  "_remove_final_layer_norm": false,
+  "activation_function": "relu",
+  "architectures": [
+    "OPTForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 2,
+  "do_layer_norm_before": true,
+  "dropout": 0.1,
+  "enable_bias": true,
+  "eos_token_id": 2,
+  "ffn_dim": 768,
+  "hidden_size": 768,
+  "init_std": 0.02,
+  "layer_norm_elementwise_affine": true,
+  "layerdrop": 0.0,
+  "max_position_embeddings": 512,
+  "model_type": "opt",
+  "num_attention_heads": 8,
+  "num_hidden_layers": 8,
+  "pad_token_id": 1,
+  "torch_dtype": "float32",
+  "transformers_version": "4.33.3",
+  "use_cache": true,
+  "vocab_size": 50002,
+  "word_embed_proj_dim": 768
+}
--- a/checkpoint-1602720/generation_config.json
+++ b/checkpoint-1602720/generation_config.json
@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 2,
+  "eos_token_id": 2,
+  "pad_token_id": 1,
+  "transformers_version": "4.33.3"
+}
--- a/checkpoint-1602720/optimizer.pt
+++ b/checkpoint-1602720/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c919ce9d9a43dcfbac906de00f166781dd224b4ff8d02435ce9ff63a5a1eb8a5
+size 537476677
--- a/checkpoint-1602720/pytorch_model.bin
+++ b/checkpoint-1602720/pytorch_model.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64ca562ac90b7f045e18a16e0e2105276c816b424e0af3fabdac0fcf0fff0c94
+size 268727709
--- a/checkpoint-1602720/rng_state.pth
+++ b/checkpoint-1602720/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f1ccfb132e5eda6454951cd0fe5c35b67ae0662800ddecbcdeaea2f16de62bf
+size 14511
--- a/checkpoint-1602720/scheduler.pt
+++ b/checkpoint-1602720/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8241a42214c250c9dce24ae3bedc371e68de47c3309bb12dfdf8c612232566e
+size 627
--- a/checkpoint-1602720/special_tokens_map.json
+++ b/checkpoint-1602720/special_tokens_map.json
@@ -0,0 +1,5 @@
+{
+  "eos_token": "<eos>",
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
+}
--- a/checkpoint-1602720/tokenizer.json
+++ b/checkpoint-1602720/tokenizer.json
--- a/checkpoint-1602720/tokenizer_config.json
+++ b/checkpoint-1602720/tokenizer_config.json
@@ -0,0 +1,12 @@
+{
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<eos>",
+  "max_length": null,
+  "model_max_length": 512,
+  "pad_to_multiple_of": null,
+  "pad_token": "<pad>",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "unk_token": "<unk>"
+}
--- a/checkpoint-1602720/trainer_state.json
+++ b/checkpoint-1602720/trainer_state.json
--- a/Show More
+++ b/Show More