初始化项目，由ModelHub XC社区提供模型

Model: CLMBR/full-transformer-0 Source: Original Platform
2026-05-22 15:00:24 +08:00
commit 43181ef4b3
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: full2-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. -->
+
+# full2-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: 3.8599
+
+## 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 |
+|:-------------:|:-----:|:-------:|:---------------:|
+| 4.2278        | 0.03  | 76320   | 4.1982          |
+| 4.022         | 1.03  | 152640  | 4.0277          |
+| 3.9114        | 0.03  | 228960  | 3.9531          |
+| 3.8457        | 1.03  | 305280  | 3.9114          |
+| 3.7937        | 0.03  | 381600  | 3.8858          |
+| 3.754         | 0.03  | 457920  | 3.8699          |
+| 3.7241        | 1.03  | 534240  | 3.8603          |
+| 3.6953        | 0.03  | 610560  | 3.8520          |
+| 3.6648        | 1.03  | 686880  | 3.8463          |
+| 3.6391        | 0.03  | 763200  | 3.8440          |
+| 3.6181        | 1.03  | 839520  | 3.8425          |
+| 3.5968        | 0.03  | 915840  | 3.8439          |
+| 3.5813        | 1.03  | 992160  | 3.8418          |
+| 3.5607        | 0.03  | 1068480 | 3.8427          |
+| 3.5409        | 1.03  | 1144800 | 3.8433          |
+| 3.5305        | 0.03  | 1221120 | 3.8444          |
+| 3.5122        | 1.03  | 1297440 | 3.8448          |
+| 3.4994        | 0.03  | 1373760 | 3.8457          |
+| 3.4845        | 1.03  | 1450080 | 3.8475          |
+| 3.4776        | 0.03  | 1526400 | 3.8493          |
+| 3.4657        | 1.03  | 1602720 | 3.8507          |
+| 3.4584        | 0.03  | 1679040 | 3.8513          |
+| 3.4537        | 1.03  | 1755360 | 3.8522          |
+| 3.4416        | 0.03  | 1831680 | 3.8545          |
+| 3.4273        | 0.03  | 1908000 | 3.8565          |
+| 3.4147        | 1.03  | 1984320 | 3.8564          |
+| 3.4051        | 0.03  | 2060640 | 3.8578          |
+| 3.3912        | 1.03  | 2136960 | 3.8585          |
+| 3.3848        | 0.03  | 2213280 | 3.8590          |
+| 3.3723        | 1.03  | 2289600 | 3.8598          |
+| 3.3586        | 0.03  | 2365920 | 3.8602          |
+| 3.3545        | 1.03  | 2442240 | 3.8610          |
+| 3.3408        | 0.03  | 2518560 | 3.8615          |
+| 3.3335        | 1.03  | 2594880 | 3.8624          |
+| 3.3191        | 0.03  | 2671200 | 3.8620          |
+| 3.3152        | 1.03  | 2747520 | 3.8622          |
+| 3.3084        | 0.03  | 2823840 | 3.8619          |
+| 3.3053        | 1.03  | 2900160 | 3.8617          |
+| 3.3031        | 0.03  | 2976480 | 3.8612          |
+| 3.2954        | 1.02  | 3052726 | 3.8599          |
+
+
+### 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 sha256:37c82da390ebd898e64af1416cd7d53b84cb954ea7bc52a601dc91252414877a
+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:ace2dc89c5c4fcf545726bc8626c0c0860667d00e74e9cc712a4c2863a90a284
+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 sha256:2fdba4ff9062120c10e1b5938d2ee7e17fc1c8f1e0e53a7787cc23b00dda38e9
+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:fd1b9594c052c801c64bf859d660905b982060313edb8cbf540cd83abdcd0453
+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:c505b102154a9ca6b729d2b8a9dbdd71647ad3d004be5a0cbdc833e3a3faebf9
+size 4219
--- 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 sha256:00eddbdd58ff16ba897c30680d3add8a418f79a35f81bdea6f128ae815c27daf
+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:dbee89fad17e90a0e38089a8b08e1bea354630e595c1bcd2f202d80edc5ec9f8
+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:d25c139b5ac9958ce8c8b2d04b150af06fca8f89cd8d83743c3d05fa505a318e
+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 sha256:7874666542368591a19a5d33c87c327c8db770a7b618288ee6b8e662ac41d4dd
+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:c505b102154a9ca6b729d2b8a9dbdd71647ad3d004be5a0cbdc833e3a3faebf9
+size 4219
--- 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 sha256:184c69ca6948684cbf0ddae7d431af7ea181064c3f75932cde93b4a05ae1778d
+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 sha256:58bce622efc6bc6037cbbc16da2de818c2d3b4c21c203e56f2ee43e78658c5f9
+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 sha256:6a05f71c4c208ebd481a8b1d18ed7407bfeba9ffb8b63aaaf74013c5676cc03c
+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 sha256:43de3a8505e4e989740095904c6f74dad74ec46aacdf52d765861dbce93cf324
+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 sha256:4ba352bde458c9147acbff8059b4424252c57ec038e4dca7fe49f4e1557d6b70
+size 4219
--- 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 sha256:52eb09b53f6e9ecf5302432de223b6b9c1f5200cc0b743a6e855c188665d8596
+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:f5bfe26442af0176b2e9099eddcda429aa2241518e96a22d9847f08b366168aa
+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 sha256:94f65cec749f3de9884f6bd516bb467e55d145297848c5cde650d9408b72ca1b
+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 sha256:09c317e5b50c77b6e746bcae158add9ac159c4c4f2f7ca6e38b41d0207efbd3d
+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 sha256:4ba352bde458c9147acbff8059b4424252c57ec038e4dca7fe49f4e1557d6b70
+size 4219
--- 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 sha256:5a392e491de5b15ee653b59bb119de8c0c2ddbe1f5dde210254d6527625584ad
+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 sha256:44851e914c687271a0b828fe0267b647e88789b575195120fbf08ffc957419ea
+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 sha256:64240b7531b0532cf8af52e978111383b8e628ece65925cc6e0067c842cad721
+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 sha256:78d2f18eafa9caf17cc94fee87e204e4fbd7feeb8d79c7ad1f83f623ec26e3d5
+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:c7b0d3db05372989d5560f3aa9113ceb52d0837ad8aaabe588818b15da1f87a7
+size 4219
--- 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 sha256:264d775636d6c9cd7d4d6dc1b41226e5042c187f53b2d7a6215849c9c9a61534
+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 sha256:667c5d98378caec7e117eb9fe91f36a4aac61f83d6b2c7f842febf246933ae09
+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 sha256:92015b2516428bc2b80e6129b3c1a00eb450deb1cf67b1deb5ed2106d157f9df
+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 sha256:0f68d98c4c21274ed37c53276cb7640e9512cfc9268f8f4f853b05e51ed16c8a
+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:c7b0d3db05372989d5560f3aa9113ceb52d0837ad8aaabe588818b15da1f87a7
+size 4219
--- 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 sha256:4d80938eb5acddb4bf3fbc0cc5ea35936059a093043021bac06648e851e7480e
+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:a4a969fbdfb65046fc533f6afef6a4e80f5e0bbedf7b988f68ef99d67fe51b9f
+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 sha256:24e113c427f786461a285eeafe7c1c33a2da666d010ec05673c13eac234b2107
+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 sha256:3fe6cec8b325de5849955f7948d912672747776ccd3e6c323c13591d524918df
+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 sha256:0a2d6788fd9369a2b4e934b339d0fce1f4181b4e9a12be3f8b0c048743bfd510
+size 4219
--- 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 sha256:27234d7027a25099dee3d5240ea0cf5f94f7302c2b6d32e389fe21e3ce65e72a
+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 sha256:09294e20ecdc43e1d77a53aa70b3485a1609bb7b6d8fd8963b2f866c91c3516f
+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 sha256:3b68edcd2110f53945a6239162b67a8512963f1afff14b0873be345782da73e0
+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 sha256:74fd2d26e67294d018f94afffa0ef2c6393a78b02e7f7fcbdb42cb994b4315db
+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:a5a27fccec080556753dd5e798949856a08bcc3c76fe2f4dcca043c1e9b3f7ab
+size 4219
--- 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 sha256:73dce2a5eee2ecdbaa875c545759df5c547b1e42152bfdbad5aaca5ff21e9705
+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:e54f13a2083b664bc17c0523dbfb7b2dfb604a0d1f9c25d0d6b95f6b236d7b00
+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 sha256:88b32fa97bc659e8821b33f61b3e5f61774bfe667c2939cce5891ab573348c03
+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 sha256:5c5c14a41479ce4576ce6637b1b25595f9e40a4ea9232437578cf95dc7401987
+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