初始化项目，由ModelHub XC社区提供模型

Model: CLMBR/old-rel-cl-transformer-1 Source: Original Platform
2026-07-02 23:35:23 +08:00
commit 93d8953072
449 changed files with 2795954 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: rel-cl-transformer-1
+  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. -->
+
+# rel-cl-transformer-1
+
+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: 3.8714
+
+## 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: 1
+- 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 |
+|:-------------:|:-----:|:-------:|:---------------:|
+| 4.238         | 0.03  | 76319   | 4.2027          |
+| 4.0312        | 0.03  | 152638  | 4.0325          |
+| 3.9229        | 0.03  | 228957  | 3.9574          |
+| 3.8541        | 0.03  | 305276  | 3.9160          |
+| 3.8015        | 0.03  | 381595  | 3.8911          |
+| 3.7558        | 0.03  | 457914  | 3.8752          |
+| 3.7219        | 0.03  | 534233  | 3.8655          |
+| 3.6946        | 0.03  | 610552  | 3.8579          |
+| 3.6653        | 0.03  | 686871  | 3.8550          |
+| 3.6444        | 1.03  | 763190  | 3.8526          |
+| 3.6189        | 0.03  | 839510  | 3.8473          |
+| 3.5975        | 1.03  | 915830  | 3.8459          |
+| 3.5762        | 0.03  | 992150  | 3.8464          |
+| 3.5575        | 1.03  | 1068470 | 3.8480          |
+| 3.5455        | 0.03  | 1144790 | 3.8497          |
+| 3.5318        | 0.03  | 1221110 | 3.8518          |
+| 3.517         | 1.03  | 1297430 | 3.8527          |
+| 3.5041        | 0.03  | 1373750 | 3.8547          |
+| 3.4888        | 1.03  | 1450070 | 3.8556          |
+| 3.4806        | 0.03  | 1526390 | 3.8578          |
+| 3.4712        | 1.03  | 1602710 | 3.8586          |
+| 3.4613        | 0.03  | 1679030 | 3.8606          |
+| 3.4536        | 1.03  | 1755350 | 3.8624          |
+| 3.4406        | 0.03  | 1831670 | 3.8640          |
+| 3.4269        | 1.03  | 1907990 | 3.8642          |
+| 3.4133        | 0.03  | 1984310 | 3.8660          |
+| 3.4003        | 1.03  | 2060630 | 3.8680          |
+| 3.3918        | 0.03  | 2136950 | 3.8685          |
+| 3.3794        | 1.03  | 2213270 | 3.8700          |
+| 3.3659        | 0.03  | 2289590 | 3.8717          |
+| 3.3609        | 1.03  | 2365910 | 3.8721          |
+| 3.3533        | 0.03  | 2442230 | 3.8733          |
+| 3.3415        | 1.03  | 2518550 | 3.8731          |
+| 3.3346        | 0.03  | 2594870 | 3.8746          |
+| 3.3234        | 0.03  | 2671190 | 3.8746          |
+| 3.3165        | 1.03  | 2747510 | 3.8744          |
+| 3.3119        | 0.03  | 2823830 | 3.8745          |
+| 3.3058        | 1.03  | 2900150 | 3.8741          |
+| 3.2988        | 0.03  | 2976470 | 3.8729          |
+| 3.2923        | 1.02  | 3052726 | 3.8714          |
+
+
+### Framework versions
+
+- Transformers 4.33.3
+- Pytorch 2.0.1
+- Datasets 2.12.0
+- Tokenizers 0.13.3
--- a/checkpoint-1068470/config.json
+++ b/checkpoint-1068470/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-1068470/generation_config.json
+++ b/checkpoint-1068470/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-1068470/optimizer.pt
+++ b/checkpoint-1068470/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61a7f28c294aaae6fa79960837235e41a323042b117f21892f9c9ab570b42bbf
+size 537476677
--- a/checkpoint-1068470/pytorch_model.bin
+++ b/checkpoint-1068470/pytorch_model.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c679fd6df65e5e05b65cc58a42ad371176853036fc3806af269019756cac18d3
+size 268727709
--- a/checkpoint-1068470/rng_state.pth
+++ b/checkpoint-1068470/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66c776b9754879b54297064c9fba8273ccc85cb860c80f53d4c9ff6763aa2c3c
+size 14575
--- a/checkpoint-1068470/scheduler.pt
+++ b/checkpoint-1068470/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c393ce0055f6c38bbcd9faa7c0ecf281c26bd2e1c0272fe00663f7076dfa2fb
+size 627
--- a/checkpoint-1068470/special_tokens_map.json
+++ b/checkpoint-1068470/special_tokens_map.json
@@ -0,0 +1,5 @@
+{
+  "eos_token": "<eos>",
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
+}
--- a/checkpoint-1068470/tokenizer.json
+++ b/checkpoint-1068470/tokenizer.json
--- a/checkpoint-1068470/tokenizer_config.json
+++ b/checkpoint-1068470/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-1068470/trainer_state.json
+++ b/checkpoint-1068470/trainer_state.json
--- a/checkpoint-1068470/training_args.bin
+++ b/checkpoint-1068470/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd6c9771669d7c01705b8bce74152e0543bf17b731bb0f661061bdc1ce506ad9
+size 4219
--- a/checkpoint-1144790/config.json
+++ b/checkpoint-1144790/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-1144790/generation_config.json
+++ b/checkpoint-1144790/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-1144790/optimizer.pt
+++ b/checkpoint-1144790/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52638b5494cec8fc704acd11d2c27dc16bedec5d8c349f26a86d03e605dc43dd
+size 537476677
--- a/checkpoint-1144790/pytorch_model.bin
+++ b/checkpoint-1144790/pytorch_model.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d08a1be28f2a4e538c93ed5e64a8938e000009d26a65774866212c684e542f7f
+size 268727709
--- a/checkpoint-1144790/rng_state.pth
+++ b/checkpoint-1144790/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:567fb78b2997881aab2e9b83b02e886e3d600d25a5103073ab11188293487432
+size 14575
--- a/checkpoint-1144790/scheduler.pt
+++ b/checkpoint-1144790/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f92409824614db96b688861238d99739792aa684331ce67356225739061f794d
+size 627
--- a/checkpoint-1144790/special_tokens_map.json
+++ b/checkpoint-1144790/special_tokens_map.json
@@ -0,0 +1,5 @@
+{
+  "eos_token": "<eos>",
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
+}
--- a/checkpoint-1144790/tokenizer.json
+++ b/checkpoint-1144790/tokenizer.json
--- a/checkpoint-1144790/tokenizer_config.json
+++ b/checkpoint-1144790/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-1144790/trainer_state.json
+++ b/checkpoint-1144790/trainer_state.json
--- a/checkpoint-1144790/training_args.bin
+++ b/checkpoint-1144790/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cba4de5dfdc84382c678f6b93078f800b12fd4b64c8e21c1d8eb20cbe75252b7
+size 4219
--- a/checkpoint-1221110/config.json
+++ b/checkpoint-1221110/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-1221110/generation_config.json
+++ b/checkpoint-1221110/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-1221110/optimizer.pt
+++ b/checkpoint-1221110/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:880d3994db816d7cf39c854c997d14f072f758f1d1062efb94ca31eea7d92355
+size 537476677
--- a/checkpoint-1221110/pytorch_model.bin
+++ b/checkpoint-1221110/pytorch_model.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1abf99d6b7de6cc275c2d84f53f9a9c6fb3a9624d2d5027a92b6250fe8e8d731
+size 268727709
--- a/checkpoint-1221110/rng_state.pth
+++ b/checkpoint-1221110/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee390c25503a555a7c3275a40b6cf98a8484722235151d46c3ecd1bc252cc27d
+size 14575
--- a/checkpoint-1221110/scheduler.pt
+++ b/checkpoint-1221110/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26c6785f3ec10d77f9cd2386739a61eac563341f6e34fa9705bbd70624ba8367
+size 627
--- a/checkpoint-1221110/special_tokens_map.json
+++ b/checkpoint-1221110/special_tokens_map.json
@@ -0,0 +1,5 @@
+{
+  "eos_token": "<eos>",
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
+}
--- a/checkpoint-1221110/tokenizer.json
+++ b/checkpoint-1221110/tokenizer.json
--- a/checkpoint-1221110/tokenizer_config.json
+++ b/checkpoint-1221110/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-1221110/trainer_state.json
+++ b/checkpoint-1221110/trainer_state.json
--- a/checkpoint-1221110/training_args.bin
+++ b/checkpoint-1221110/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83941fd3cb0ac8dcd2fb72b71d5e224bd98fc54b451295ac7421fdd12776f955
+size 4219
--- a/checkpoint-1297430/config.json
+++ b/checkpoint-1297430/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-1297430/generation_config.json
+++ b/checkpoint-1297430/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-1297430/optimizer.pt
+++ b/checkpoint-1297430/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c4bfa4fc1265cfb037991ed352207f48d1d46a46f6278aefac8b6a21f21f2b6
+size 537476677
--- a/checkpoint-1297430/pytorch_model.bin
+++ b/checkpoint-1297430/pytorch_model.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4117006576ddac063c4fb331eddbbbbda8830b271064d418b1521a12b856493
+size 268727709
--- a/checkpoint-1297430/rng_state.pth
+++ b/checkpoint-1297430/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea78697c2e3cc044791eb921a9f992020bed383ee225df8b0fdbc9b68c240485
+size 14575
--- a/checkpoint-1297430/scheduler.pt
+++ b/checkpoint-1297430/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a59d07a5374ce6d09b9f096225ff8f5a7534c84e9d49df6655ece2592f12d71d
+size 627
--- a/checkpoint-1297430/special_tokens_map.json
+++ b/checkpoint-1297430/special_tokens_map.json
@@ -0,0 +1,5 @@
+{
+  "eos_token": "<eos>",
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
+}
--- a/checkpoint-1297430/tokenizer.json
+++ b/checkpoint-1297430/tokenizer.json
--- a/checkpoint-1297430/tokenizer_config.json
+++ b/checkpoint-1297430/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-1297430/trainer_state.json
+++ b/checkpoint-1297430/trainer_state.json
--- a/checkpoint-1297430/training_args.bin
+++ b/checkpoint-1297430/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83941fd3cb0ac8dcd2fb72b71d5e224bd98fc54b451295ac7421fdd12776f955
+size 4219
--- a/checkpoint-1373750/config.json
+++ b/checkpoint-1373750/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-1373750/generation_config.json
+++ b/checkpoint-1373750/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-1373750/optimizer.pt
+++ b/checkpoint-1373750/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee6d6a6991d898921c4b4933f0d5dc917c0c79c373c0fddb65e2cdfe003e29a9
+size 537476677
--- a/checkpoint-1373750/pytorch_model.bin
+++ b/checkpoint-1373750/pytorch_model.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:adebd78208cb3f875ace735aff80ddc624458d9369002e6d8fa6642954eba58e
+size 268727709
--- a/checkpoint-1373750/rng_state.pth
+++ b/checkpoint-1373750/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9dc40573609e30a767987fb2ee13e40caec0b133a0e71d2962d2a276634ff24d
+size 14575
--- a/checkpoint-1373750/scheduler.pt
+++ b/checkpoint-1373750/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e37b248aca4b006dd17c304c299cca41da475f45bc8e6c0134c3423af63567fd
+size 627
--- a/checkpoint-1373750/special_tokens_map.json
+++ b/checkpoint-1373750/special_tokens_map.json
@@ -0,0 +1,5 @@
+{
+  "eos_token": "<eos>",
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
+}
--- a/checkpoint-1373750/tokenizer.json
+++ b/checkpoint-1373750/tokenizer.json
--- a/checkpoint-1373750/tokenizer_config.json
+++ b/checkpoint-1373750/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-1373750/trainer_state.json
+++ b/checkpoint-1373750/trainer_state.json
--- a/checkpoint-1373750/training_args.bin
+++ b/checkpoint-1373750/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f389d2bc94d2245c89fa9250aa76f2edb3e47cbc0e304115d047b7b177aadbb
+size 4219
--- a/checkpoint-1450070/config.json
+++ b/checkpoint-1450070/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-1450070/generation_config.json
+++ b/checkpoint-1450070/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-1450070/optimizer.pt
+++ b/checkpoint-1450070/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7ebca45a276c3a1807ad2af50b6c64a7b970f27016f14dc3e9e0da32ec21b0f
+size 537476677
--- a/checkpoint-1450070/pytorch_model.bin
+++ b/checkpoint-1450070/pytorch_model.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:abccd2c6f3797b0550e82734a27dfe08f3140894a81bd5aa63675734c820a9d6
+size 268727709
--- a/checkpoint-1450070/rng_state.pth
+++ b/checkpoint-1450070/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86cd88e109a982adb704d4c2ff278234984687f018fc0d3e2a8eb4b50e242aa4
+size 14575
--- a/checkpoint-1450070/scheduler.pt
+++ b/checkpoint-1450070/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7895cb8e4f1b023f6dddd0cd807bc5ec9f39af43feab2426ad403edf2daee844
+size 627
--- a/checkpoint-1450070/special_tokens_map.json
+++ b/checkpoint-1450070/special_tokens_map.json
@@ -0,0 +1,5 @@
+{
+  "eos_token": "<eos>",
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
+}
--- a/checkpoint-1450070/tokenizer.json
+++ b/checkpoint-1450070/tokenizer.json
--- a/checkpoint-1450070/tokenizer_config.json
+++ b/checkpoint-1450070/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-1450070/trainer_state.json
+++ b/checkpoint-1450070/trainer_state.json
--- a/checkpoint-1450070/training_args.bin
+++ b/checkpoint-1450070/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f389d2bc94d2245c89fa9250aa76f2edb3e47cbc0e304115d047b7b177aadbb
+size 4219
--- a/checkpoint-152638/config.json
+++ b/checkpoint-152638/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-152638/generation_config.json
+++ b/checkpoint-152638/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-152638/optimizer.pt
+++ b/checkpoint-152638/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c5821bac294227b2d0cc251c4575b71bd6916fca50b0b0752bbc73d7bb17d49
+size 537476677
--- a/checkpoint-152638/pytorch_model.bin
+++ b/checkpoint-152638/pytorch_model.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ccdb461d01fc586e95e4c4a9702af4a8d2b74e856e9266fbc4106d87f439d0c0
+size 268727709
--- a/checkpoint-152638/rng_state.pth
+++ b/checkpoint-152638/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6db71247e1c3eb7ca47ab37a3e05c8dbd32c20b06262b779426a5121b3c0ad69
+size 14575
--- a/checkpoint-152638/scheduler.pt
+++ b/checkpoint-152638/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e91cf5cf94ab63248a37ffc2e3dcfb00c11ad9088fd71e395e8754f81a1e7aa
+size 627
--- a/checkpoint-152638/special_tokens_map.json
+++ b/checkpoint-152638/special_tokens_map.json
@@ -0,0 +1,5 @@
+{
+  "eos_token": "<eos>",
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
+}
--- a/checkpoint-152638/tokenizer.json
+++ b/checkpoint-152638/tokenizer.json
--- a/checkpoint-152638/tokenizer_config.json
+++ b/checkpoint-152638/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-152638/trainer_state.json
+++ b/checkpoint-152638/trainer_state.json
--- a/checkpoint-152638/training_args.bin
+++ b/checkpoint-152638/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b04a2a93615fea45df7f475b565152c1cfd7438f543336e4c9c0ea8aa3e819bd
+size 4219
--- a/checkpoint-1526390/config.json
+++ b/checkpoint-1526390/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-1526390/generation_config.json
+++ b/checkpoint-1526390/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-1526390/optimizer.pt
+++ b/checkpoint-1526390/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d75b902b08e1aa6a0409273cab1a57b213d9888dc1167223a11a2974923406ed
+size 537476677
--- a/checkpoint-1526390/pytorch_model.bin
+++ b/checkpoint-1526390/pytorch_model.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b36c12a403b32b8fce9e88af2489f69f79ca4ada0e13bd77a8e81d55f8bd7762
+size 268727709
--- a/checkpoint-1526390/rng_state.pth
+++ b/checkpoint-1526390/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b39512538594399576561b211a3815d998254ec255ea8445f0933dba1df19f2e
+size 14575
--- a/checkpoint-1526390/scheduler.pt
+++ b/checkpoint-1526390/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:140cc5d7671db52fdf5add150edd2af879a8a089d82d0c59499c66c0f2d0e5a1
+size 627
--- a/checkpoint-1526390/special_tokens_map.json
+++ b/checkpoint-1526390/special_tokens_map.json
@@ -0,0 +1,5 @@
+{
+  "eos_token": "<eos>",
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
+}
--- a/checkpoint-1526390/tokenizer.json
+++ b/checkpoint-1526390/tokenizer.json
--- a/checkpoint-1526390/tokenizer_config.json
+++ b/checkpoint-1526390/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-1526390/trainer_state.json
+++ b/checkpoint-1526390/trainer_state.json
--- a/checkpoint-1526390/training_args.bin
+++ b/checkpoint-1526390/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29fe553a2a77741e4aa0cbf4d7aaec5c3e0981d816af894d59d6753517f21c16
+size 4219
--- a/checkpoint-1602710/config.json
+++ b/checkpoint-1602710/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-1602710/generation_config.json
+++ b/checkpoint-1602710/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-1602710/optimizer.pt
+++ b/checkpoint-1602710/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c631fce3c3ae3056b8875980385dd9745bf4d1cb3c48d1a2ebfe721d912490d
+size 537476677
--- a/checkpoint-1602710/pytorch_model.bin
+++ b/checkpoint-1602710/pytorch_model.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6c1fb90cc72582d587ce199e2a010dc0645aa980f7b129e471ab2eea7c57114
+size 268727709
--- a/checkpoint-1602710/rng_state.pth
+++ b/checkpoint-1602710/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02768ab70f0ae800c254b42648cccf119c8f1d09af5f94c9039298034579a451
+size 14575
--- a/checkpoint-1602710/scheduler.pt
+++ b/checkpoint-1602710/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81c945a6715f18b57eb3a10a5b8d00db66c8649629e6bdeced0d1e99760815b2
+size 627
--- a/checkpoint-1602710/special_tokens_map.json
+++ b/checkpoint-1602710/special_tokens_map.json
@@ -0,0 +1,5 @@
+{
+  "eos_token": "<eos>",
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
+}
--- a/checkpoint-1602710/tokenizer.json
+++ b/checkpoint-1602710/tokenizer.json
--- a/checkpoint-1602710/tokenizer_config.json
+++ b/checkpoint-1602710/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-1602710/trainer_state.json
+++ b/checkpoint-1602710/trainer_state.json
--- a/Show More
+++ b/Show More