初始化项目，由ModelHub XC社区提供模型

Model: craa/100M_low_1000_6910
Source: Original Platform

.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

README.md

@@ -0,0 +1,152 @@
+---
+library_name: transformers
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: 100M_low_1000_6910
+  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. -->
+
+# 100M_low_1000_6910
+
+This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 3.3009
+- Accuracy: 0.3946
+
+## 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: 0.0006
+- train_batch_size: 32
+- eval_batch_size: 16
+- seed: 6910
+- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.98) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 100
+- num_epochs: 10
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch  | Step  | Validation Loss | Accuracy |
+|:-------------:|:------:|:-----:|:---------------:|:--------:|
+| 5.1184        | 0.1078 | 1000  | 5.0307          | 0.2266   |
+| 4.5882        | 0.2156 | 2000  | 4.5119          | 0.2696   |
+| 4.3179        | 0.3235 | 3000  | 4.2384          | 0.2980   |
+| 4.1615        | 0.4313 | 4000  | 4.0961          | 0.3116   |
+| 4.0664        | 0.5391 | 5000  | 3.9981          | 0.3208   |
+| 4.0053        | 0.6469 | 6000  | 3.9227          | 0.3275   |
+| 3.9311        | 0.7547 | 7000  | 3.8684          | 0.3327   |
+| 3.8888        | 0.8625 | 8000  | 3.8206          | 0.3374   |
+| 3.8417        | 0.9704 | 9000  | 3.7826          | 0.3407   |
+| 3.7812        | 1.0782 | 10000 | 3.7592          | 0.3442   |
+| 3.7435        | 1.1860 | 11000 | 3.7252          | 0.3471   |
+| 3.7391        | 1.2938 | 12000 | 3.7055          | 0.3491   |
+| 3.7123        | 1.4016 | 13000 | 3.6798          | 0.3514   |
+| 3.7017        | 1.5094 | 14000 | 3.6590          | 0.3535   |
+| 3.6819        | 1.6173 | 15000 | 3.6405          | 0.3555   |
+| 3.6808        | 1.7251 | 16000 | 3.6213          | 0.3568   |
+| 3.6642        | 1.8329 | 17000 | 3.6082          | 0.3583   |
+| 3.6455        | 1.9407 | 18000 | 3.5910          | 0.3600   |
+| 3.5613        | 2.0485 | 19000 | 3.5819          | 0.3616   |
+| 3.5589        | 2.1563 | 20000 | 3.5736          | 0.3625   |
+| 3.5597        | 2.2642 | 21000 | 3.5627          | 0.3635   |
+| 3.5455        | 2.3720 | 22000 | 3.5519          | 0.3648   |
+| 3.5547        | 2.4798 | 23000 | 3.5428          | 0.3656   |
+| 3.5427        | 2.5876 | 24000 | 3.5324          | 0.3670   |
+| 3.5285        | 2.6954 | 25000 | 3.5216          | 0.3680   |
+| 3.5395        | 2.8032 | 26000 | 3.5136          | 0.3686   |
+| 3.523         | 2.9111 | 27000 | 3.5060          | 0.3693   |
+| 3.4475        | 3.0189 | 28000 | 3.5024          | 0.3704   |
+| 3.4418        | 3.1267 | 29000 | 3.4971          | 0.3705   |
+| 3.47          | 3.2345 | 30000 | 3.4905          | 0.3717   |
+| 3.4761        | 3.3423 | 31000 | 3.4836          | 0.3726   |
+| 3.4649        | 3.4501 | 32000 | 3.4763          | 0.3731   |
+| 3.456         | 3.5580 | 33000 | 3.4716          | 0.3732   |
+| 3.4552        | 3.6658 | 34000 | 3.4656          | 0.3743   |
+| 3.4719        | 3.7736 | 35000 | 3.4591          | 0.3749   |
+| 3.4387        | 3.8814 | 36000 | 3.4521          | 0.3754   |
+| 3.4191        | 3.9892 | 37000 | 3.4474          | 0.3759   |
+| 3.3624        | 4.0970 | 38000 | 3.4529          | 0.3762   |
+| 3.3861        | 4.2049 | 39000 | 3.4477          | 0.3769   |
+| 3.4024        | 4.3127 | 40000 | 3.4409          | 0.3772   |
+| 3.4166        | 4.4205 | 41000 | 3.4363          | 0.3781   |
+| 3.3894        | 4.5283 | 42000 | 3.4303          | 0.3787   |
+| 3.4099        | 4.6361 | 43000 | 3.4254          | 0.3790   |
+| 3.394         | 4.7439 | 44000 | 3.4206          | 0.3794   |
+| 3.3911        | 4.8518 | 45000 | 3.4143          | 0.3802   |
+| 3.3895        | 4.9596 | 46000 | 3.4123          | 0.3804   |
+| 3.3172        | 5.0674 | 47000 | 3.4136          | 0.3808   |
+| 3.3081        | 5.1752 | 48000 | 3.4135          | 0.3811   |
+| 3.3303        | 5.2830 | 49000 | 3.4095          | 0.3813   |
+| 3.3431        | 5.3908 | 50000 | 3.4027          | 0.3819   |
+| 3.3191        | 5.4987 | 51000 | 3.3983          | 0.3822   |
+| 3.3286        | 5.6065 | 52000 | 3.3952          | 0.3826   |
+| 3.3427        | 5.7143 | 53000 | 3.3901          | 0.3830   |
+| 3.3263        | 5.8221 | 54000 | 3.3863          | 0.3835   |
+| 3.3294        | 5.9299 | 55000 | 3.3817          | 0.3840   |
+| 3.24          | 6.0377 | 56000 | 3.3839          | 0.3839   |
+| 3.2721        | 6.1456 | 57000 | 3.3864          | 0.3839   |
+| 3.2775        | 6.2534 | 58000 | 3.3806          | 0.3846   |
+| 3.2946        | 6.3612 | 59000 | 3.3778          | 0.3849   |
+| 3.2855        | 6.4690 | 60000 | 3.3749          | 0.3852   |
+| 3.2779        | 6.5768 | 61000 | 3.3691          | 0.3860   |
+| 3.2812        | 6.6846 | 62000 | 3.3644          | 0.3863   |
+| 3.2898        | 6.7925 | 63000 | 3.3619          | 0.3868   |
+| 3.3025        | 6.9003 | 64000 | 3.3567          | 0.3871   |
+| 3.2126        | 7.0081 | 65000 | 3.3610          | 0.3870   |
+| 3.2238        | 7.1159 | 66000 | 3.3621          | 0.3874   |
+| 3.2352        | 7.2237 | 67000 | 3.3576          | 0.3876   |
+| 3.2156        | 7.3315 | 68000 | 3.3556          | 0.3880   |
+| 3.2497        | 7.4394 | 69000 | 3.3526          | 0.3882   |
+| 3.2359        | 7.5472 | 70000 | 3.3483          | 0.3887   |
+| 3.2385        | 7.6550 | 71000 | 3.3431          | 0.3892   |
+| 3.2328        | 7.7628 | 72000 | 3.3404          | 0.3895   |
+| 3.2317        | 7.8706 | 73000 | 3.3351          | 0.3898   |
+| 3.2461        | 7.9784 | 74000 | 3.3336          | 0.3901   |
+| 3.162         | 8.0863 | 75000 | 3.3396          | 0.3898   |
+| 3.1882        | 8.1941 | 76000 | 3.3383          | 0.3901   |
+| 3.1773        | 8.3019 | 77000 | 3.3338          | 0.3906   |
+| 3.1951        | 8.4097 | 78000 | 3.3299          | 0.3909   |
+| 3.1813        | 8.5175 | 79000 | 3.3278          | 0.3911   |
+| 3.177         | 8.6253 | 80000 | 3.3245          | 0.3918   |
+| 3.1908        | 8.7332 | 81000 | 3.3191          | 0.3922   |
+| 3.1958        | 8.8410 | 82000 | 3.3159          | 0.3925   |
+| 3.1736        | 8.9488 | 83000 | 3.3149          | 0.3926   |
+| 3.1096        | 9.0566 | 84000 | 3.3174          | 0.3926   |
+| 3.147         | 9.1644 | 85000 | 3.3151          | 0.3928   |
+| 3.1339        | 9.2722 | 86000 | 3.3137          | 0.3932   |
+| 3.1222        | 9.3801 | 87000 | 3.3120          | 0.3933   |
+| 3.1379        | 9.4879 | 88000 | 3.3084          | 0.3938   |
+| 3.1324        | 9.5957 | 89000 | 3.3067          | 0.3939   |
+| 3.1352        | 9.7035 | 90000 | 3.3044          | 0.3943   |
+| 3.1327        | 9.8113 | 91000 | 3.3029          | 0.3944   |
+| 3.1428        | 9.9191 | 92000 | 3.3009          | 0.3946   |
+
+
+### Framework versions
+
+- Transformers 4.47.0.dev0
+- Pytorch 2.5.0+cu124
+- Datasets 3.0.2
+- Tokenizers 0.20.1

all_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 10.0,
+    "eval_accuracy": 0.3945585112642079,
+    "eval_loss": 3.3003323078155518,
+    "eval_runtime": 183.9415,
+    "eval_samples": 18011,
+    "eval_samples_per_second": 97.917,
+    "eval_steps_per_second": 6.122,
+    "perplexity": 27.1216501596411,
+    "total_flos": 7.75449427968e+17,
+    "train_loss": 3.4540262829556942,
+    "train_runtime": 79697.0382,
+    "train_samples": 296775,
+    "train_samples_per_second": 37.238,
+    "train_steps_per_second": 1.164
+}

checkpoint-10000/config.json

@@ -0,0 +1,31 @@
+{
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 1024,
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.1,
+  "scale_attn_by_inverse_layer_idx": false,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.47.0.dev0",
+  "use_cache": true,
+  "vocab_size": 52000
+}

checkpoint-10000/generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.47.0.dev0"
+}

checkpoint-10000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8cbe6c7ebe3b4d9f3b05c1cba622f285527d797b137af3778eeece3685aee08
+size 503128704

checkpoint-10000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9972d0f3b95121571a9cd529abb75f1fd63e9863862af95238967ff6d5b13370
+size 1006351290

checkpoint-10000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05788209930a9dbb2e5cacfa40a77b7ba4679c4dff249e545786454ad50d8489
+size 14244

checkpoint-10000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4e7893396eb2644b36995e7c0917ee358383aadd367376b940738387a18a156
+size 1064

checkpoint-10000/special_tokens_map.json

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

checkpoint-10000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe4bc3f5331aa4ca13eac4e833f0046ac51a91820c81b312cbdeb531b06a5b1f
+size 5304

checkpoint-20000/config.json

@@ -0,0 +1,31 @@
+{
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 1024,
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.1,
+  "scale_attn_by_inverse_layer_idx": false,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.47.0.dev0",
+  "use_cache": true,
+  "vocab_size": 52000
+}

checkpoint-20000/generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.47.0.dev0"
+}

checkpoint-20000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd0271a316e9fce045e3cb8f20272f62c9dd1da3b2fafc536136543c4e48ae20
+size 503128704

checkpoint-20000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:528cead1019b0b8f6ac8825a987b92c3772ae54389e593a62d228612922184f7
+size 1006351290

checkpoint-20000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:126145d19e611c56a182520052170501df78fe0a14f3a3f1e7edcbda0b4195fc
+size 14244

checkpoint-20000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4081d50f1887f3a982b2f3cabb2e58590020a0424181d8b5b776143e4ebaaf72
+size 1064

checkpoint-20000/special_tokens_map.json

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

checkpoint-20000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe4bc3f5331aa4ca13eac4e833f0046ac51a91820c81b312cbdeb531b06a5b1f
+size 5304

checkpoint-30000/config.json

@@ -0,0 +1,31 @@
+{
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 1024,
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.1,
+  "scale_attn_by_inverse_layer_idx": false,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.47.0.dev0",
+  "use_cache": true,
+  "vocab_size": 52000
+}

checkpoint-30000/generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.47.0.dev0"
+}

checkpoint-30000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff375c36a224b1a0d4f65785230868440be76713159d669b3d37a722c7fc0614
+size 503128704

checkpoint-30000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:31b21c385ee364639e69876df3b4ecefa323b09f0571df881d8f96528392c0e9
+size 1006351290

checkpoint-30000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62d7d6889a3d03289c9df95a4d59ac70c786942965bfb1019e7d138872a014a7
+size 14244

checkpoint-30000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44deee510a72037554cac5075591c8da41bde22939e978af5b40f1dd60ee2078
+size 1064

checkpoint-30000/special_tokens_map.json

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

checkpoint-30000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe4bc3f5331aa4ca13eac4e833f0046ac51a91820c81b312cbdeb531b06a5b1f
+size 5304

checkpoint-40000/config.json

@@ -0,0 +1,31 @@
+{
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 1024,
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.1,
+  "scale_attn_by_inverse_layer_idx": false,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.47.0.dev0",
+  "use_cache": true,
+  "vocab_size": 52000
+}

checkpoint-40000/generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.47.0.dev0"
+}

checkpoint-40000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:143195d249a314badaa97b5feeb0cc8d078ca3b6901af9ff68a993929689e230
+size 503128704

checkpoint-40000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e437e3213adb95a3dd9adf2a8b1266be6b5cb5fe367b9f0e310fa86189927d8c
+size 1006351290

checkpoint-40000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:001ff43ab6df1383faa0b224266a8638f491276789c39d822de8a337e193c9c6
+size 14244

checkpoint-40000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88579607fedf53d62f04850fc869d84d7839a944ef6443c3da8173036d467934
+size 1064

checkpoint-40000/special_tokens_map.json

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

checkpoint-40000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe4bc3f5331aa4ca13eac4e833f0046ac51a91820c81b312cbdeb531b06a5b1f
+size 5304

checkpoint-50000/config.json

@@ -0,0 +1,31 @@
+{
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 1024,
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.1,
+  "scale_attn_by_inverse_layer_idx": false,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.47.0.dev0",
+  "use_cache": true,
+  "vocab_size": 52000
+}

checkpoint-50000/generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.47.0.dev0"
+}

checkpoint-50000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ba3669e3a66ed314d09a846aca151cb421db057f7f4bfd955ae1109b260f9fc
+size 503128704

checkpoint-50000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:123577d49745eeb8421b7dce6be176af18266d965cb295c565cb7639d91c1a22
+size 1006351290

checkpoint-50000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d58a9230439cef209946047ec6ffe73e2bb192badd1eab19102c1f6da21c49a
+size 14244

checkpoint-50000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:751e87b5d8381a36f448c02b4727bb330481c261deabdd02dc13c87af089cc7a
+size 1064

checkpoint-50000/special_tokens_map.json

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

checkpoint-50000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe4bc3f5331aa4ca13eac4e833f0046ac51a91820c81b312cbdeb531b06a5b1f
+size 5304

checkpoint-60000/config.json

@@ -0,0 +1,31 @@
+{
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 1024,
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.1,
+  "scale_attn_by_inverse_layer_idx": false,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.47.0.dev0",
+  "use_cache": true,
+  "vocab_size": 52000
+}

checkpoint-60000/generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.47.0.dev0"
+}

checkpoint-60000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:805fd78f9c3d10a2a6684c81eff3f2e868e2d632a55c59a61b3337137081230c
+size 503128704

checkpoint-60000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44fae0d88d8bcd1f71ad94bacd64009b1bd6690af9e11dab178894cf34c2e005
+size 1006351290

checkpoint-60000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:085c2b444c23f56b7220029b7fc401d102bb3f89fee2fd16c8e6292abe326875
+size 14244

checkpoint-60000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:30ec4589fa7ea66fa548b837d232fd4cf22314611740f58d8ac1fd6c158eba0e
+size 1064

checkpoint-60000/special_tokens_map.json

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

checkpoint-60000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe4bc3f5331aa4ca13eac4e833f0046ac51a91820c81b312cbdeb531b06a5b1f
+size 5304

checkpoint-70000/config.json

@@ -0,0 +1,31 @@
+{
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 1024,
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.1,
+  "scale_attn_by_inverse_layer_idx": false,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.47.0.dev0",
+  "use_cache": true,
+  "vocab_size": 52000
+}

checkpoint-70000/generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.47.0.dev0"
+}

checkpoint-70000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7cadb65a3990a14f5d25ccfc9535475a4bee04ac20b418b087da1afa33f8e05
+size 503128704

checkpoint-70000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22727be18c78d8f568b093373ea5c36ae744b73f76eca64ded26f5a32456ebc0
+size 1006351290

checkpoint-70000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a141f4fee467c9f69d2cd3028d5c152fefdd875024276bf4a129287cee10b7a6
+size 14244

checkpoint-70000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:834b1dd5d2ac795fd2716a17eae79a2a7944c05863af2feeeb604b29ad32b195
+size 1064

checkpoint-70000/special_tokens_map.json

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

checkpoint-70000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe4bc3f5331aa4ca13eac4e833f0046ac51a91820c81b312cbdeb531b06a5b1f
+size 5304

checkpoint-80000/config.json

@@ -0,0 +1,31 @@
+{
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 1024,
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.1,
+  "scale_attn_by_inverse_layer_idx": false,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.47.0.dev0",
+  "use_cache": true,
+  "vocab_size": 52000
+}

checkpoint-80000/generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.47.0.dev0"
+}

checkpoint-80000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ced59699709a8254e8a1c81befd4111a64ad6a5e2079eceecee5a0f2441844ff
+size 503128704

checkpoint-80000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:497ae4d18f9611e439ca379c278cdfb5a71e1ff1afe044120555069c57e56d3d
+size 1006351290

checkpoint-80000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76e74f6b281c6245459eed8547eb520338a9d92804aa32acbccd3bb6c367228c
+size 14244

checkpoint-80000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:343c5672d071f8881da0f872c4c5d2b5ecf494f40709115967a9e5c39afa630e
+size 1064

checkpoint-80000/special_tokens_map.json

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

checkpoint-80000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe4bc3f5331aa4ca13eac4e833f0046ac51a91820c81b312cbdeb531b06a5b1f
+size 5304

checkpoint-90000/config.json

@@ -0,0 +1,31 @@
+{
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 50256,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 1024,
+  "reorder_and_upcast_attn": false,
+  "resid_pdrop": 0.1,
+  "scale_attn_by_inverse_layer_idx": false,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.47.0.dev0",
+  "use_cache": true,
+  "vocab_size": 52000
+}

checkpoint-90000/generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "transformers_version": "4.47.0.dev0"
+}

checkpoint-90000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32c9b9ab9a88a647182dad73d3e910b1769f6d1895d5a815f4a1411f846df129
+size 503128704

checkpoint-90000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce83cfb09be4e60623646d40d06441d86d3c369b41a51149da80c66806188034
+size 1006351290

checkpoint-90000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24e69e6ecb8c38a6d2ada12b6a531f3329c58d85872fbd9136c2d4b702131599
+size 14244

checkpoint-90000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6cc0526fec3e82fba03edee49af1d6bd8bf8c692b3cf613fe828924883c0d780
+size 1064

checkpoint-90000/special_tokens_map.json

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