初始化项目，由ModelHub XC社区提供模型

Model: fpadovani/cds_sh1_fr_30
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

.gitignore

@@ -0,0 +1,2 @@
+step_*
+epoch_*

README.md

@@ -0,0 +1,77 @@
+---
+library_name: transformers
+tags:
+- generated_from_trainer
+model-index:
+- name: cds_sh1_fr_30
+  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. -->
+
+# cds_sh1_fr_30
+
+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: 3.3099
+
+## 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: 0.0001
+- train_batch_size: 256
+- eval_batch_size: 256
+- seed: 30
+- optimizer: Use adamw_torch_fused with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_steps: 500
+- num_epochs: 20
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 6.0017        | 1.0   | 145  | 4.5165          |
+| 4.1747        | 2.0   | 290  | 4.0281          |
+| 3.8777        | 3.0   | 435  | 3.7704          |
+| 3.6723        | 4.0   | 580  | 3.6043          |
+| 3.5366        | 5.0   | 725  | 3.5114          |
+| 3.4452        | 6.0   | 870  | 3.4480          |
+| 3.3743        | 7.0   | 1015 | 3.4009          |
+| 3.3153        | 8.0   | 1160 | 3.3667          |
+| 3.2657        | 9.0   | 1305 | 3.3414          |
+| 3.2193        | 10.0  | 1450 | 3.3189          |
+| 3.1773        | 11.0  | 1595 | 3.3084          |
+| 3.1366        | 12.0  | 1740 | 3.2952          |
+| 3.0985        | 13.0  | 1885 | 3.2936          |
+| 3.061         | 14.0  | 2030 | 3.2873          |
+| 3.0252        | 15.0  | 2175 | 3.2956          |
+| 2.9897        | 16.0  | 2320 | 3.2938          |
+| 2.9574        | 17.0  | 2465 | 3.2979          |
+| 2.9302        | 18.0  | 2610 | 3.3015          |
+| 2.9063        | 19.0  | 2755 | 3.3071          |
+| 2.8895        | 20.0  | 2900 | 3.3099          |
+
+
+### Framework versions
+
+- Transformers 4.56.1
+- Pytorch 2.8.0+cu128
+- Datasets 4.0.0
+- Tokenizers 0.22.0

check-1/config.json

@@ -0,0 +1,33 @@
+{
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 1,
+  "dtype": "float32",
+  "embd_pdrop": 0.1,
+  "eos_token_id": 2,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 1024,
+  "pad_token_id": 2,
+  "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,
+  "transformers_version": "4.56.1",
+  "use_cache": true,
+  "vocab_size": 16000
+}

check-1/generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": [
+    2
+  ],
+  "pad_token_id": 2,
+  "transformers_version": "4.56.1"
+}

check-1/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ccc4f637ae36fba27e846296175bdbfcb8c4f0e7dc7a0200222022369fe6d10
+size 392536704

check-101/config.json

@@ -0,0 +1,33 @@
+{
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 1,
+  "dtype": "float32",
+  "embd_pdrop": 0.1,
+  "eos_token_id": 2,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 1024,
+  "pad_token_id": 2,
+  "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,
+  "transformers_version": "4.56.1",
+  "use_cache": true,
+  "vocab_size": 16000
+}

check-101/generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": [
+    2
+  ],
+  "pad_token_id": 2,
+  "transformers_version": "4.56.1"
+}

check-101/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e9a0996d01d25f8960896e7d309dcac2d12f66b1a53dbe496d41d9fa39241e5
+size 392536704

check-12/config.json

@@ -0,0 +1,33 @@
+{
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 1,
+  "dtype": "float32",
+  "embd_pdrop": 0.1,
+  "eos_token_id": 2,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 1024,
+  "pad_token_id": 2,
+  "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,
+  "transformers_version": "4.56.1",
+  "use_cache": true,
+  "vocab_size": 16000
+}

check-12/generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": [
+    2
+  ],
+  "pad_token_id": 2,
+  "transformers_version": "4.56.1"
+}

check-12/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:811e7d137448b7bd4891eb82afa149a3f856247fbaafc176f0c05799f7d098b3
+size 392536704

check-1245/config.json

@@ -0,0 +1,33 @@
+{
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 1,
+  "dtype": "float32",
+  "embd_pdrop": 0.1,
+  "eos_token_id": 2,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 1024,
+  "pad_token_id": 2,
+  "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,
+  "transformers_version": "4.56.1",
+  "use_cache": true,
+  "vocab_size": 16000
+}

check-1245/generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": [
+    2
+  ],
+  "pad_token_id": 2,
+  "transformers_version": "4.56.1"
+}

check-1245/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:acdbdab66c661061c339d0ac8124741d935f85f6b9f52542aba938fc3c0df545
+size 392536704

check-153/config.json

@@ -0,0 +1,33 @@
+{
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 1,
+  "dtype": "float32",
+  "embd_pdrop": 0.1,
+  "eos_token_id": 2,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 1024,
+  "pad_token_id": 2,
+  "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,
+  "transformers_version": "4.56.1",
+  "use_cache": true,
+  "vocab_size": 16000
+}

check-153/generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": [
+    2
+  ],
+  "pad_token_id": 2,
+  "transformers_version": "4.56.1"
+}

check-153/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a9a4e4cd0499bfa4e3b3008f6a75482a5a140f3773064decb7b2eab596d7776
+size 392536704

check-1894/config.json

@@ -0,0 +1,33 @@
+{
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 1,
+  "dtype": "float32",
+  "embd_pdrop": 0.1,
+  "eos_token_id": 2,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 1024,
+  "pad_token_id": 2,
+  "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,
+  "transformers_version": "4.56.1",
+  "use_cache": true,
+  "vocab_size": 16000
+}

check-1894/generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": [
+    2
+  ],
+  "pad_token_id": 2,
+  "transformers_version": "4.56.1"
+}

check-1894/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74758b9d1caf910e95d996f0f028fcddb1e5a7531c037dd8421afdb76c1c0d51
+size 392536704

check-19/config.json

@@ -0,0 +1,33 @@
+{
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 1,
+  "dtype": "float32",
+  "embd_pdrop": 0.1,
+  "eos_token_id": 2,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 1024,
+  "pad_token_id": 2,
+  "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,
+  "transformers_version": "4.56.1",
+  "use_cache": true,
+  "vocab_size": 16000
+}

check-19/generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": [
+    2
+  ],
+  "pad_token_id": 2,
+  "transformers_version": "4.56.1"
+}

check-19/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d6a7cd2ed2cc8f9aa88cf71989bc3ac27e61f21202423c83e7b1b95ba707d34
+size 392536704

check-2/config.json

@@ -0,0 +1,33 @@
+{
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 1,
+  "dtype": "float32",
+  "embd_pdrop": 0.1,
+  "eos_token_id": 2,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 1024,
+  "pad_token_id": 2,
+  "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,
+  "transformers_version": "4.56.1",
+  "use_cache": true,
+  "vocab_size": 16000
+}

check-2/generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": [
+    2
+  ],
+  "pad_token_id": 2,
+  "transformers_version": "4.56.1"
+}

check-2/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9c0ef696a241946b4edbca4977f867a13297c88d87f1f5020e2245efd20cd98
+size 392536704

check-233/config.json

@@ -0,0 +1,33 @@
+{
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 1,
+  "dtype": "float32",
+  "embd_pdrop": 0.1,
+  "eos_token_id": 2,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 1024,
+  "pad_token_id": 2,
+  "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,
+  "transformers_version": "4.56.1",
+  "use_cache": true,
+  "vocab_size": 16000
+}

check-233/generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": [
+    2
+  ],
+  "pad_token_id": 2,
+  "transformers_version": "4.56.1"
+}

check-233/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1755c266003b1144aba371ea06cb7ddc7b3029dab473a260d34fd7c241a54cfa
+size 392536704

check-2880/config.json

@@ -0,0 +1,33 @@
+{
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 1,
+  "dtype": "float32",
+  "embd_pdrop": 0.1,
+  "eos_token_id": 2,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 1024,
+  "pad_token_id": 2,
+  "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,
+  "transformers_version": "4.56.1",
+  "use_cache": true,
+  "vocab_size": 16000
+}

check-2880/generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": [
+    2
+  ],
+  "pad_token_id": 2,
+  "transformers_version": "4.56.1"
+}

check-2880/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92bfb04f5c1093521721778dedf3e3c0b9ea0863e1f3fa72f732b1a9a9acc64b
+size 392536704

check-29/config.json

@@ -0,0 +1,33 @@
+{
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 1,
+  "dtype": "float32",
+  "embd_pdrop": 0.1,
+  "eos_token_id": 2,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 1024,
+  "pad_token_id": 2,
+  "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,
+  "transformers_version": "4.56.1",
+  "use_cache": true,
+  "vocab_size": 16000
+}

check-29/generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": [
+    2
+  ],
+  "pad_token_id": 2,
+  "transformers_version": "4.56.1"
+}

check-29/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d93c143c603b3170bd424824523ad672702200436eef61b9b1f681b46f590d26
+size 392536704

check-354/config.json

@@ -0,0 +1,33 @@
+{
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 1,
+  "dtype": "float32",
+  "embd_pdrop": 0.1,
+  "eos_token_id": 2,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 1024,
+  "pad_token_id": 2,
+  "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,
+  "transformers_version": "4.56.1",
+  "use_cache": true,
+  "vocab_size": 16000
+}

check-354/generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": [
+    2
+  ],
+  "pad_token_id": 2,
+  "transformers_version": "4.56.1"
+}

check-354/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f01088da68ebd2c71af573a2e9f34588dbc49d3d9b606725df66fa44a8ca26c3
+size 392536704

check-4/config.json

@@ -0,0 +1,33 @@
+{
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 1,
+  "dtype": "float32",
+  "embd_pdrop": 0.1,
+  "eos_token_id": 2,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 1024,
+  "pad_token_id": 2,
+  "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,
+  "transformers_version": "4.56.1",
+  "use_cache": true,
+  "vocab_size": 16000
+}

check-4/generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": [
+    2
+  ],
+  "pad_token_id": 2,
+  "transformers_version": "4.56.1"
+}

check-4/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9cff045ba5687d23fef4949958d090a7c744af024ba6202ba9e407c2c14873fa
+size 392536704

check-44/config.json

@@ -0,0 +1,33 @@
+{
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 1,
+  "dtype": "float32",
+  "embd_pdrop": 0.1,
+  "eos_token_id": 2,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 1024,
+  "pad_token_id": 2,
+  "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,
+  "transformers_version": "4.56.1",
+  "use_cache": true,
+  "vocab_size": 16000
+}

check-44/generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": [
+    2
+  ],
+  "pad_token_id": 2,
+  "transformers_version": "4.56.1"
+}

check-44/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21643823128333eb3e9a36d2de6e57baec640f3963e0b31b045741e86eb01c6d
+size 392536704

check-5/config.json

@@ -0,0 +1,33 @@
+{
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 1,
+  "dtype": "float32",
+  "embd_pdrop": 0.1,
+  "eos_token_id": 2,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 1024,
+  "pad_token_id": 2,
+  "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,
+  "transformers_version": "4.56.1",
+  "use_cache": true,
+  "vocab_size": 16000
+}

check-5/generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": [
+    2
+  ],
+  "pad_token_id": 2,
+  "transformers_version": "4.56.1"
+}

check-5/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:353ea9e29add804124ee2715645e7a72ce68380915b6ab2f4fb424d46180a3c9
+size 392536704

check-538/config.json

@@ -0,0 +1,33 @@
+{
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 1,
+  "dtype": "float32",
+  "embd_pdrop": 0.1,
+  "eos_token_id": 2,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 1024,
+  "pad_token_id": 2,
+  "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,
+  "transformers_version": "4.56.1",
+  "use_cache": true,
+  "vocab_size": 16000
+}

check-538/generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": [
+    2
+  ],
+  "pad_token_id": 2,
+  "transformers_version": "4.56.1"
+}

check-538/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b45793ddc0b27e4617895943f084f040325a96f23d909936fa1261613bbf6c76
+size 392536704

check-66/config.json

@@ -0,0 +1,33 @@
+{
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 1,
+  "dtype": "float32",
+  "embd_pdrop": 0.1,
+  "eos_token_id": 2,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 1024,
+  "pad_token_id": 2,
+  "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,
+  "transformers_version": "4.56.1",
+  "use_cache": true,
+  "vocab_size": 16000
+}

check-66/generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": [
+    2
+  ],
+  "pad_token_id": 2,
+  "transformers_version": "4.56.1"
+}

check-66/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c982c0501aa48dfb31adadad86393505cf208082f92211b0ccdff051208c0370
+size 392536704

check-8/config.json

@@ -0,0 +1,33 @@
+{
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 1,
+  "dtype": "float32",
+  "embd_pdrop": 0.1,
+  "eos_token_id": 2,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 1024,
+  "pad_token_id": 2,
+  "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,
+  "transformers_version": "4.56.1",
+  "use_cache": true,
+  "vocab_size": 16000
+}

check-8/generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": [
+    2
+  ],
+  "pad_token_id": 2,
+  "transformers_version": "4.56.1"
+}

check-8/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93c85e6d331443c97b6b1f01f66b57573988a57d384f0ccbd103c5242279b566
+size 392536704

check-819/config.json

@@ -0,0 +1,33 @@
+{
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 1,
+  "dtype": "float32",
+  "embd_pdrop": 0.1,
+  "eos_token_id": 2,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 1024,
+  "pad_token_id": 2,
+  "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,
+  "transformers_version": "4.56.1",
+  "use_cache": true,
+  "vocab_size": 16000
+}

check-819/generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": [
+    2
+  ],
+  "pad_token_id": 2,
+  "transformers_version": "4.56.1"
+}

check-819/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87be28d91580a81638f36e1e4fa67f591d72935a4c163b4cc7519751242d2872
+size 392536704

checkpoint-1015/config.json

@@ -0,0 +1,33 @@
+{
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 1,
+  "dtype": "float32",
+  "embd_pdrop": 0.1,
+  "eos_token_id": 2,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 1024,
+  "pad_token_id": 2,
+  "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,
+  "transformers_version": "4.56.1",
+  "use_cache": true,
+  "vocab_size": 16000
+}

checkpoint-1015/generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": [
+    2
+  ],
+  "pad_token_id": 2,
+  "transformers_version": "4.56.1"
+}

checkpoint-1015/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8cf45a537a278f2dd91ea9c4881662e1d3a636c8f645efa286b2399d2f598db2
+size 392536704

checkpoint-1015/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4db4075383bf6e6acf1126223d7be1039a6c501172e612705fa7ea84952bdff
+size 785167627

checkpoint-1015/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:623d4efb231c95f3e82824adb8d4ef70aa9505a0067d2e9528b335b53baa855b
+size 14709

checkpoint-1015/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46b2f6446f0b27df06da019626a4e1873499b30df9f7b33b69faa54469a75be2
+size 1383

checkpoint-1015/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:465e320c2b11792fcce78282d2e353788fce58e0f78c5474162e9c7abe4c597d
+size 1465

checkpoint-1015/special_tokens_map.json

@@ -0,0 +1,8 @@
+{
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "pad_token": "</s>",
+  "sep_token": "<sep>",
+  "unk_token": "<unk>"
+}

checkpoint-1015/tokenizer_config.json

@@ -0,0 +1,62 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<mask>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "<sep>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "sep_token": "<sep>",
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "unk_token": "<unk>"
+}

checkpoint-1015/trainer_state.json

@@ -0,0 +1,146 @@
+{
+  "best_global_step": 1015,
+  "best_metric": 3.4008681774139404,
+  "best_model_checkpoint": "/home/p318482/syntactic-bootstrapping/model_trained/cds_sh1_fr_30/checkpoint-1015",
+  "epoch": 7.0,
+  "eval_steps": 500,
+  "global_step": 1015,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.006896551724137931,
+      "grad_norm": 34.13589859008789,
+      "learning_rate": 0.0,
+      "loss": 9.8164,
+      "step": 1
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.4214282035827637,
+      "learning_rate": 2.88e-05,
+      "loss": 6.0017,
+      "step": 145
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 4.516501426696777,
+      "eval_runtime": 4.3416,
+      "eval_samples_per_second": 810.983,
+      "eval_steps_per_second": 3.225,
+      "step": 145
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.7844622135162354,
+      "learning_rate": 5.7799999999999995e-05,
+      "loss": 4.1747,
+      "step": 290
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 4.028092384338379,
+      "eval_runtime": 4.4671,
+      "eval_samples_per_second": 788.2,
+      "eval_steps_per_second": 3.134,
+      "step": 290
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 1.2072691917419434,
+      "learning_rate": 8.680000000000001e-05,
+      "loss": 3.8777,
+      "step": 435
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 3.7704145908355713,
+      "eval_runtime": 4.3729,
+      "eval_samples_per_second": 805.181,
+      "eval_steps_per_second": 3.202,
+      "step": 435
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 1.2117047309875488,
+      "learning_rate": 9.668067226890756e-05,
+      "loss": 3.6723,
+      "step": 580
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 3.6042661666870117,
+      "eval_runtime": 4.4715,
+      "eval_samples_per_second": 787.434,
+      "eval_steps_per_second": 3.131,
+      "step": 580
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 1.2041577100753784,
+      "learning_rate": 9.058823529411765e-05,
+      "loss": 3.5366,
+      "step": 725
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 3.5113701820373535,
+      "eval_runtime": 4.511,
+      "eval_samples_per_second": 780.542,
+      "eval_steps_per_second": 3.104,
+      "step": 725
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 1.1716428995132446,
+      "learning_rate": 8.449579831932774e-05,
+      "loss": 3.4452,
+      "step": 870
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 3.4479944705963135,
+      "eval_runtime": 4.4139,
+      "eval_samples_per_second": 797.713,
+      "eval_steps_per_second": 3.172,
+      "step": 870
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 1.1970024108886719,
+      "learning_rate": 7.840336134453782e-05,
+      "loss": 3.3743,
+      "step": 1015
+    },
+    {
+      "epoch": 7.0,
+      "eval_loss": 3.4008681774139404,
+      "eval_runtime": 4.385,
+      "eval_samples_per_second": 802.963,
+      "eval_steps_per_second": 3.193,
+      "step": 1015
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2900,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 20,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.6887108059136e+16,
+  "train_batch_size": 256,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1015/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ae6cc6c783e227db1116f8c005f43aa568ec75be9eed4765d2de3e98ad03a41
+size 5905

checkpoint-1160/config.json

@@ -0,0 +1,33 @@
+{
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 1,
+  "dtype": "float32",
+  "embd_pdrop": 0.1,
+  "eos_token_id": 2,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 1024,
+  "pad_token_id": 2,
+  "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,
+  "transformers_version": "4.56.1",
+  "use_cache": true,
+  "vocab_size": 16000
+}

checkpoint-1160/generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": [
+    2
+  ],
+  "pad_token_id": 2,
+  "transformers_version": "4.56.1"
+}

checkpoint-1160/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4db0974186cca8610e6b464e50f0b09fe0be8b7c83b9c798b7a0a9f051649e24
+size 392536704

checkpoint-1160/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4abcbf27459bbbeddcffca73048d90129f33d05dba0761fb55d18fe6b1506d9
+size 785167627

checkpoint-1160/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b68752a4dcb7296c95c284aad3891bb507800a7d7960c59071321d6e7547bcc3
+size 14709

checkpoint-1160/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a01e05c141882b52ba1d11c99445d54bc70ba64ecb2da4f75d8d22201fd2731
+size 1383

checkpoint-1160/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ba236707809e46fa7582953d39e4e704ad3853e87945489040a90f5a3977823
+size 1465

checkpoint-1160/special_tokens_map.json

@@ -0,0 +1,8 @@
+{
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "pad_token": "</s>",
+  "sep_token": "<sep>",
+  "unk_token": "<unk>"
+}

checkpoint-1160/tokenizer_config.json

@@ -0,0 +1,62 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<mask>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "<sep>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "sep_token": "<sep>",
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "unk_token": "<unk>"
+}

checkpoint-1160/trainer_state.json

@@ -0,0 +1,161 @@
+{
+  "best_global_step": 1160,
+  "best_metric": 3.366744041442871,
+  "best_model_checkpoint": "/home/p318482/syntactic-bootstrapping/model_trained/cds_sh1_fr_30/checkpoint-1160",
+  "epoch": 8.0,
+  "eval_steps": 500,
+  "global_step": 1160,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.006896551724137931,
+      "grad_norm": 34.13589859008789,
+      "learning_rate": 0.0,
+      "loss": 9.8164,
+      "step": 1
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.4214282035827637,
+      "learning_rate": 2.88e-05,
+      "loss": 6.0017,
+      "step": 145
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 4.516501426696777,
+      "eval_runtime": 4.3416,
+      "eval_samples_per_second": 810.983,
+      "eval_steps_per_second": 3.225,
+      "step": 145
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.7844622135162354,
+      "learning_rate": 5.7799999999999995e-05,
+      "loss": 4.1747,
+      "step": 290
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 4.028092384338379,
+      "eval_runtime": 4.4671,
+      "eval_samples_per_second": 788.2,
+      "eval_steps_per_second": 3.134,
+      "step": 290
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 1.2072691917419434,
+      "learning_rate": 8.680000000000001e-05,
+      "loss": 3.8777,
+      "step": 435
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 3.7704145908355713,
+      "eval_runtime": 4.3729,
+      "eval_samples_per_second": 805.181,
+      "eval_steps_per_second": 3.202,
+      "step": 435
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 1.2117047309875488,
+      "learning_rate": 9.668067226890756e-05,
+      "loss": 3.6723,
+      "step": 580
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 3.6042661666870117,
+      "eval_runtime": 4.4715,
+      "eval_samples_per_second": 787.434,
+      "eval_steps_per_second": 3.131,
+      "step": 580
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 1.2041577100753784,
+      "learning_rate": 9.058823529411765e-05,
+      "loss": 3.5366,
+      "step": 725
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 3.5113701820373535,
+      "eval_runtime": 4.511,
+      "eval_samples_per_second": 780.542,
+      "eval_steps_per_second": 3.104,
+      "step": 725
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 1.1716428995132446,
+      "learning_rate": 8.449579831932774e-05,
+      "loss": 3.4452,
+      "step": 870
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 3.4479944705963135,
+      "eval_runtime": 4.4139,
+      "eval_samples_per_second": 797.713,
+      "eval_steps_per_second": 3.172,
+      "step": 870
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 1.1970024108886719,
+      "learning_rate": 7.840336134453782e-05,
+      "loss": 3.3743,
+      "step": 1015
+    },
+    {
+      "epoch": 7.0,
+      "eval_loss": 3.4008681774139404,
+      "eval_runtime": 4.385,
+      "eval_samples_per_second": 802.963,
+      "eval_steps_per_second": 3.193,
+      "step": 1015
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 1.2204298973083496,
+      "learning_rate": 7.23109243697479e-05,
+      "loss": 3.3153,
+      "step": 1160
+    },
+    {
+      "epoch": 8.0,
+      "eval_loss": 3.366744041442871,
+      "eval_runtime": 4.437,
+      "eval_samples_per_second": 793.546,
+      "eval_steps_per_second": 3.155,
+      "step": 1160
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2900,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 20,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.9299552067584e+16,
+  "train_batch_size": 256,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1160/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ae6cc6c783e227db1116f8c005f43aa568ec75be9eed4765d2de3e98ad03a41
+size 5905

checkpoint-1305/config.json

@@ -0,0 +1,33 @@
+{
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 1,
+  "dtype": "float32",
+  "embd_pdrop": 0.1,
+  "eos_token_id": 2,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 1024,
+  "pad_token_id": 2,
+  "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,
+  "transformers_version": "4.56.1",
+  "use_cache": true,
+  "vocab_size": 16000
+}

checkpoint-1305/generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": [
+    2
+  ],
+  "pad_token_id": 2,
+  "transformers_version": "4.56.1"
+}

checkpoint-1305/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ed1a1c8097b664b23ccb1250061833f3f41ae4e9fcfe93e3727bb29810d0896
+size 392536704

checkpoint-1305/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c7f2b6ba3fbe19bc20beae9b2d5012ee4744237ad20f09a2279e2e9c3281b6c
+size 785167627

checkpoint-1305/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ee1d920ea89bf81aca7aa78dbfe9a02dc7ad031d6582a428575b69684212a3f
+size 14709

checkpoint-1305/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb3f993f19242cc21b249926529d9621fcd4005c95c36819f3b93098771d8c48
+size 1383

checkpoint-1305/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d082ce387ce17f69c45b6ca0dcc100d3ad0fe496283dae1cc9d9dda55625dbd
+size 1465

checkpoint-1305/special_tokens_map.json

@@ -0,0 +1,8 @@
+{
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "pad_token": "</s>",
+  "sep_token": "<sep>",
+  "unk_token": "<unk>"
+}

checkpoint-1305/tokenizer_config.json

@@ -0,0 +1,62 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<mask>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "<sep>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "sep_token": "<sep>",
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "unk_token": "<unk>"
+}

checkpoint-1305/trainer_state.json

@@ -0,0 +1,176 @@
+{
+  "best_global_step": 1305,
+  "best_metric": 3.3413963317871094,
+  "best_model_checkpoint": "/home/p318482/syntactic-bootstrapping/model_trained/cds_sh1_fr_30/checkpoint-1305",
+  "epoch": 9.0,
+  "eval_steps": 500,
+  "global_step": 1305,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.006896551724137931,
+      "grad_norm": 34.13589859008789,
+      "learning_rate": 0.0,
+      "loss": 9.8164,
+      "step": 1
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.4214282035827637,
+      "learning_rate": 2.88e-05,
+      "loss": 6.0017,
+      "step": 145
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 4.516501426696777,
+      "eval_runtime": 4.3416,
+      "eval_samples_per_second": 810.983,
+      "eval_steps_per_second": 3.225,
+      "step": 145
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.7844622135162354,
+      "learning_rate": 5.7799999999999995e-05,
+      "loss": 4.1747,
+      "step": 290
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 4.028092384338379,
+      "eval_runtime": 4.4671,
+      "eval_samples_per_second": 788.2,
+      "eval_steps_per_second": 3.134,
+      "step": 290
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 1.2072691917419434,
+      "learning_rate": 8.680000000000001e-05,
+      "loss": 3.8777,
+      "step": 435
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 3.7704145908355713,
+      "eval_runtime": 4.3729,
+      "eval_samples_per_second": 805.181,
+      "eval_steps_per_second": 3.202,
+      "step": 435
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 1.2117047309875488,
+      "learning_rate": 9.668067226890756e-05,
+      "loss": 3.6723,
+      "step": 580
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 3.6042661666870117,
+      "eval_runtime": 4.4715,
+      "eval_samples_per_second": 787.434,
+      "eval_steps_per_second": 3.131,
+      "step": 580
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 1.2041577100753784,
+      "learning_rate": 9.058823529411765e-05,
+      "loss": 3.5366,
+      "step": 725
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 3.5113701820373535,
+      "eval_runtime": 4.511,
+      "eval_samples_per_second": 780.542,
+      "eval_steps_per_second": 3.104,
+      "step": 725
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 1.1716428995132446,
+      "learning_rate": 8.449579831932774e-05,
+      "loss": 3.4452,
+      "step": 870
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 3.4479944705963135,
+      "eval_runtime": 4.4139,
+      "eval_samples_per_second": 797.713,
+      "eval_steps_per_second": 3.172,
+      "step": 870
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 1.1970024108886719,
+      "learning_rate": 7.840336134453782e-05,
+      "loss": 3.3743,
+      "step": 1015
+    },
+    {
+      "epoch": 7.0,
+      "eval_loss": 3.4008681774139404,
+      "eval_runtime": 4.385,
+      "eval_samples_per_second": 802.963,
+      "eval_steps_per_second": 3.193,
+      "step": 1015
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 1.2204298973083496,
+      "learning_rate": 7.23109243697479e-05,
+      "loss": 3.3153,
+      "step": 1160
+    },
+    {
+      "epoch": 8.0,
+      "eval_loss": 3.366744041442871,
+      "eval_runtime": 4.437,
+      "eval_samples_per_second": 793.546,
+      "eval_steps_per_second": 3.155,
+      "step": 1160
+    },
+    {
+      "epoch": 9.0,
+      "grad_norm": 1.3044636249542236,
+      "learning_rate": 6.621848739495798e-05,
+      "loss": 3.2657,
+      "step": 1305
+    },
+    {
+      "epoch": 9.0,
+      "eval_loss": 3.3413963317871094,
+      "eval_runtime": 4.694,
+      "eval_samples_per_second": 750.11,
+      "eval_steps_per_second": 2.983,
+      "step": 1305
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2900,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 20,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.1711996076032e+16,
+  "train_batch_size": 256,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1305/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ae6cc6c783e227db1116f8c005f43aa568ec75be9eed4765d2de3e98ad03a41
+size 5905

checkpoint-145/config.json

@@ -0,0 +1,33 @@
+{
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPT2LMHeadModel"
+  ],
+  "attn_pdrop": 0.1,
+  "bos_token_id": 1,
+  "dtype": "float32",
+  "embd_pdrop": 0.1,
+  "eos_token_id": 2,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gpt2",
+  "n_ctx": 1024,
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": null,
+  "n_layer": 12,
+  "n_positions": 1024,
+  "pad_token_id": 2,
+  "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,
+  "transformers_version": "4.56.1",
+  "use_cache": true,
+  "vocab_size": 16000
+}

checkpoint-145/generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": [
+    2
+  ],
+  "pad_token_id": 2,
+  "transformers_version": "4.56.1"
+}

checkpoint-145/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dca475870282421bfffdb6770dfee1380c4fef35a9b480acf8b1d48824ee7a96
+size 392536704

checkpoint-145/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50cd21d5b06525da814783a893eb14612294da411cde1224a691de14e0841fa1
+size 785167627