fpadovani/cds_o_fr_13
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

初始化项目，由ModelHub XC社区提供模型

Browse Source 
Model: fpadovani/cds_o_fr_13
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-06-04 10:55:17 +08:00
commit 0eeb6eecd7
308 changed files with 1692832 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

33
checkpoint-580/config.json Normal file
View File

@@ -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
}

9
checkpoint-580/generation_config.json Normal file
View File

@@ -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"
}

3
checkpoint-580/model.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:32ea6faff199d3f53d63e20183f3b7c0f710f0e7e8c80a04157e365660194e91
size 392536704

3
checkpoint-580/optimizer.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:fcb6d6b50c62bd7f8938de158189999d786dfecc988ccf8d77cacf2e1787bc0f
size 785167627

3
checkpoint-580/rng_state.pth Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:f945b408514b21d4c889f8ac3e96cd27bfe07810a24a078d3ca5cb3e57a77527
size 14709

3
checkpoint-580/scaler.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:9e0fb36995362331e4a2023dd2348464495d80eebc89fb722873bafb3ee8e577
size 1383

3
checkpoint-580/scheduler.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:988711f96c67f3ecece0d0f01438dfbeb251a2964395d8380ec920796867d20c
size 1465

8
checkpoint-580/special_tokens_map.json Normal file
View File

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

79755
checkpoint-580/tokenizer.json Normal file
View File

File diff suppressed because it is too large Load Diff

62
checkpoint-580/tokenizer_config.json Normal file
View File

@@ -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>"
}

101
checkpoint-580/trainer_state.json Normal file
View File

@@ -0,0 +1,101 @@
{
"best_global_step": 580,
"best_metric": 3.0691733360290527,
"best_model_checkpoint": "/home/p318482/syntactic-bootstrapping/model_trained/cds_o_fr_13/checkpoint-580",
"epoch": 4.0,
"eval_steps": 500,
"global_step": 580,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.006896551724137931,
"grad_norm": 32.2354736328125,
"learning_rate": 0.0,
"loss": 9.7326,
"step": 1
},
{
"epoch": 1.0,
"grad_norm": 1.26012122631073,
"learning_rate": 2.88e-05,
"loss": 5.8188,
"step": 145
},
{
"epoch": 1.0,
"eval_loss": 4.1781511306762695,
"eval_runtime": 4.3842,
"eval_samples_per_second": 803.562,
"eval_steps_per_second": 3.193,
"step": 145
},
{
"epoch": 2.0,
"grad_norm": 1.0639448165893555,
"learning_rate": 5.7799999999999995e-05,
"loss": 3.6451,
"step": 290
},
{
"epoch": 2.0,
"eval_loss": 3.4042274951934814,
"eval_runtime": 4.6134,
"eval_samples_per_second": 763.65,
"eval_steps_per_second": 3.035,
"step": 290
},
{
"epoch": 3.0,
"grad_norm": 0.9253916144371033,
"learning_rate": 8.680000000000001e-05,
"loss": 3.2742,
"step": 435
},
{
"epoch": 3.0,
"eval_loss": 3.1871676445007324,
"eval_runtime": 4.7952,
"eval_samples_per_second": 734.687,
"eval_steps_per_second": 2.92,
"step": 435
},
{
"epoch": 4.0,
"grad_norm": 0.8254706263542175,
"learning_rate": 9.668067226890756e-05,
"loss": 3.1065,
"step": 580
},
{
"epoch": 4.0,
"eval_loss": 3.0691733360290527,
"eval_runtime": 4.4368,
"eval_samples_per_second": 794.047,
"eval_steps_per_second": 3.155,
"step": 580
}
],
"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": 9663624511488000.0,
"train_batch_size": 256,
"trial_name": null,
"trial_params": null
}

3
checkpoint-580/training_args.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:35d1173395a906c65a769a2df8203d374e82540a954fe0dc718fba07dd3acdc2
size 5905