fpadovani/cds_sh1_fr_30
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_sh1_fr_30
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-06-04 10:55:18 +08:00
commit 226f4a4038
308 changed files with 1692832 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

33
checkpoint-2175/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-2175/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-2175/model.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:24388806fb96026c2f6d464456b91b7d16f2940721d04e281800160329a93bc3
size 392536704

3
checkpoint-2175/optimizer.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:9ba6ba18b893c8bcc97bc3a738e2c36601296c83b878ce484183e9550e19f61d
size 785167627

3
checkpoint-2175/rng_state.pth Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:7cfff192f776a32abce1497a063ddaa4cdcda8ccbe39a76777c0355e0b0e4bf2
size 14709

3
checkpoint-2175/scaler.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:b88f510bab1bdef3875f348f2e04e21fbac1cb875072fd709a6f2edd747ed8f1
size 1383

3
checkpoint-2175/scheduler.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:5f5ab29ad76a00bec9578350749136eef9da83aea8c28bbcd2f5d8311943ec54
size 1465

8
checkpoint-2175/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-2175/tokenizer.json Normal file
View File

File diff suppressed because it is too large Load Diff

62
checkpoint-2175/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>"
}

266
checkpoint-2175/trainer_state.json Normal file
View File

@@ -0,0 +1,266 @@
{
"best_global_step": 2030,
"best_metric": 3.28729248046875,
"best_model_checkpoint": "/home/p318482/syntactic-bootstrapping/model_trained/cds_sh1_fr_30/checkpoint-2030",
"epoch": 15.0,
"eval_steps": 500,
"global_step": 2175,
"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
},
{
"epoch": 10.0,
"grad_norm": 1.4050198793411255,
"learning_rate": 6.012605042016807e-05,
"loss": 3.2193,
"step": 1450
},
{
"epoch": 10.0,
"eval_loss": 3.3189010620117188,
"eval_runtime": 4.3858,
"eval_samples_per_second": 802.816,
"eval_steps_per_second": 3.192,
"step": 1450
},
{
"epoch": 11.0,
"grad_norm": 1.4973615407943726,
"learning_rate": 5.403361344537815e-05,
"loss": 3.1773,
"step": 1595
},
{
"epoch": 11.0,
"eval_loss": 3.30843448638916,
"eval_runtime": 4.4298,
"eval_samples_per_second": 794.852,
"eval_steps_per_second": 3.16,
"step": 1595
},
{
"epoch": 12.0,
"grad_norm": 1.5111000537872314,
"learning_rate": 4.794117647058824e-05,
"loss": 3.1366,
"step": 1740
},
{
"epoch": 12.0,
"eval_loss": 3.2951903343200684,
"eval_runtime": 4.3718,
"eval_samples_per_second": 805.398,
"eval_steps_per_second": 3.202,
"step": 1740
},
{
"epoch": 13.0,
"grad_norm": 1.6258167028427124,
"learning_rate": 4.184873949579832e-05,
"loss": 3.0985,
"step": 1885
},
{
"epoch": 13.0,
"eval_loss": 3.2935917377471924,
"eval_runtime": 4.4103,
"eval_samples_per_second": 798.356,
"eval_steps_per_second": 3.174,
"step": 1885
},
{
"epoch": 14.0,
"grad_norm": 1.7234424352645874,
"learning_rate": 3.575630252100841e-05,
"loss": 3.061,
"step": 2030
},
{
"epoch": 14.0,
"eval_loss": 3.28729248046875,
"eval_runtime": 4.3993,
"eval_samples_per_second": 800.353,
"eval_steps_per_second": 3.182,
"step": 2030
},
{
"epoch": 15.0,
"grad_norm": 1.8610221147537231,
"learning_rate": 2.966386554621849e-05,
"loss": 3.0252,
"step": 2175
},
{
"epoch": 15.0,
"eval_loss": 3.2955870628356934,
"eval_runtime": 4.5452,
"eval_samples_per_second": 774.661,
"eval_steps_per_second": 3.08,
"step": 2175
}
],
"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": 3.618666012672e+16,
"train_batch_size": 256,
"trial_name": null,
"trial_params": null
}

3
checkpoint-2175/training_args.bin Normal file
View File

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