Cisco1963/llmplasticity-de_fi_instant_0.5_1-seed42
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: Cisco1963/llmplasticity-de_fi_instant_0.5_1-seed42
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-05-01 05:00:51 +08:00
commit 2c5cc60da8
158 changed files with 4508267 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

39
checkpoint-4669/config.json Normal file
View File

@@ -0,0 +1,39 @@
{
"activation_function": "gelu_new",
"architectures": [
"GPT2LMHeadModel"
],
"attn_pdrop": 0.1,
"bos_token_id": 50256,
"dtype": "float32",
"embd_pdrop": 0.1,
"eos_token_id": 50256,
"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": 50256,
"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,
"task_specific_params": {
"text-generation": {
"do_sample": true,
"max_length": 50
}
},
"transformers_version": "4.57.1",
"use_cache": true,
"vocab_size": 50257
}

6
checkpoint-4669/generation_config.json Normal file
View File

@@ -0,0 +1,6 @@
{
"_from_model_config": true,
"bos_token_id": 50256,
"eos_token_id": 50256,
"transformers_version": "4.57.1"
}

50001
checkpoint-4669/merges.txt Normal file
View File

File diff suppressed because it is too large Load Diff

3
checkpoint-4669/model.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:2f32523af49dc835881a064546d1a7e3b375e46c63dea9f59ee58e7bb44e34e6
size 497774208

3
checkpoint-4669/optimizer.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:fd5bb4995439c09fc04b642b895eed921e7b5d7d68630e1c0ee518829bebe55d
size 995644811

3
checkpoint-4669/rng_state.pth Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:4895fa096e281db99ee595f9941dfdd12ebdf12087248a4b61dd277507b671f0
size 14645

3
checkpoint-4669/scaler.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:3fcea1751117d89e4406bf73d6b903ae36ef8a2e3f810aeac28cea83524d3a64
size 1383

3
checkpoint-4669/scheduler.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:69d9ebe0c2b5b26833fb0c1b9be0f83fcc8a6913dd3b1565c23055905b54aade
size 1465

6
checkpoint-4669/special_tokens_map.json Normal file
View File

@@ -0,0 +1,6 @@
{
"bos_token": "<|endoftext|>",
"eos_token": "<|endoftext|>",
"pad_token": "<|endoftext|>",
"unk_token": "<|endoftext|>"
}

250306
checkpoint-4669/tokenizer.json Normal file
View File

File diff suppressed because it is too large Load Diff

21
checkpoint-4669/tokenizer_config.json Normal file
View File

@@ -0,0 +1,21 @@
{
"add_prefix_space": false,
"added_tokens_decoder": {
"50256": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": true,
"rstrip": false,
"single_word": false,
"special": true
}
},
"bos_token": "<|endoftext|>",
"clean_up_tokenization_spaces": false,
"eos_token": "<|endoftext|>",
"extra_special_tokens": {},
"model_max_length": 1024,
"pad_token": "<|endoftext|>",
"tokenizer_class": "GPT2Tokenizer",
"unk_token": "<|endoftext|>"
}

242
checkpoint-4669/trainer_state.json Normal file
View File

@@ -0,0 +1,242 @@
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.0,
"eval_steps": 99999999,
"global_step": 4669,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.00021421303486317142,
"grad_norm": 174.29400634765625,
"learning_rate": 5e-05,
"loss": 175.3938,
"step": 1
},
{
"epoch": 0.00021421303486317142,
"eval_accuracy": 0.024215843286987115,
"eval_loss": 10.354011535644531,
"eval_runtime": 152.0177,
"eval_samples_per_second": 52.06,
"eval_steps_per_second": 6.512,
"step": 1
},
{
"epoch": 0.00042842606972634284,
"grad_norm": 83.63705444335938,
"learning_rate": 4.998929106875134e-05,
"loss": 164.501,
"step": 2
},
{
"epoch": 0.00042842606972634284,
"eval_accuracy": 0.024217696048750854,
"eval_loss": 10.13454532623291,
"eval_runtime": 137.1006,
"eval_samples_per_second": 57.724,
"eval_steps_per_second": 7.221,
"step": 2
},
{
"epoch": 0.0008568521394526857,
"grad_norm": 43.825008392333984,
"learning_rate": 4.996787320625402e-05,
"loss": 158.761,
"step": 4
},
{
"epoch": 0.0008568521394526857,
"eval_accuracy": 0.024217696048750854,
"eval_loss": 9.977794647216797,
"eval_runtime": 136.1039,
"eval_samples_per_second": 58.147,
"eval_steps_per_second": 7.274,
"step": 4
},
{
"epoch": 0.0017137042789053714,
"grad_norm": 35.26683044433594,
"learning_rate": 4.9925037481259376e-05,
"loss": 155.013,
"step": 8
},
{
"epoch": 0.0017137042789053714,
"eval_accuracy": 0.054267762612305155,
"eval_loss": 9.693761825561523,
"eval_runtime": 137.244,
"eval_samples_per_second": 57.664,
"eval_steps_per_second": 7.213,
"step": 8
},
{
"epoch": 0.0034274085578107428,
"grad_norm": 40.224300384521484,
"learning_rate": 4.983936603127008e-05,
"loss": 149.2168,
"step": 16
},
{
"epoch": 0.0034274085578107428,
"eval_accuracy": 0.016920902635887105,
"eval_loss": 11.783411026000977,
"eval_runtime": 146.7615,
"eval_samples_per_second": 53.924,
"eval_steps_per_second": 6.746,
"step": 16
},
{
"epoch": 0.0068548171156214855,
"grad_norm": 37.21358871459961,
"learning_rate": 4.96680231312915e-05,
"loss": 145.3381,
"step": 32
},
{
"epoch": 0.0068548171156214855,
"eval_accuracy": 0.0519994881436834,
"eval_loss": 8.588780403137207,
"eval_runtime": 142.279,
"eval_samples_per_second": 55.623,
"eval_steps_per_second": 6.958,
"step": 32
},
{
"epoch": 0.013709634231242971,
"grad_norm": 23.38722038269043,
"learning_rate": 4.932533733133434e-05,
"loss": 115.3768,
"step": 64
},
{
"epoch": 0.013709634231242971,
"eval_accuracy": 0.07924990816477524,
"eval_loss": 7.433769702911377,
"eval_runtime": 147.5767,
"eval_samples_per_second": 53.626,
"eval_steps_per_second": 6.708,
"step": 64
},
{
"epoch": 0.027419268462485942,
"grad_norm": 18.296302795410156,
"learning_rate": 4.8639965731420003e-05,
"loss": 92.7634,
"step": 128
},
{
"epoch": 0.027419268462485942,
"eval_accuracy": 0.09311190112872716,
"eval_loss": 6.83799409866333,
"eval_runtime": 143.065,
"eval_samples_per_second": 55.318,
"eval_steps_per_second": 6.92,
"step": 128
},
{
"epoch": 0.054838536924971884,
"grad_norm": 12.443135261535645,
"learning_rate": 4.726922253159135e-05,
"loss": 74.9485,
"step": 256
},
{
"epoch": 0.054838536924971884,
"eval_accuracy": 0.14537732234423276,
"eval_loss": 6.180610656738281,
"eval_runtime": 139.6377,
"eval_samples_per_second": 56.675,
"eval_steps_per_second": 7.09,
"step": 256
},
{
"epoch": 0.10967707384994377,
"grad_norm": 10.523282051086426,
"learning_rate": 4.452773613193403e-05,
"loss": 66.064,
"step": 512
},
{
"epoch": 0.10967707384994377,
"eval_accuracy": 0.14975638653155834,
"eval_loss": 6.066355228424072,
"eval_runtime": 143.9305,
"eval_samples_per_second": 54.985,
"eval_steps_per_second": 6.878,
"step": 512
},
{
"epoch": 0.21935414769988754,
"grad_norm": 11.639715194702148,
"learning_rate": 3.9044763332619404e-05,
"loss": 61.2244,
"step": 1024
},
{
"epoch": 0.21935414769988754,
"eval_accuracy": 0.1782677962090518,
"eval_loss": 5.892604351043701,
"eval_runtime": 158.4884,
"eval_samples_per_second": 49.934,
"eval_steps_per_second": 6.247,
"step": 1024
},
{
"epoch": 0.4387082953997751,
"grad_norm": 19.752676010131836,
"learning_rate": 2.807881773399015e-05,
"loss": 60.9252,
"step": 2048
},
{
"epoch": 0.4387082953997751,
"eval_accuracy": 0.25111369509618425,
"eval_loss": 4.6798505783081055,
"eval_runtime": 162.0054,
"eval_samples_per_second": 48.85,
"eval_steps_per_second": 6.111,
"step": 2048
},
{
"epoch": 0.8774165907995501,
"grad_norm": 19.41061782836914,
"learning_rate": 6.146926536731634e-06,
"loss": 49.8739,
"step": 4096
},
{
"epoch": 0.8774165907995501,
"eval_accuracy": 0.2639839664467315,
"eval_loss": 4.5035400390625,
"eval_runtime": 152.0669,
"eval_samples_per_second": 52.043,
"eval_steps_per_second": 6.51,
"step": 4096
}
],
"logging_steps": 99999999,
"max_steps": 4669,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 99999999,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 3.12261223514112e+17,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}

3
checkpoint-4669/training_args.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:f50924331c1de5e48d50012fff872f96fc7cbb023d365504e669dda3e5d82865
size 5969

1
checkpoint-4669/vocab.json Normal file
View File

File diff suppressed because one or more lines are too long