BananaMind/BananaMind-1.0-Instruct
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: BananaMind/BananaMind-1.0-Instruct
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-08-15 00:25:35 +08:00
commit c0de26ddfc
44 changed files with 1004868 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

42
checkpoints/checkpoint-500/config.json Normal file
View File

@@ -0,0 +1,42 @@
{
"activation_function": "gelu_new",
"add_cross_attention": false,
"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": 1600,
"n_head": 25,
"n_inner": null,
"n_layer": 48,
"n_positions": 1024,
"output_past": true,
"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
}
},
"tie_word_embeddings": true,
"transformers_version": "5.12.1",
"use_cache": false,
"vocab_size": 50257
}

6
checkpoints/checkpoint-500/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": "5.12.1"
}

3
checkpoints/checkpoint-500/model.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:d8138102255c98db99f9fb78d187cb6a039393e4e27b6fe717799381c110e4cf
size 6230505744

3
checkpoints/checkpoint-500/optimizer.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:a2598119ebf904cc3b7ffef50dd8fcdac8d893e60921a1760b8f4dd02a0cd28f
size 12461394739

3
checkpoints/checkpoint-500/rng_state.pth Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:35821b748856c27d0d558b0494e873f222c9f77130d8344a150c29d80638aada
size 14645

3
checkpoints/checkpoint-500/scaler.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:f77569c2e850b04af982cc8c1389f1430851448915c593b69e5da36ce05b71d7
size 1383

3
checkpoints/checkpoint-500/scheduler.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:3004b1f3d59b5870e7d52b04fb700c9ab163925d77fd7780e057472941df31d6
size 1465

250306
checkpoints/checkpoint-500/tokenizer.json Normal file
View File

File diff suppressed because it is too large Load Diff

13
checkpoints/checkpoint-500/tokenizer_config.json Normal file
View File

@@ -0,0 +1,13 @@
{
"add_prefix_space": false,
"backend": "tokenizers",
"bos_token": "<|endoftext|>",
"eos_token": "<|endoftext|>",
"errors": "replace",
"is_local": false,
"local_files_only": false,
"model_max_length": 1024,
"pad_token": "<|endoftext|>",
"tokenizer_class": "GPT2Tokenizer",
"unk_token": "<|endoftext|>"
}

384
checkpoints/checkpoint-500/trainer_state.json Normal file
View File

@@ -0,0 +1,384 @@
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.1545595054095827,
"eval_steps": 500,
"global_step": 500,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0030911901081916537,
"grad_norm": 2.9735140800476074,
"learning_rate": 9.183673469387756e-07,
"loss": 1.8602472305297852,
"step": 10
},
{
"epoch": 0.0061823802163833074,
"grad_norm": 2.6337854862213135,
"learning_rate": 1.938775510204082e-06,
"loss": 1.7525932312011718,
"step": 20
},
{
"epoch": 0.00927357032457496,
"grad_norm": 1.5814393758773804,
"learning_rate": 2.959183673469388e-06,
"loss": 1.7173307418823243,
"step": 30
},
{
"epoch": 0.012364760432766615,
"grad_norm": 1.5865761041641235,
"learning_rate": 3.979591836734694e-06,
"loss": 1.6625125885009766,
"step": 40
},
{
"epoch": 0.015455950540958269,
"grad_norm": 1.6338456869125366,
"learning_rate": 5e-06,
"loss": 1.6665992736816406,
"step": 50
},
{
"epoch": 0.01854714064914992,
"grad_norm": 1.336181879043579,
"learning_rate": 6.020408163265307e-06,
"loss": 1.6779584884643555,
"step": 60
},
{
"epoch": 0.021638330757341576,
"grad_norm": 1.6245481967926025,
"learning_rate": 7.0408163265306125e-06,
"loss": 1.6278823852539062,
"step": 70
},
{
"epoch": 0.02472952086553323,
"grad_norm": 1.3484340906143188,
"learning_rate": 8.06122448979592e-06,
"loss": 1.6239589691162108,
"step": 80
},
{
"epoch": 0.027820710973724884,
"grad_norm": 1.4237396717071533,
"learning_rate": 9.081632653061225e-06,
"loss": 1.6229394912719726,
"step": 90
},
{
"epoch": 0.030911901081916538,
"grad_norm": 1.9831488132476807,
"learning_rate": 9.999997492674716e-06,
"loss": 1.604932975769043,
"step": 100
},
{
"epoch": 0.03400309119010819,
"grad_norm": 1.3235148191452026,
"learning_rate": 9.99969661668322e-06,
"loss": 1.7327735900878907,
"step": 110
},
{
"epoch": 0.03709428129829984,
"grad_norm": 1.4738770723342896,
"learning_rate": 9.998894310210835e-06,
"loss": 1.5656912803649903,
"step": 120
},
{
"epoch": 0.0401854714064915,
"grad_norm": 1.5969219207763672,
"learning_rate": 9.997590653722625e-06,
"loss": 1.6269208908081054,
"step": 130
},
{
"epoch": 0.04327666151468315,
"grad_norm": 1.747842788696289,
"learning_rate": 9.995785777965145e-06,
"loss": 1.6059745788574218,
"step": 140
},
{
"epoch": 0.04636785162287481,
"grad_norm": 1.5844131708145142,
"learning_rate": 9.99347986395332e-06,
"loss": 1.606407928466797,
"step": 150
},
{
"epoch": 0.04945904173106646,
"grad_norm": 3.227466106414795,
"learning_rate": 9.990673142952299e-06,
"loss": 1.5951569557189942,
"step": 160
},
{
"epoch": 0.05255023183925812,
"grad_norm": 1.5301669836044312,
"learning_rate": 9.987365896454253e-06,
"loss": 1.555880069732666,
"step": 170
},
{
"epoch": 0.05564142194744977,
"grad_norm": 1.346501350402832,
"learning_rate": 9.98355845615015e-06,
"loss": 1.5443081855773926,
"step": 180
},
{
"epoch": 0.05873261205564142,
"grad_norm": 1.7208951711654663,
"learning_rate": 9.979251203896482e-06,
"loss": 1.589011001586914,
"step": 190
},
{
"epoch": 0.061823802163833076,
"grad_norm": 1.6657794713974,
"learning_rate": 9.974444571676974e-06,
"loss": 1.6033136367797851,
"step": 200
},
{
"epoch": 0.06491499227202473,
"grad_norm": 1.3685671091079712,
"learning_rate": 9.969139041559259e-06,
"loss": 1.564203643798828,
"step": 210
},
{
"epoch": 0.06800618238021638,
"grad_norm": 1.4963208436965942,
"learning_rate": 9.963335145646528e-06,
"loss": 1.5261777877807616,
"step": 220
},
{
"epoch": 0.07109737248840804,
"grad_norm": 1.378618597984314,
"learning_rate": 9.95703346602416e-06,
"loss": 1.7190706253051757,
"step": 230
},
{
"epoch": 0.07418856259659969,
"grad_norm": 1.3284642696380615,
"learning_rate": 9.950234634701355e-06,
"loss": 1.5670341491699218,
"step": 240
},
{
"epoch": 0.07727975270479134,
"grad_norm": 1.2741881608963013,
"learning_rate": 9.942939333547737e-06,
"loss": 1.605707550048828,
"step": 250
},
{
"epoch": 0.080370942812983,
"grad_norm": 1.4335650205612183,
"learning_rate": 9.935148294224974e-06,
"loss": 1.5591754913330078,
"step": 260
},
{
"epoch": 0.08346213292117466,
"grad_norm": 1.4812300205230713,
"learning_rate": 9.926862298113397e-06,
"loss": 1.4808053016662597,
"step": 270
},
{
"epoch": 0.0865533230293663,
"grad_norm": 1.5364317893981934,
"learning_rate": 9.918082176233633e-06,
"loss": 1.5635189056396483,
"step": 280
},
{
"epoch": 0.08964451313755796,
"grad_norm": 1.4932867288589478,
"learning_rate": 9.908808809163259e-06,
"loss": 1.5150517463684081,
"step": 290
},
{
"epoch": 0.09273570324574962,
"grad_norm": 1.27454674243927,
"learning_rate": 9.899043126948488e-06,
"loss": 1.5336437225341797,
"step": 300
},
{
"epoch": 0.09582689335394126,
"grad_norm": 1.2767815589904785,
"learning_rate": 9.888786109010895e-06,
"loss": 1.5452400207519532,
"step": 310
},
{
"epoch": 0.09891808346213292,
"grad_norm": 1.4611462354660034,
"learning_rate": 9.878038784049187e-06,
"loss": 1.4844867706298828,
"step": 320
},
{
"epoch": 0.10200927357032458,
"grad_norm": 1.507378101348877,
"learning_rate": 9.866802229936027e-06,
"loss": 1.4919805526733398,
"step": 330
},
{
"epoch": 0.10510046367851623,
"grad_norm": 1.380361795425415,
"learning_rate": 9.855077573609943e-06,
"loss": 1.5452465057373046,
"step": 340
},
{
"epoch": 0.10819165378670788,
"grad_norm": 1.351883053779602,
"learning_rate": 9.842865990962296e-06,
"loss": 1.5766680717468262,
"step": 350
},
{
"epoch": 0.11128284389489954,
"grad_norm": 1.4119234085083008,
"learning_rate": 9.830168706719348e-06,
"loss": 1.5874876022338866,
"step": 360
},
{
"epoch": 0.1143740340030912,
"grad_norm": 1.3740119934082031,
"learning_rate": 9.816986994319438e-06,
"loss": 1.543256950378418,
"step": 370
},
{
"epoch": 0.11746522411128284,
"grad_norm": 1.349916934967041,
"learning_rate": 9.803322175785259e-06,
"loss": 1.4975996971130372,
"step": 380
},
{
"epoch": 0.1205564142194745,
"grad_norm": 1.8141902685165405,
"learning_rate": 9.789175621591274e-06,
"loss": 1.523211669921875,
"step": 390
},
{
"epoch": 0.12364760432766615,
"grad_norm": 1.6711773872375488,
"learning_rate": 9.774548750526261e-06,
"loss": 1.5890820503234864,
"step": 400
},
{
"epoch": 0.1267387944358578,
"grad_norm": 1.4761755466461182,
"learning_rate": 9.75944302955103e-06,
"loss": 1.5950213432312013,
"step": 410
},
{
"epoch": 0.12982998454404945,
"grad_norm": 1.3480901718139648,
"learning_rate": 9.743859973651296e-06,
"loss": 1.5783711433410645,
"step": 420
},
{
"epoch": 0.13292117465224113,
"grad_norm": 1.2381082773208618,
"learning_rate": 9.727801145685725e-06,
"loss": 1.5575005531311035,
"step": 430
},
{
"epoch": 0.13601236476043277,
"grad_norm": 1.2985453605651855,
"learning_rate": 9.71126815622921e-06,
"loss": 1.5073147773742677,
"step": 440
},
{
"epoch": 0.1391035548686244,
"grad_norm": 1.3880364894866943,
"learning_rate": 9.694262663411333e-06,
"loss": 1.56723051071167,
"step": 450
},
{
"epoch": 0.14219474497681608,
"grad_norm": 1.4708359241485596,
"learning_rate": 9.676786372750064e-06,
"loss": 1.5140653610229493,
"step": 460
},
{
"epoch": 0.14528593508500773,
"grad_norm": 1.6823925971984863,
"learning_rate": 9.658841036980722e-06,
"loss": 1.523008441925049,
"step": 470
},
{
"epoch": 0.14837712519319937,
"grad_norm": 1.3621658086776733,
"learning_rate": 9.640428455880178e-06,
"loss": 1.5539534568786622,
"step": 480
},
{
"epoch": 0.15146831530139104,
"grad_norm": 1.972955584526062,
"learning_rate": 9.621550476086362e-06,
"loss": 1.5369157791137695,
"step": 490
},
{
"epoch": 0.1545595054095827,
"grad_norm": 1.6722270250320435,
"learning_rate": 9.602208990913046e-06,
"loss": 1.5470399856567383,
"step": 500
}
],
"logging_steps": 10,
"max_steps": 3235,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"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": 1.42941547674624e+16,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}

3
checkpoints/checkpoint-500/training_args.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:505999d3a1e6baaa16832f11db4bf97a5d1bd224d517d6d4a7ac2f3008a3aff8
size 5201