VehaanS/slm-125m-tutor
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: VehaanS/slm-125m-tutor
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-10-04 16:47:22 +08:00
commit b6a0578ddf
20 changed files with 491076 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

32
last-checkpoint/config.json Normal file
View File

@@ -0,0 +1,32 @@
{
"architectures": [
"LlamaForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 0,
"dtype": "float32",
"eos_token_id": 0,
"head_dim": 64,
"hidden_act": "silu",
"hidden_size": 768,
"initializer_range": 0.02,
"intermediate_size": 2048,
"max_position_embeddings": 2048,
"mlp_bias": false,
"model_type": "llama",
"num_attention_heads": 12,
"num_hidden_layers": 12,
"num_key_value_heads": 12,
"pad_token_id": 0,
"pretraining_tp": 1,
"rms_norm_eps": 1e-05,
"rope_parameters": {
"rope_theta": 10000.0,
"rope_type": "default"
},
"tie_word_embeddings": true,
"transformers_version": "5.0.0",
"use_cache": false,
"vocab_size": 49152
}

12
last-checkpoint/generation_config.json Normal file
View File

@@ -0,0 +1,12 @@
{
"_from_model_config": true,
"bos_token_id": 0,
"eos_token_id": [
0
],
"output_attentions": false,
"output_hidden_states": false,
"pad_token_id": 0,
"transformers_version": "5.0.0",
"use_cache": true
}

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

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:2ffe3417eba02202eceec12b967243f7461ed5afce8b31d95e48f4d5b61a4212
size 490822600

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

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:328836c1310f363ec345bea34c5ec16ac2bb4eef64f5ffcb14645a108d922476
size 981715659

3
last-checkpoint/rng_state_0.pth Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:e1557eea53882574b3f18c13a4ba48b553f2cf8514c888f71896ffe922a42d70
size 14917

3
last-checkpoint/rng_state_1.pth Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:ed239779e6c9f5466cc9b1bc2adf2c4f487688a6bf675c36513a13bc18b548da
size 14917

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

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:612ce4ef3c17c03e084f8a4d379b0ebe3f3e1f1f8adc51dca474c3446cf2627c
size 1383

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

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:e157c1d29b98e6e4b10532f55558a6c9052ff466fde6294afcb79eaa651d22c4
size 1465

244974
last-checkpoint/tokenizer.json Normal file
View File

File diff suppressed because it is too large Load Diff

32
last-checkpoint/tokenizer_config.json Normal file
View File

@@ -0,0 +1,32 @@
{
"add_prefix_space": false,
"backend": "tokenizers",
"bos_token": "<|endoftext|>",
"clean_up_tokenization_spaces": false,
"eos_token": "<|endoftext|>",
"extra_special_tokens": [
"<|endoftext|>",
"<|im_start|>",
"<|im_end|>",
"<repo_name>",
"<reponame>",
"<file_sep>",
"<filename>",
"<gh_stars>",
"<issue_start>",
"<issue_comment>",
"<issue_closed>",
"<jupyter_start>",
"<jupyter_text>",
"<jupyter_code>",
"<jupyter_output>",
"<jupyter_script>",
"<empty_output>"
],
"is_local": false,
"model_max_length": 8192,
"pad_token": "<|endoftext|>",
"tokenizer_class": "TokenizersBackend",
"unk_token": "<|endoftext|>",
"vocab_size": 49152
}

842
last-checkpoint/trainer_state.json Normal file
View File

@@ -0,0 +1,842 @@
{
"best_global_step": 5000,
"best_metric": 1.0573397874832153,
"best_model_checkpoint": "/kaggle/working/sft_results/checkpoint-5000",
"epoch": 3.0,
"eval_steps": 500,
"global_step": 5241,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0286286859433152,
"grad_norm": 2.3644826412200928,
"learning_rate": 9.30379746835443e-06,
"loss": 2.383511810302734,
"step": 50
},
{
"epoch": 0.0572573718866304,
"grad_norm": 2.793384552001953,
"learning_rate": 1.879746835443038e-05,
"loss": 1.7826736450195313,
"step": 100
},
{
"epoch": 0.0858860578299456,
"grad_norm": 3.0280966758728027,
"learning_rate": 2.829113924050633e-05,
"loss": 1.6139263916015625,
"step": 150
},
{
"epoch": 0.1145147437732608,
"grad_norm": 2.1233787536621094,
"learning_rate": 2.9995184235255446e-05,
"loss": 1.5219964599609375,
"step": 200
},
{
"epoch": 0.143143429716576,
"grad_norm": 2.236110210418701,
"learning_rate": 2.9976281398044544e-05,
"loss": 1.483748321533203,
"step": 250
},
{
"epoch": 0.1717721156598912,
"grad_norm": 1.9872335195541382,
"learning_rate": 2.9943077476629365e-05,
"loss": 1.4081883239746094,
"step": 300
},
{
"epoch": 0.20040080160320642,
"grad_norm": 2.2232892513275146,
"learning_rate": 2.989560417795128e-05,
"loss": 1.3665139770507813,
"step": 350
},
{
"epoch": 0.2290294875465216,
"grad_norm": 2.2857749462127686,
"learning_rate": 2.9833906835002093e-05,
"loss": 1.3606991577148437,
"step": 400
},
{
"epoch": 0.25765817348983683,
"grad_norm": 2.1947431564331055,
"learning_rate": 2.9758044363534864e-05,
"loss": 1.2904006958007812,
"step": 450
},
{
"epoch": 0.286286859433152,
"grad_norm": 2.0554747581481934,
"learning_rate": 2.9668089205804355e-05,
"loss": 1.3378230285644532,
"step": 500
},
{
"epoch": 0.286286859433152,
"eval_loss": 1.2903425693511963,
"eval_runtime": 11.0207,
"eval_samples_per_second": 181.476,
"eval_steps_per_second": 5.717,
"step": 500
},
{
"epoch": 0.3149155453764672,
"grad_norm": 1.8369818925857544,
"learning_rate": 2.956412726139078e-05,
"loss": 1.27742431640625,
"step": 550
},
{
"epoch": 0.3435442313197824,
"grad_norm": 1.9453657865524292,
"learning_rate": 2.9446257805172974e-05,
"loss": 1.2718665313720703,
"step": 600
},
{
"epoch": 0.37217291726309765,
"grad_norm": 2.3209869861602783,
"learning_rate": 2.931459339252925e-05,
"loss": 1.3020565795898438,
"step": 650
},
{
"epoch": 0.40080160320641284,
"grad_norm": 2.067246198654175,
"learning_rate": 2.9169259751856517e-05,
"loss": 1.2828439331054688,
"step": 700
},
{
"epoch": 0.42943028914972803,
"grad_norm": 2.0901293754577637,
"learning_rate": 2.9010395664510292e-05,
"loss": 1.2508758544921874,
"step": 750
},
{
"epoch": 0.4580589750930432,
"grad_norm": 1.8446509838104248,
"learning_rate": 2.8838152832280215e-05,
"loss": 1.2217894744873048,
"step": 800
},
{
"epoch": 0.4866876610363584,
"grad_norm": 1.7549279928207397,
"learning_rate": 2.865269573252764e-05,
"loss": 1.2381829833984375,
"step": 850
},
{
"epoch": 0.5153163469796737,
"grad_norm": 1.96665358543396,
"learning_rate": 2.8454201461123648e-05,
"loss": 1.2288348388671875,
"step": 900
},
{
"epoch": 0.5439450329229888,
"grad_norm": 2.0387542247772217,
"learning_rate": 2.824285956333746e-05,
"loss": 1.1924710845947266,
"step": 950
},
{
"epoch": 0.572573718866304,
"grad_norm": 1.9063761234283447,
"learning_rate": 2.8018871852836696e-05,
"loss": 1.2280746459960938,
"step": 1000
},
{
"epoch": 0.572573718866304,
"eval_loss": 1.1913903951644897,
"eval_runtime": 11.0108,
"eval_samples_per_second": 181.639,
"eval_steps_per_second": 5.722,
"step": 1000
},
{
"epoch": 0.6012024048096193,
"grad_norm": 2.0231268405914307,
"learning_rate": 2.778245221897234e-05,
"loss": 1.2401188659667968,
"step": 1050
},
{
"epoch": 0.6298310907529344,
"grad_norm": 1.944474458694458,
"learning_rate": 2.753382642253251e-05,
"loss": 1.2116682434082031,
"step": 1100
},
{
"epoch": 0.6584597766962497,
"grad_norm": 1.8070766925811768,
"learning_rate": 2.7273231880159948e-05,
"loss": 1.190076904296875,
"step": 1150
},
{
"epoch": 0.6870884626395648,
"grad_norm": 1.8720484972000122,
"learning_rate": 2.700091743763917e-05,
"loss": 1.147376480102539,
"step": 1200
},
{
"epoch": 0.71571714858288,
"grad_norm": 1.8500466346740723,
"learning_rate": 2.6717143132269754e-05,
"loss": 1.1755177307128906,
"step": 1250
},
{
"epoch": 0.7443458345261953,
"grad_norm": 1.9229680299758911,
"learning_rate": 2.642217994455269e-05,
"loss": 1.1593478393554688,
"step": 1300
},
{
"epoch": 0.7729745204695104,
"grad_norm": 2.050952672958374,
"learning_rate": 2.6116309539426855e-05,
"loss": 1.153465576171875,
"step": 1350
},
{
"epoch": 0.8016032064128257,
"grad_norm": 1.862654685974121,
"learning_rate": 2.579982399730281e-05,
"loss": 1.1520048522949218,
"step": 1400
},
{
"epoch": 0.8302318923561408,
"grad_norm": 1.7920376062393188,
"learning_rate": 2.547302553515064e-05,
"loss": 1.1590766906738281,
"step": 1450
},
{
"epoch": 0.8588605782994561,
"grad_norm": 2.0007483959198,
"learning_rate": 2.513622621790828e-05,
"loss": 1.1361324310302734,
"step": 1500
},
{
"epoch": 0.8588605782994561,
"eval_loss": 1.1384907960891724,
"eval_runtime": 11.0081,
"eval_samples_per_second": 181.684,
"eval_steps_per_second": 5.723,
"step": 1500
},
{
"epoch": 0.8874892642427713,
"grad_norm": 1.9219996929168701,
"learning_rate": 2.478974766048587e-05,
"loss": 1.15419677734375,
"step": 1550
},
{
"epoch": 0.9161179501860864,
"grad_norm": 2.0371313095092773,
"learning_rate": 2.4433920720650622e-05,
"loss": 1.1277503204345702,
"step": 1600
},
{
"epoch": 0.9447466361294017,
"grad_norm": 1.8095065355300903,
"learning_rate": 2.406908518308563e-05,
"loss": 1.0934870910644532,
"step": 1650
},
{
"epoch": 0.9733753220727168,
"grad_norm": 1.8120338916778564,
"learning_rate": 2.369558943492418e-05,
"loss": 1.1021994018554688,
"step": 1700
},
{
"epoch": 1.0017177211565989,
"grad_norm": 1.5730403661727905,
"learning_rate": 2.3313790133069424e-05,
"loss": 1.1217953491210937,
"step": 1750
},
{
"epoch": 1.0303464070999142,
"grad_norm": 1.7535940408706665,
"learning_rate": 2.2924051863617208e-05,
"loss": 0.9622462463378906,
"step": 1800
},
{
"epoch": 1.0589750930432293,
"grad_norm": 1.9717522859573364,
"learning_rate": 2.2526746793707068e-05,
"loss": 0.967343978881836,
"step": 1850
},
{
"epoch": 1.0876037789865445,
"grad_norm": 1.8649731874465942,
"learning_rate": 2.21222543161341e-05,
"loss": 0.9579476928710937,
"step": 1900
},
{
"epoch": 1.1162324649298596,
"grad_norm": 1.8400834798812866,
"learning_rate": 2.1710960687060838e-05,
"loss": 0.9494917297363281,
"step": 1950
},
{
"epoch": 1.144861150873175,
"grad_norm": 1.9335684776306152,
"learning_rate": 2.1293258657175218e-05,
"loss": 0.9815617370605468,
"step": 2000
},
{
"epoch": 1.144861150873175,
"eval_loss": 1.1078585386276245,
"eval_runtime": 11.0109,
"eval_samples_per_second": 181.638,
"eval_steps_per_second": 5.722,
"step": 2000
},
{
"epoch": 1.17348983681649,
"grad_norm": 1.7664735317230225,
"learning_rate": 2.0869547096646885e-05,
"loss": 0.9837296295166016,
"step": 2050
},
{
"epoch": 1.2021185227598052,
"grad_norm": 1.9013019800186157,
"learning_rate": 2.0440230614239816e-05,
"loss": 0.92987060546875,
"step": 2100
},
{
"epoch": 1.2307472087031206,
"grad_norm": 2.0005931854248047,
"learning_rate": 2.000571917094512e-05,
"loss": 0.9705058288574219,
"step": 2150
},
{
"epoch": 1.2593758946464357,
"grad_norm": 1.6769753694534302,
"learning_rate": 1.956642768850292e-05,
"loss": 0.9469895935058594,
"step": 2200
},
{
"epoch": 1.2880045805897509,
"grad_norm": 1.7288581132888794,
"learning_rate": 1.9122775653187134e-05,
"loss": 0.9716603088378907,
"step": 2250
},
{
"epoch": 1.3166332665330662,
"grad_norm": 1.8138453960418701,
"learning_rate": 1.8675186715231472e-05,
"loss": 0.9610521697998047,
"step": 2300
},
{
"epoch": 1.3452619524763814,
"grad_norm": 1.9363412857055664,
"learning_rate": 1.8224088284279244e-05,
"loss": 0.9432389831542969,
"step": 2350
},
{
"epoch": 1.3738906384196965,
"grad_norm": 1.7704347372055054,
"learning_rate": 1.776991112124326e-05,
"loss": 0.9887850952148437,
"step": 2400
},
{
"epoch": 1.4025193243630119,
"grad_norm": 1.7712854146957397,
"learning_rate": 1.7313088926965525e-05,
"loss": 0.9210721588134766,
"step": 2450
},
{
"epoch": 1.431148010306327,
"grad_norm": 1.9473704099655151,
"learning_rate": 1.6854057928069515e-05,
"loss": 0.9342054748535156,
"step": 2500
},
{
"epoch": 1.431148010306327,
"eval_loss": 1.0880300998687744,
"eval_runtime": 11.0577,
"eval_samples_per_second": 180.869,
"eval_steps_per_second": 5.697,
"step": 2500
},
{
"epoch": 1.4597766962496421,
"grad_norm": 1.9916857481002808,
"learning_rate": 1.6393256460400636e-05,
"loss": 0.9525706481933593,
"step": 2550
},
{
"epoch": 1.4884053821929573,
"grad_norm": 1.74235999584198,
"learning_rate": 1.593112455045248e-05,
"loss": 0.9621110534667969,
"step": 2600
},
{
"epoch": 1.5170340681362724,
"grad_norm": 1.7582793235778809,
"learning_rate": 1.546810349517868e-05,
"loss": 0.9485533905029296,
"step": 2650
},
{
"epoch": 1.5456627540795878,
"grad_norm": 1.8177229166030884,
"learning_rate": 1.5004635440591563e-05,
"loss": 0.9394265747070313,
"step": 2700
},
{
"epoch": 1.574291440022903,
"grad_norm": 2.078019142150879,
"learning_rate": 1.4541162959550073e-05,
"loss": 0.952137451171875,
"step": 2750
},
{
"epoch": 1.602920125966218,
"grad_norm": 1.6308784484863281,
"learning_rate": 1.4078128629140056e-05,
"loss": 0.9435613250732422,
"step": 2800
},
{
"epoch": 1.6315488119095334,
"grad_norm": 2.2911417484283447,
"learning_rate": 1.3615974608050472e-05,
"loss": 0.9238491058349609,
"step": 2850
},
{
"epoch": 1.6601774978528485,
"grad_norm": 1.8992805480957031,
"learning_rate": 1.3155142214349223e-05,
"loss": 0.9344891357421875,
"step": 2900
},
{
"epoch": 1.6888061837961637,
"grad_norm": 2.08618426322937,
"learning_rate": 1.2696071504061656e-05,
"loss": 0.95639892578125,
"step": 2950
},
{
"epoch": 1.717434869739479,
"grad_norm": 1.7914495468139648,
"learning_rate": 1.223920085095419e-05,
"loss": 0.927100830078125,
"step": 3000
},
{
"epoch": 1.717434869739479,
"eval_loss": 1.0696886777877808,
"eval_runtime": 11.0891,
"eval_samples_per_second": 180.357,
"eval_steps_per_second": 5.681,
"step": 3000
},
{
"epoch": 1.7460635556827941,
"grad_norm": 1.7411514520645142,
"learning_rate": 1.1784966527924408e-05,
"loss": 0.9183525085449219,
"step": 3050
},
{
"epoch": 1.7746922416261093,
"grad_norm": 1.8799350261688232,
"learning_rate": 1.133380229039728e-05,
"loss": 0.9203878021240235,
"step": 3100
},
{
"epoch": 1.8033209275694246,
"grad_norm": 1.796403408050537,
"learning_rate": 1.088613896212532e-05,
"loss": 0.9330632019042969,
"step": 3150
},
{
"epoch": 1.8319496135127398,
"grad_norm": 1.818672776222229,
"learning_rate": 1.0442404023788332e-05,
"loss": 0.9458512878417968,
"step": 3200
},
{
"epoch": 1.860578299456055,
"grad_norm": 1.6023250818252563,
"learning_rate": 1.0003021204785405e-05,
"loss": 0.9331502532958984,
"step": 3250
},
{
"epoch": 1.8892069853993703,
"grad_norm": 1.9209835529327393,
"learning_rate": 9.568410078609159e-06,
"loss": 0.936725845336914,
"step": 3300
},
{
"epoch": 1.9178356713426854,
"grad_norm": 1.9322785139083862,
"learning_rate": 9.138985662188441e-06,
"loss": 0.94916015625,
"step": 3350
},
{
"epoch": 1.9464643572860005,
"grad_norm": 2.0159995555877686,
"learning_rate": 8.715158019582246e-06,
"loss": 0.9459092712402344,
"step": 3400
},
{
"epoch": 1.975093043229316,
"grad_norm": 1.8557511568069458,
"learning_rate": 8.297331870403134e-06,
"loss": 0.9145167541503906,
"step": 3450
},
{
"epoch": 2.0034354423131977,
"grad_norm": 1.831240177154541,
"learning_rate": 7.885906203344176e-06,
"loss": 0.918878173828125,
"step": 3500
},
{
"epoch": 2.0034354423131977,
"eval_loss": 1.0578292608261108,
"eval_runtime": 11.088,
"eval_samples_per_second": 180.375,
"eval_steps_per_second": 5.682,
"step": 3500
},
{
"epoch": 2.032064128256513,
"grad_norm": 1.746333122253418,
"learning_rate": 7.4812738951784534e-06,
"loss": 0.7855290222167969,
"step": 3550
},
{
"epoch": 2.0606928141998284,
"grad_norm": 1.8168827295303345,
"learning_rate": 7.083821335594914e-06,
"loss": 0.8110740661621094,
"step": 3600
},
{
"epoch": 2.0893215001431433,
"grad_norm": 1.999387264251709,
"learning_rate": 6.693928058228819e-06,
"loss": 0.8094084167480469,
"step": 3650
},
{
"epoch": 2.1179501860864587,
"grad_norm": 1.7955976724624634,
"learning_rate": 6.311966378239187e-06,
"loss": 0.7892781066894531,
"step": 3700
},
{
"epoch": 2.1465788720297736,
"grad_norm": 1.9907435178756714,
"learning_rate": 5.9383010367792605e-06,
"loss": 0.7843812561035156,
"step": 3750
},
{
"epoch": 2.175207557973089,
"grad_norm": 1.774929165840149,
"learning_rate": 5.573288852699494e-06,
"loss": 0.833739013671875,
"step": 3800
},
{
"epoch": 2.2038362439164043,
"grad_norm": 1.8390209674835205,
"learning_rate": 5.217278381815659e-06,
"loss": 0.7984774780273437,
"step": 3850
},
{
"epoch": 2.2324649298597192,
"grad_norm": 1.8013503551483154,
"learning_rate": 4.87060958406751e-06,
"loss": 0.8090000915527343,
"step": 3900
},
{
"epoch": 2.2610936158030346,
"grad_norm": 1.9675740003585815,
"learning_rate": 4.533613498885722e-06,
"loss": 0.8269770812988281,
"step": 3950
},
{
"epoch": 2.28972230174635,
"grad_norm": 1.9597092866897583,
"learning_rate": 4.206611929077178e-06,
"loss": 0.7955089569091797,
"step": 4000
},
{
"epoch": 2.28972230174635,
"eval_loss": 1.0618994235992432,
"eval_runtime": 10.9993,
"eval_samples_per_second": 181.83,
"eval_steps_per_second": 5.728,
"step": 4000
},
{
"epoch": 2.318350987689665,
"grad_norm": 1.9027864933013916,
"learning_rate": 3.88991713353049e-06,
"loss": 0.7880819702148437,
"step": 4050
},
{
"epoch": 2.34697967363298,
"grad_norm": 2.1922247409820557,
"learning_rate": 3.58383152903509e-06,
"loss": 0.7940321350097657,
"step": 4100
},
{
"epoch": 2.3756083595762956,
"grad_norm": 1.7064813375473022,
"learning_rate": 3.2886474014987678e-06,
"loss": 0.8168456268310547,
"step": 4150
},
{
"epoch": 2.4042370455196105,
"grad_norm": 1.8323137760162354,
"learning_rate": 3.0046466268392724e-06,
"loss": 0.7974643707275391,
"step": 4200
},
{
"epoch": 2.432865731462926,
"grad_norm": 1.8089032173156738,
"learning_rate": 2.7321004018166394e-06,
"loss": 0.8085546875,
"step": 4250
},
{
"epoch": 2.461494417406241,
"grad_norm": 2.0021238327026367,
"learning_rate": 2.4712689850631743e-06,
"loss": 0.7902973937988281,
"step": 4300
},
{
"epoch": 2.490123103349556,
"grad_norm": 1.8765511512756348,
"learning_rate": 2.2224014485584178e-06,
"loss": 0.8023321533203125,
"step": 4350
},
{
"epoch": 2.5187517892928715,
"grad_norm": 1.8883023262023926,
"learning_rate": 1.9857354397864695e-06,
"loss": 0.8000016021728515,
"step": 4400
},
{
"epoch": 2.547380475236187,
"grad_norm": 1.8686455488204956,
"learning_rate": 1.7614969548026666e-06,
"loss": 0.7877293395996093,
"step": 4450
},
{
"epoch": 2.5760091611795017,
"grad_norm": 2.149655818939209,
"learning_rate": 1.549900122426474e-06,
"loss": 0.8140004730224609,
"step": 4500
},
{
"epoch": 2.5760091611795017,
"eval_loss": 1.0588970184326172,
"eval_runtime": 11.0391,
"eval_samples_per_second": 181.174,
"eval_steps_per_second": 5.707,
"step": 4500
},
{
"epoch": 2.604637847122817,
"grad_norm": 2.0576822757720947,
"learning_rate": 1.3511469997665038e-06,
"loss": 0.7878628540039062,
"step": 4550
},
{
"epoch": 2.6332665330661325,
"grad_norm": 1.9110583066940308,
"learning_rate": 1.1654273792730663e-06,
"loss": 0.7879611206054687,
"step": 4600
},
{
"epoch": 2.6618952190094474,
"grad_norm": 1.9194525480270386,
"learning_rate": 9.929186075023938e-07,
"loss": 0.8128913116455078,
"step": 4650
},
{
"epoch": 2.6905239049527627,
"grad_norm": 1.9693336486816406,
"learning_rate": 8.337854157656449e-07,
"loss": 0.8126602172851562,
"step": 4700
},
{
"epoch": 2.719152590896078,
"grad_norm": 1.909978985786438,
"learning_rate": 6.881797628244302e-07,
"loss": 0.8042438507080079,
"step": 4750
},
{
"epoch": 2.747781276839393,
"grad_norm": 2.284548282623291,
"learning_rate": 5.56240689783013e-07,
"loss": 0.8226654052734375,
"step": 4800
},
{
"epoch": 2.7764099627827084,
"grad_norm": 1.9905219078063965,
"learning_rate": 4.3809418731579175e-07,
"loss": 0.7958916473388672,
"step": 4850
},
{
"epoch": 2.8050386487260237,
"grad_norm": 1.910882592201233,
"learning_rate": 3.338530753568597e-07,
"loss": 0.8007672119140625,
"step": 4900
},
{
"epoch": 2.8336673346693386,
"grad_norm": 2.1473939418792725,
"learning_rate": 2.4361689536647804e-07,
"loss": 0.8120519256591797,
"step": 4950
},
{
"epoch": 2.862296020612654,
"grad_norm": 1.6422446966171265,
"learning_rate": 1.6747181527739574e-07,
"loss": 0.8316423797607422,
"step": 5000
},
{
"epoch": 2.862296020612654,
"eval_loss": 1.0573397874832153,
"eval_runtime": 10.9846,
"eval_samples_per_second": 182.074,
"eval_steps_per_second": 5.735,
"step": 5000
},
{
"epoch": 2.8909247065559693,
"grad_norm": 2.2556588649749756,
"learning_rate": 1.0549054721174456e-07,
"loss": 0.7857763671875,
"step": 5050
},
{
"epoch": 2.9195533924992843,
"grad_norm": 2.0582995414733887,
"learning_rate": 5.7732278047101795e-08,
"loss": 0.7936778259277344,
"step": 5100
},
{
"epoch": 2.9481820784425996,
"grad_norm": 2.0624160766601562,
"learning_rate": 2.424261289802554e-08,
"loss": 0.8139122009277344,
"step": 5150
},
{
"epoch": 2.9768107643859145,
"grad_norm": 1.8928687572479248,
"learning_rate": 5.0535315670102725e-09,
"loss": 0.7940410614013672,
"step": 5200
}
],
"logging_steps": 50,
"max_steps": 5241,
"num_input_tokens_seen": 0,
"num_train_epochs": 3,
"save_steps": 500,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 5.845420066052506e+16,
"train_batch_size": 16,
"trial_name": null,
"trial_params": null
}

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

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:a7359435fd2b5233fdb5b1abcb0c6f9ff3b2fa08eda77c14af00f76e2dda0f98
size 5201