Instructions to use KexuanShi/sft_gemma2_2b_code_layerdrop_p005 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use KexuanShi/sft_gemma2_2b_code_layerdrop_p005 with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="KexuanShi/sft_gemma2_2b_code_layerdrop_p005")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("KexuanShi/sft_gemma2_2b_code_layerdrop_p005")
model = AutoModelForCausalLM.from_pretrained("KexuanShi/sft_gemma2_2b_code_layerdrop_p005", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use KexuanShi/sft_gemma2_2b_code_layerdrop_p005 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "KexuanShi/sft_gemma2_2b_code_layerdrop_p005"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "KexuanShi/sft_gemma2_2b_code_layerdrop_p005",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/KexuanShi/sft_gemma2_2b_code_layerdrop_p005

SGLang

How to use KexuanShi/sft_gemma2_2b_code_layerdrop_p005 with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "KexuanShi/sft_gemma2_2b_code_layerdrop_p005" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "KexuanShi/sft_gemma2_2b_code_layerdrop_p005",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "KexuanShi/sft_gemma2_2b_code_layerdrop_p005" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "KexuanShi/sft_gemma2_2b_code_layerdrop_p005",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use KexuanShi/sft_gemma2_2b_code_layerdrop_p005 with Docker Model Runner:
```
docker model run hf.co/KexuanShi/sft_gemma2_2b_code_layerdrop_p005
```

KexuanShi commited on Oct 5

Commit

3284ff5

verified ·

1 Parent(s): 9b2dfdf

Upload checkpoint-567

Browse files

Files changed (7) hide show

checkpoint-567/config.json +65 -0
checkpoint-567/generation_config.json +10 -0
checkpoint-567/model.safetensors +3 -0
checkpoint-567/tokenizer.json +3 -0
checkpoint-567/tokenizer_config.json +20 -0
checkpoint-567/trainer_state.json +594 -0
checkpoint-567/training_args.bin +3 -0

checkpoint-567/config.json ADDED Viewed

	@@ -0,0 +1,65 @@

+{
+  "architectures": [
+    "Gemma2ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "attn_logit_softcapping": 50.0,
+  "bos_token_id": 2,
+  "cache_implementation": "hybrid",
+  "dtype": "bfloat16",
+  "eos_token_id": 1,
+  "final_logit_softcapping": 30.0,
+  "head_dim": 256,
+  "hidden_act": "gelu_pytorch_tanh",
+  "hidden_activation": "gelu_pytorch_tanh",
+  "hidden_size": 2304,
+  "initializer_range": 0.02,
+  "intermediate_size": 9216,
+  "layer_types": [
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 8192,
+  "model_type": "gemma2",
+  "num_attention_heads": 8,
+  "num_hidden_layers": 26,
+  "num_key_value_heads": 4,
+  "pad_token_id": 0,
+  "query_pre_attn_scalar": 256,
+  "rms_norm_eps": 1e-06,
+  "rope_parameters": {
+    "rope_theta": 10000.0,
+    "rope_type": "default"
+  },
+  "sliding_window": 4096,
+  "tie_word_embeddings": true,
+  "transformers_version": "5.17.0",
+  "use_bidirectional_attention": null,
+  "use_cache": false,
+  "vocab_size": 256000
+}

checkpoint-567/generation_config.json ADDED Viewed

	@@ -0,0 +1,10 @@

+{
+  "_from_model_config": true,
+  "bos_token_id": 2,
+  "cache_implementation": "hybrid",
+  "eos_token_id": [
+    1
+  ],
+  "pad_token_id": 0,
+  "transformers_version": "5.17.0"
+}

checkpoint-567/model.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:561e0afcf303a802b80c77ad5e4286c37e455ec122747c2df07e72d8ed9a233f
+size 5228717512

checkpoint-567/tokenizer.json ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:487cee8724215dcd2dde8888539e8b1bf844ceb5dbbe27f7845abda69eeb060f
+size 34362872

checkpoint-567/tokenizer_config.json ADDED Viewed

	@@ -0,0 +1,20 @@

+{
+  "backend": "tokenizers",
+  "bos_token": "<bos>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<eos>",
+  "extra_special_tokens": [
+    "<start_of_turn>",
+    "<end_of_turn>"
+  ],
+  "is_local": true,
+  "local_files_only": false,
+  "mask_token": "<mask>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "GemmaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

checkpoint-567/trainer_state.json ADDED Viewed

	@@ -0,0 +1,594 @@

+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 567,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 1.2536803647875785,
+      "epoch": 0.05291005291005291,
+      "grad_norm": 8.8125,
+      "learning_rate": 3.2142857142857147e-06,
+      "loss": 1.1722795486450195,
+      "mean_token_accuracy": 0.7258133076131343,
+      "num_tokens": 710093.0,
+      "step": 10
+    },
+    {
+      "entropy": 0.9760579235851765,
+      "epoch": 0.10582010582010581,
+      "grad_norm": 2.65625,
+      "learning_rate": 6.785714285714287e-06,
+      "loss": 0.9763177871704102,
+      "mean_token_accuracy": 0.7567757397890091,
+      "num_tokens": 1429271.0,
+      "step": 20
+    },
+    {
+      "entropy": 0.794147289544344,
+      "epoch": 0.15873015873015872,
+      "grad_norm": 2.46875,
+      "learning_rate": 1.0357142857142859e-05,
+      "loss": 0.8046525001525879,
+      "mean_token_accuracy": 0.7873034350574016,
+      "num_tokens": 2149735.0,
+      "step": 30
+    },
+    {
+      "entropy": 0.7088500954210758,
+      "epoch": 0.21164021164021163,
+      "grad_norm": 1.4609375,
+      "learning_rate": 1.3928571428571429e-05,
+      "loss": 0.7121071815490723,
+      "mean_token_accuracy": 0.8070594437420369,
+      "num_tokens": 2868867.0,
+      "step": 40
+    },
+    {
+      "entropy": 0.683020292967558,
+      "epoch": 0.26455026455026454,
+      "grad_norm": 1.46875,
+      "learning_rate": 1.7500000000000002e-05,
+      "loss": 0.68443603515625,
+      "mean_token_accuracy": 0.8138657048344612,
+      "num_tokens": 3582476.0,
+      "step": 50
+    },
+    {
+      "entropy": 0.6564815938472748,
+      "epoch": 0.31746031746031744,
+      "grad_norm": 1.4296875,
+      "learning_rate": 1.999986795783372e-05,
+      "loss": 0.6578450202941895,
+      "mean_token_accuracy": 0.8192978233098984,
+      "num_tokens": 4287689.0,
+      "step": 60
+    },
+    {
+      "entropy": 0.6446133196353913,
+      "epoch": 0.37037037037037035,
+      "grad_norm": 1.5859375,
+      "learning_rate": 1.9997520638548385e-05,
+      "loss": 0.651158332824707,
+      "mean_token_accuracy": 0.8207244381308556,
+      "num_tokens": 5011191.0,
+      "step": 70
+    },
+    {
+      "entropy": 0.6360202118754387,
+      "epoch": 0.42328042328042326,
+      "grad_norm": 1.3984375,
+      "learning_rate": 1.9992239841688418e-05,
+      "loss": 0.6350794792175293,
+      "mean_token_accuracy": 0.8251068785786628,
+      "num_tokens": 5714842.0,
+      "step": 80
+    },
+    {
+      "entropy": 0.6189912840723991,
+      "epoch": 0.47619047619047616,
+      "grad_norm": 1.328125,
+      "learning_rate": 1.9984027116747914e-05,
+      "loss": 0.622182559967041,
+      "mean_token_accuracy": 0.8279523886740208,
+      "num_tokens": 6424614.0,
+      "step": 90
+    },
+    {
+      "entropy": 0.6159785229712724,
+      "epoch": 0.5291005291005291,
+      "grad_norm": 1.3671875,
+      "learning_rate": 1.997288487350878e-05,
+      "loss": 0.617555046081543,
+      "mean_token_accuracy": 0.8284852005541324,
+      "num_tokens": 7139778.0,
+      "step": 100
+    },
+    {
+      "entropy": 0.6129939660429955,
+      "epoch": 0.582010582010582,
+      "grad_norm": 1.328125,
+      "learning_rate": 1.9958816381333684e-05,
+      "loss": 0.6128347873687744,
+      "mean_token_accuracy": 0.8294584318995476,
+      "num_tokens": 7852540.0,
+      "step": 110
+    },
+    {
+      "entropy": 0.6052542962133884,
+      "epoch": 0.6349206349206349,
+      "grad_norm": 1.3359375,
+      "learning_rate": 1.994182576820673e-05,
+      "loss": 0.6046356201171875,
+      "mean_token_accuracy": 0.831394524872303,
+      "num_tokens": 8568056.0,
+      "step": 120
+    },
+    {
+      "entropy": 0.6013224326074124,
+      "epoch": 0.6878306878306878,
+      "grad_norm": 1.3203125,
+      "learning_rate": 1.9921918019522238e-05,
+      "loss": 0.6063410758972168,
+      "mean_token_accuracy": 0.8313738636672496,
+      "num_tokens": 9276742.0,
+      "step": 130
+    },
+    {
+      "entropy": 0.5983927462249994,
+      "epoch": 0.7407407407407407,
+      "grad_norm": 1.3125,
+      "learning_rate": 1.9899098976621922e-05,
+      "loss": 0.5977112770080566,
+      "mean_token_accuracy": 0.8335464030504227,
+      "num_tokens": 9990163.0,
+      "step": 140
+    },
+    {
+      "entropy": 0.5922725383192301,
+      "epoch": 0.7936507936507936,
+      "grad_norm": 1.5078125,
+      "learning_rate": 1.9873375335080915e-05,
+      "loss": 0.5917873382568359,
+      "mean_token_accuracy": 0.8347524181008339,
+      "num_tokens": 10710006.0,
+      "step": 150
+    },
+    {
+      "entropy": 0.5920293003320694,
+      "epoch": 0.8465608465608465,
+      "grad_norm": 1.3046875,
+      "learning_rate": 1.9844754642743164e-05,
+      "loss": 0.5962053298950195,
+      "mean_token_accuracy": 0.8335559628903866,
+      "num_tokens": 11416822.0,
+      "step": 160
+    },
+    {
+      "entropy": 0.5966673269867897,
+      "epoch": 0.8994708994708994,
+      "grad_norm": 1.3828125,
+      "learning_rate": 1.981324529750672e-05,
+      "loss": 0.6019061088562012,
+      "mean_token_accuracy": 0.83258865326643,
+      "num_tokens": 12123118.0,
+      "step": 170
+    },
+    {
+      "entropy": 0.5854565776884556,
+      "epoch": 0.9523809523809523,
+      "grad_norm": 1.359375,
+      "learning_rate": 1.9778856544859647e-05,
+      "loss": 0.5845203399658203,
+      "mean_token_accuracy": 0.8360438510775566,
+      "num_tokens": 12831058.0,
+      "step": 180
+    },
+    {
+      "entropy": 0.5759805988520383,
+      "epoch": 1.0052910052910053,
+      "grad_norm": 1.3046875,
+      "learning_rate": 1.9741598475167173e-05,
+      "loss": 0.5696067810058594,
+      "mean_token_accuracy": 0.839682175219059,
+      "num_tokens": 13547943.0,
+      "step": 190
+    },
+    {
+      "entropy": 0.5275494448840619,
+      "epoch": 1.0582010582010581,
+      "grad_norm": 1.3984375,
+      "learning_rate": 1.9701482020711004e-05,
+      "loss": 0.5299928665161133,
+      "mean_token_accuracy": 0.8484233327209949,
+      "num_tokens": 14264772.0,
+      "step": 200
+    },
+    {
+      "entropy": 0.5196751751005649,
+      "epoch": 1.1111111111111112,
+      "grad_norm": 1.2109375,
+      "learning_rate": 1.9658518952481543e-05,
+      "loss": 0.5208037853240967,
+      "mean_token_accuracy": 0.8509362854063511,
+      "num_tokens": 14985565.0,
+      "step": 210
+    },
+    {
+      "entropy": 0.5303940393030644,
+      "epoch": 1.164021164021164,
+      "grad_norm": 1.3359375,
+      "learning_rate": 1.9612721876724054e-05,
+      "loss": 0.5318955421447754,
+      "mean_token_accuracy": 0.8480072498321534,
+      "num_tokens": 15701796.0,
+      "step": 220
+    },
+    {
+      "entropy": 0.5232694145292044,
+      "epoch": 1.216931216931217,
+      "grad_norm": 1.359375,
+      "learning_rate": 1.9564104231239726e-05,
+      "loss": 0.5231654167175293,
+      "mean_token_accuracy": 0.8490844376385212,
+      "num_tokens": 16412522.0,
+      "step": 230
+    },
+    {
+      "entropy": 0.529466836899519,
+      "epoch": 1.2698412698412698,
+      "grad_norm": 1.3046875,
+      "learning_rate": 1.9512680281442745e-05,
+      "loss": 0.5309067726135254,
+      "mean_token_accuracy": 0.8485323786735535,
+      "num_tokens": 17126523.0,
+      "step": 240
+    },
+    {
+      "entropy": 0.527790617197752,
+      "epoch": 1.3227513227513228,
+      "grad_norm": 1.3125,
+      "learning_rate": 1.9458465116174534e-05,
+      "loss": 0.5262090682983398,
+      "mean_token_accuracy": 0.8493455089628696,
+      "num_tokens": 17834934.0,
+      "step": 250
+    },
+    {
+      "entropy": 0.528411227837205,
+      "epoch": 1.3756613756613756,
+      "grad_norm": 1.265625,
+      "learning_rate": 1.940147464327637e-05,
+      "loss": 0.529714298248291,
+      "mean_token_accuracy": 0.8480914957821369,
+      "num_tokens": 18553413.0,
+      "step": 260
+    },
+    {
+      "entropy": 0.516933124884963,
+      "epoch": 1.4285714285714286,
+      "grad_norm": 1.296875,
+      "learning_rate": 1.9341725584921712e-05,
+      "loss": 0.5172879219055175,
+      "mean_token_accuracy": 0.8517736725509166,
+      "num_tokens": 19270191.0,
+      "step": 270
+    },
+    {
+      "entropy": 0.5223661050200462,
+      "epoch": 1.4814814814814814,
+      "grad_norm": 1.2421875,
+      "learning_rate": 1.9279235472709554e-05,
+      "loss": 0.5231949329376221,
+      "mean_token_accuracy": 0.8496842503547668,
+      "num_tokens": 19976552.0,
+      "step": 280
+    },
+    {
+      "entropy": 0.5293067336082459,
+      "epoch": 1.5343915343915344,
+      "grad_norm": 1.2421875,
+      "learning_rate": 1.92140226425203e-05,
+      "loss": 0.5295753479003906,
+      "mean_token_accuracy": 0.8479710258543491,
+      "num_tokens": 20676613.0,
+      "step": 290
+    },
+    {
+      "entropy": 0.5302139949053526,
+      "epoch": 1.5873015873015874,
+      "grad_norm": 1.28125,
+      "learning_rate": 1.914610622913566e-05,
+      "loss": 0.530374813079834,
+      "mean_token_accuracy": 0.8484688423573971,
+      "num_tokens": 21385978.0,
+      "step": 300
+    },
+    {
+      "entropy": 0.5183596257120371,
+      "epoch": 1.6402116402116402,
+      "grad_norm": 1.1953125,
+      "learning_rate": 1.9075506160624068e-05,
+      "loss": 0.519154167175293,
+      "mean_token_accuracy": 0.8509341597557067,
+      "num_tokens": 22094336.0,
+      "step": 310
+    },
+    {
+      "entropy": 0.5201449614018202,
+      "epoch": 1.693121693121693,
+      "grad_norm": 1.328125,
+      "learning_rate": 1.900224315249343e-05,
+      "loss": 0.5171724796295166,
+      "mean_token_accuracy": 0.8508495308458806,
+      "num_tokens": 22798906.0,
+      "step": 320
+    },
+    {
+      "entropy": 0.5111908499151468,
+      "epoch": 1.746031746031746,
+      "grad_norm": 1.2265625,
+      "learning_rate": 1.8926338701612738e-05,
+      "loss": 0.511273717880249,
+      "mean_token_accuracy": 0.8524932019412518,
+      "num_tokens": 23511239.0,
+      "step": 330
+    },
+    {
+      "entropy": 0.5265866108238697,
+      "epoch": 1.798941798941799,
+      "grad_norm": 1.265625,
+      "learning_rate": 1.884781507990445e-05,
+      "loss": 0.5289421558380127,
+      "mean_token_accuracy": 0.8486531592905522,
+      "num_tokens": 24231185.0,
+      "step": 340
+    },
+    {
+      "entropy": 0.5189403794705868,
+      "epoch": 1.8518518518518519,
+      "grad_norm": 1.2578125,
+      "learning_rate": 1.8766695327809463e-05,
+      "loss": 0.5158460140228271,
+      "mean_token_accuracy": 0.8517816573381424,
+      "num_tokens": 24944285.0,
+      "step": 350
+    },
+    {
+      "entropy": 0.5055529039353133,
+      "epoch": 1.9047619047619047,
+      "grad_norm": 1.1953125,
+      "learning_rate": 1.8683003247526567e-05,
+      "loss": 0.5064782619476318,
+      "mean_token_accuracy": 0.8533773042261601,
+      "num_tokens": 25670441.0,
+      "step": 360
+    },
+    {
+      "entropy": 0.5245815236121416,
+      "epoch": 1.9576719576719577,
+      "grad_norm": 1.2421875,
+      "learning_rate": 1.8596763396028384e-05,
+      "loss": 0.5262872219085694,
+      "mean_token_accuracy": 0.8492341041564941,
+      "num_tokens": 26379786.0,
+      "step": 370
+    },
+    {
+      "entropy": 0.5117530789226293,
+      "epoch": 2.0105820105820107,
+      "grad_norm": 1.390625,
+      "learning_rate": 1.8508001077855876e-05,
+      "loss": 0.5020773887634278,
+      "mean_token_accuracy": 0.854968623816967,
+      "num_tokens": 27097166.0,
+      "step": 380
+    },
+    {
+      "entropy": 0.44686204604804514,
+      "epoch": 2.0634920634920633,
+      "grad_norm": 1.3046875,
+      "learning_rate": 1.8416742337693436e-05,
+      "loss": 0.4472813606262207,
+      "mean_token_accuracy": 0.8682501375675201,
+      "num_tokens": 27818991.0,
+      "step": 390
+    },
+    {
+      "entropy": 0.4516366470605135,
+      "epoch": 2.1164021164021163,
+      "grad_norm": 1.484375,
+      "learning_rate": 1.8323013952726877e-05,
+      "loss": 0.45279760360717775,
+      "mean_token_accuracy": 0.8667486943304539,
+      "num_tokens": 28524822.0,
+      "step": 400
+    },
+    {
+      "entropy": 0.44368173032999036,
+      "epoch": 2.1693121693121693,
+      "grad_norm": 1.328125,
+      "learning_rate": 1.8226843424786434e-05,
+      "loss": 0.4443831443786621,
+      "mean_token_accuracy": 0.8681288480758667,
+      "num_tokens": 29245634.0,
+      "step": 410
+    },
+    {
+      "entropy": 0.44680118896067145,
+      "epoch": 2.2222222222222223,
+      "grad_norm": 1.3046875,
+      "learning_rate": 1.8128258972277176e-05,
+      "loss": 0.4440959930419922,
+      "mean_token_accuracy": 0.8689466655254364,
+      "num_tokens": 29967135.0,
+      "step": 420
+    },
+    {
+      "entropy": 0.4494645904749632,
+      "epoch": 2.2751322751322753,
+      "grad_norm": 1.328125,
+      "learning_rate": 1.8027289521899143e-05,
+      "loss": 0.45146980285644533,
+      "mean_token_accuracy": 0.8666525632143021,
+      "num_tokens": 30680274.0,
+      "step": 430
+    },
+    {
+      "entropy": 0.4557589769363403,
+      "epoch": 2.328042328042328,
+      "grad_norm": 1.2734375,
+      "learning_rate": 1.7923964700159658e-05,
+      "loss": 0.45585927963256834,
+      "mean_token_accuracy": 0.8663338787853718,
+      "num_tokens": 31386859.0,
+      "step": 440
+    },
+    {
+      "entropy": 0.46223078556358815,
+      "epoch": 2.380952380952381,
+      "grad_norm": 1.390625,
+      "learning_rate": 1.78183148246803e-05,
+      "loss": 0.4587599754333496,
+      "mean_token_accuracy": 0.86525354757905,
+      "num_tokens": 32111007.0,
+      "step": 450
+    },
+    {
+      "entropy": 0.4548660650849342,
+      "epoch": 2.433862433862434,
+      "grad_norm": 1.265625,
+      "learning_rate": 1.77103708953011e-05,
+      "loss": 0.4531528949737549,
+      "mean_token_accuracy": 0.8663033962249755,
+      "num_tokens": 32819180.0,
+      "step": 460
+    },
+    {
+      "entropy": 0.4630272053182125,
+      "epoch": 2.4867724867724865,
+      "grad_norm": 1.28125,
+      "learning_rate": 1.7600164584984548e-05,
+      "loss": 0.4610149383544922,
+      "mean_token_accuracy": 0.8639790855348111,
+      "num_tokens": 33523113.0,
+      "step": 470
+    },
+    {
+      "entropy": 0.4509055320173502,
+      "epoch": 2.5396825396825395,
+      "grad_norm": 1.34375,
+      "learning_rate": 1.7487728230522085e-05,
+      "loss": 0.44989833831787107,
+      "mean_token_accuracy": 0.8673267938196659,
+      "num_tokens": 34240357.0,
+      "step": 480
+    },
+    {
+      "entropy": 0.455976203456521,
+      "epoch": 2.5925925925925926,
+      "grad_norm": 1.2265625,
+      "learning_rate": 1.737309482304585e-05,
+      "loss": 0.4550386905670166,
+      "mean_token_accuracy": 0.8660441562533379,
+      "num_tokens": 34958032.0,
+      "step": 490
+    },
+    {
+      "entropy": 0.4540476597845554,
+      "epoch": 2.6455026455026456,
+      "grad_norm": 1.328125,
+      "learning_rate": 1.7256297998348388e-05,
+      "loss": 0.45427827835083007,
+      "mean_token_accuracy": 0.866205920279026,
+      "num_tokens": 35658658.0,
+      "step": 500
+    },
+    {
+      "entropy": 0.45439887307584287,
+      "epoch": 2.6984126984126986,
+      "grad_norm": 1.3203125,
+      "learning_rate": 1.7137372027013212e-05,
+      "loss": 0.45563058853149413,
+      "mean_token_accuracy": 0.865429712831974,
+      "num_tokens": 36364754.0,
+      "step": 510
+    },
+    {
+      "entropy": 0.46197318099439144,
+      "epoch": 2.751322751322751,
+      "grad_norm": 1.296875,
+      "learning_rate": 1.7016351804359134e-05,
+      "loss": 0.46036925315856936,
+      "mean_token_accuracy": 0.8651507623493672,
+      "num_tokens": 37074678.0,
+      "step": 520
+    },
+    {
+      "entropy": 0.47125925347208975,
+      "epoch": 2.804232804232804,
+      "grad_norm": 1.296875,
+      "learning_rate": 1.6893272840201243e-05,
+      "loss": 0.4696796417236328,
+      "mean_token_accuracy": 0.862788101285696,
+      "num_tokens": 37787128.0,
+      "step": 530
+    },
+    {
+      "entropy": 0.4597961250692606,
+      "epoch": 2.857142857142857,
+      "grad_norm": 1.3203125,
+      "learning_rate": 1.6768171248431603e-05,
+      "loss": 0.45906572341918944,
+      "mean_token_accuracy": 0.8650128476321697,
+      "num_tokens": 38504013.0,
+      "step": 540
+    },
+    {
+      "entropy": 0.4489801775664091,
+      "epoch": 2.91005291005291,
+      "grad_norm": 1.3046875,
+      "learning_rate": 1.66410837364227e-05,
+      "loss": 0.4477699279785156,
+      "mean_token_accuracy": 0.8676867328584195,
+      "num_tokens": 39212782.0,
+      "step": 550
+    },
+    {
+      "entropy": 0.4513770941644907,
+      "epoch": 2.962962962962963,
+      "grad_norm": 1.2734375,
+      "learning_rate": 1.651204759425674e-05,
+      "loss": 0.4503082275390625,
+      "mean_token_accuracy": 0.8672237955033779,
+      "num_tokens": 39931947.0,
+      "step": 560
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1890,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "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": 7.297082180742676e+17,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-567/training_args.bin ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:b8c85992cf63551e842ab98a6f49581a6e79e2e3e8210ccdf817e4d5ce49c466
+size 5841