Instructions to use Ba2han/test_CPTlsft with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Ba2han/test_CPTlsft with Transformers:

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

pipe = pipeline("text-generation", model="Ba2han/test_CPTlsft")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

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

tokenizer = AutoTokenizer.from_pretrained("Ba2han/test_CPTlsft")
model = AutoModelForCausalLM.from_pretrained("Ba2han/test_CPTlsft", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Ba2han/test_CPTlsft with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Ba2han/test_CPTlsft"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Ba2han/test_CPTlsft",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Ba2han/test_CPTlsft

SGLang

How to use Ba2han/test_CPTlsft 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 "Ba2han/test_CPTlsft" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Ba2han/test_CPTlsft",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "Ba2han/test_CPTlsft" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Ba2han/test_CPTlsft",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Desktop
Docker Model Runner
How to use Ba2han/test_CPTlsft with Docker Model Runner:
```
docker model run hf.co/Ba2han/test_CPTlsft
```

Ba2han commited on Aug 6

Commit

d219e00

verified ·

1 Parent(s): d6b2f81

Training in progress, step 5892, checkpoint

Browse files

Files changed (4) hide show

last-checkpoint/model.safetensors +1 -1
last-checkpoint/optimizer.pt +1 -1
last-checkpoint/scheduler.pt +1 -1
last-checkpoint/trainer_state.json +3440 -3

last-checkpoint/model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:010b8a20033cfaa884caba83e2c0880de02a7803d4f38c36752deafc7d44968a
 size 2934397032

 version https://git-lfs.github.com/spec/v1
+oid sha256:2ec5b297e9f09c47ebe739ca4f533dc14be4963410cdcdf702a5d964e759db25
 size 2934397032

last-checkpoint/optimizer.pt CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3580910646bbdb222a25f3563fecf307765fed66d9c781f91fdd1c0b181fcd6e
 size 1471680120

 version https://git-lfs.github.com/spec/v1
+oid sha256:c1f4a672144a8af6b0391ad2d313ff94330906bf0a4cd9e7864556368b86e73f
 size 1471680120

last-checkpoint/scheduler.pt CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c878ff125fd1c7e41c3ba5fb83e3759dd9ddfabdac4b17acbe314bd6122c14a3
 size 9785

 version https://git-lfs.github.com/spec/v1
+oid sha256:f74ea87819da762c362c08906691208182892b7ce0f78b25613c7278cd404419
 size 9785

last-checkpoint/trainer_state.json CHANGED Viewed

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.5000483753519943,
   "eval_steps": 500,
-  "global_step": 4910,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -17193,6 +17193,3443 @@
       "learning_rate": 0.0008682814710042432,
       "loss": 2.0071849822998047,
       "step": 4910
     }
   ],
   "logging_steps": 2,
@@ -17212,7 +20649,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.5133462673573806e+18,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null

   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
+  "epoch": 0.6000580504223932,
   "eval_steps": 500,
+  "global_step": 5892,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
       "learning_rate": 0.0008682814710042432,
       "loss": 2.0071849822998047,
       "step": 4910
+    },
+    {
+      "epoch": 0.5002520610446021,
+      "grad_norm": 0.10800334811210632,
+      "learning_rate": 0.000867927864214993,
+      "loss": 2.1183738708496094,
+      "step": 4912
+    },
+    {
+      "epoch": 0.5004557467372098,
+      "grad_norm": 0.13783392310142517,
+      "learning_rate": 0.0008675742574257426,
+      "loss": 2.212221622467041,
+      "step": 4914
+    },
+    {
+      "epoch": 0.5006594324298176,
+      "grad_norm": 0.11800715327262878,
+      "learning_rate": 0.0008672206506364922,
+      "loss": 2.0681071281433105,
+      "step": 4916
+    },
+    {
+      "epoch": 0.5008631181224252,
+      "grad_norm": 0.12124183773994446,
+      "learning_rate": 0.0008668670438472419,
+      "loss": 2.3058724403381348,
+      "step": 4918
+    },
+    {
+      "epoch": 0.501066803815033,
+      "grad_norm": 0.14865583181381226,
+      "learning_rate": 0.0008665134370579915,
+      "loss": 2.313575267791748,
+      "step": 4920
+    },
+    {
+      "epoch": 0.5012704895076407,
+      "grad_norm": 0.12178020924329758,
+      "learning_rate": 0.0008661598302687412,
+      "loss": 2.2611684799194336,
+      "step": 4922
+    },
+    {
+      "epoch": 0.5014741752002485,
+      "grad_norm": 0.11182554066181183,
+      "learning_rate": 0.0008658062234794908,
+      "loss": 2.2161929607391357,
+      "step": 4924
+    },
+    {
+      "epoch": 0.5016778608928563,
+      "grad_norm": 0.12803375720977783,
+      "learning_rate": 0.0008654526166902405,
+      "loss": 2.2218289375305176,
+      "step": 4926
+    },
+    {
+      "epoch": 0.501881546585464,
+      "grad_norm": 0.12626463174819946,
+      "learning_rate": 0.0008650990099009901,
+      "loss": 2.0726730823516846,
+      "step": 4928
+    },
+    {
+      "epoch": 0.5020852322780717,
+      "grad_norm": 0.12647219002246857,
+      "learning_rate": 0.0008647454031117397,
+      "loss": 2.1301116943359375,
+      "step": 4930
+    },
+    {
+      "epoch": 0.5022889179706794,
+      "grad_norm": 0.14045177400112152,
+      "learning_rate": 0.0008643917963224894,
+      "loss": 2.2914271354675293,
+      "step": 4932
+    },
+    {
+      "epoch": 0.5024926036632872,
+      "grad_norm": 0.12012903392314911,
+      "learning_rate": 0.0008640381895332391,
+      "loss": 2.2886650562286377,
+      "step": 4934
+    },
+    {
+      "epoch": 0.5026962893558949,
+      "grad_norm": 0.14497384428977966,
+      "learning_rate": 0.0008636845827439888,
+      "loss": 2.1270246505737305,
+      "step": 4936
+    },
+    {
+      "epoch": 0.5028999750485027,
+      "grad_norm": 0.14201490581035614,
+      "learning_rate": 0.0008633309759547383,
+      "loss": 2.128908157348633,
+      "step": 4938
+    },
+    {
+      "epoch": 0.5031036607411103,
+      "grad_norm": 0.13806842267513275,
+      "learning_rate": 0.000862977369165488,
+      "loss": 2.186222553253174,
+      "step": 4940
+    },
+    {
+      "epoch": 0.5033073464337181,
+      "grad_norm": 0.19249582290649414,
+      "learning_rate": 0.0008626237623762376,
+      "loss": 2.1915698051452637,
+      "step": 4942
+    },
+    {
+      "epoch": 0.5035110321263259,
+      "grad_norm": 0.11891204863786697,
+      "learning_rate": 0.0008622701555869872,
+      "loss": 2.1132044792175293,
+      "step": 4944
+    },
+    {
+      "epoch": 0.5037147178189336,
+      "grad_norm": 0.13233911991119385,
+      "learning_rate": 0.000861916548797737,
+      "loss": 2.172250270843506,
+      "step": 4946
+    },
+    {
+      "epoch": 0.5039184035115414,
+      "grad_norm": 0.17398637533187866,
+      "learning_rate": 0.0008615629420084866,
+      "loss": 2.2885708808898926,
+      "step": 4948
+    },
+    {
+      "epoch": 0.504122089204149,
+      "grad_norm": 0.14322367310523987,
+      "learning_rate": 0.0008612093352192363,
+      "loss": 2.281339645385742,
+      "step": 4950
+    },
+    {
+      "epoch": 0.5043257748967568,
+      "grad_norm": 0.12107861787080765,
+      "learning_rate": 0.0008608557284299858,
+      "loss": 2.1631810665130615,
+      "step": 4952
+    },
+    {
+      "epoch": 0.5045294605893645,
+      "grad_norm": 0.11637546867132187,
+      "learning_rate": 0.0008605021216407355,
+      "loss": 2.121302604675293,
+      "step": 4954
+    },
+    {
+      "epoch": 0.5047331462819723,
+      "grad_norm": 0.11281871050596237,
+      "learning_rate": 0.0008601485148514852,
+      "loss": 2.25927996635437,
+      "step": 4956
+    },
+    {
+      "epoch": 0.5049368319745801,
+      "grad_norm": 0.14516855776309967,
+      "learning_rate": 0.0008597949080622348,
+      "loss": 2.048182964324951,
+      "step": 4958
+    },
+    {
+      "epoch": 0.5051405176671878,
+      "grad_norm": 0.11057573556900024,
+      "learning_rate": 0.0008594413012729845,
+      "loss": 2.042949676513672,
+      "step": 4960
+    },
+    {
+      "epoch": 0.5053442033597955,
+      "grad_norm": 0.11559516936540604,
+      "learning_rate": 0.0008590876944837341,
+      "loss": 2.138516902923584,
+      "step": 4962
+    },
+    {
+      "epoch": 0.5055478890524032,
+      "grad_norm": 0.12866032123565674,
+      "learning_rate": 0.0008587340876944838,
+      "loss": 2.2007784843444824,
+      "step": 4964
+    },
+    {
+      "epoch": 0.505751574745011,
+      "grad_norm": 0.11582763493061066,
+      "learning_rate": 0.0008583804809052333,
+      "loss": 2.175652027130127,
+      "step": 4966
+    },
+    {
+      "epoch": 0.5059552604376187,
+      "grad_norm": 0.1259339600801468,
+      "learning_rate": 0.0008580268741159831,
+      "loss": 2.2329771518707275,
+      "step": 4968
+    },
+    {
+      "epoch": 0.5061589461302265,
+      "grad_norm": 0.12424679845571518,
+      "learning_rate": 0.0008576732673267327,
+      "loss": 2.2211313247680664,
+      "step": 4970
+    },
+    {
+      "epoch": 0.5063626318228341,
+      "grad_norm": 0.11080215871334076,
+      "learning_rate": 0.0008573196605374823,
+      "loss": 2.210732936859131,
+      "step": 4972
+    },
+    {
+      "epoch": 0.5065663175154419,
+      "grad_norm": 0.10492751002311707,
+      "learning_rate": 0.000856966053748232,
+      "loss": 2.2811591625213623,
+      "step": 4974
+    },
+    {
+      "epoch": 0.5067700032080497,
+      "grad_norm": 0.10982757061719894,
+      "learning_rate": 0.0008566124469589816,
+      "loss": 2.307586193084717,
+      "step": 4976
+    },
+    {
+      "epoch": 0.5069736889006574,
+      "grad_norm": 0.12710316479206085,
+      "learning_rate": 0.0008562588401697314,
+      "loss": 2.119844913482666,
+      "step": 4978
+    },
+    {
+      "epoch": 0.5071773745932652,
+      "grad_norm": 0.10244240611791611,
+      "learning_rate": 0.0008559052333804809,
+      "loss": 2.1466193199157715,
+      "step": 4980
+    },
+    {
+      "epoch": 0.5073810602858728,
+      "grad_norm": 0.12233993411064148,
+      "learning_rate": 0.0008555516265912306,
+      "loss": 2.2796826362609863,
+      "step": 4982
+    },
+    {
+      "epoch": 0.5075847459784806,
+      "grad_norm": 0.12066663801670074,
+      "learning_rate": 0.0008551980198019802,
+      "loss": 2.223788261413574,
+      "step": 4984
+    },
+    {
+      "epoch": 0.5077884316710883,
+      "grad_norm": 0.12710580229759216,
+      "learning_rate": 0.0008548444130127298,
+      "loss": 2.262063980102539,
+      "step": 4986
+    },
+    {
+      "epoch": 0.5079921173636961,
+      "grad_norm": 0.16390135884284973,
+      "learning_rate": 0.0008544908062234795,
+      "loss": 2.243265151977539,
+      "step": 4988
+    },
+    {
+      "epoch": 0.5081958030563039,
+      "grad_norm": 0.11351998150348663,
+      "learning_rate": 0.0008541371994342292,
+      "loss": 2.1079492568969727,
+      "step": 4990
+    },
+    {
+      "epoch": 0.5083994887489116,
+      "grad_norm": 0.14687949419021606,
+      "learning_rate": 0.0008537835926449789,
+      "loss": 2.193711280822754,
+      "step": 4992
+    },
+    {
+      "epoch": 0.5086031744415193,
+      "grad_norm": 0.14203138649463654,
+      "learning_rate": 0.0008534299858557284,
+      "loss": 2.1728384494781494,
+      "step": 4994
+    },
+    {
+      "epoch": 0.508806860134127,
+      "grad_norm": 0.127712219953537,
+      "learning_rate": 0.0008530763790664781,
+      "loss": 2.1585443019866943,
+      "step": 4996
+    },
+    {
+      "epoch": 0.5090105458267348,
+      "grad_norm": 0.21903108060359955,
+      "learning_rate": 0.0008527227722772277,
+      "loss": 2.2555124759674072,
+      "step": 4998
+    },
+    {
+      "epoch": 0.5092142315193425,
+      "grad_norm": 0.13355471193790436,
+      "learning_rate": 0.0008523691654879773,
+      "loss": 2.2137441635131836,
+      "step": 5000
+    },
+    {
+      "epoch": 0.5094179172119503,
+      "grad_norm": 0.12607721984386444,
+      "learning_rate": 0.0008520155586987271,
+      "loss": 2.2624385356903076,
+      "step": 5002
+    },
+    {
+      "epoch": 0.5096216029045579,
+      "grad_norm": 0.12369659543037415,
+      "learning_rate": 0.0008516619519094767,
+      "loss": 2.157174825668335,
+      "step": 5004
+    },
+    {
+      "epoch": 0.5098252885971657,
+      "grad_norm": 0.16258826851844788,
+      "learning_rate": 0.0008513083451202264,
+      "loss": 2.1680660247802734,
+      "step": 5006
+    },
+    {
+      "epoch": 0.5100289742897735,
+      "grad_norm": 0.11050062626600266,
+      "learning_rate": 0.0008509547383309759,
+      "loss": 2.1131086349487305,
+      "step": 5008
+    },
+    {
+      "epoch": 0.5102326599823812,
+      "grad_norm": 0.13122889399528503,
+      "learning_rate": 0.0008506011315417256,
+      "loss": 2.170982599258423,
+      "step": 5010
+    },
+    {
+      "epoch": 0.510436345674989,
+      "grad_norm": 0.10916507244110107,
+      "learning_rate": 0.0008502475247524752,
+      "loss": 2.1027419567108154,
+      "step": 5012
+    },
+    {
+      "epoch": 0.5106400313675966,
+      "grad_norm": 0.13671652972698212,
+      "learning_rate": 0.0008498939179632249,
+      "loss": 2.1125004291534424,
+      "step": 5014
+    },
+    {
+      "epoch": 0.5108437170602044,
+      "grad_norm": 0.12384458631277084,
+      "learning_rate": 0.0008495403111739746,
+      "loss": 2.2215585708618164,
+      "step": 5016
+    },
+    {
+      "epoch": 0.5110474027528121,
+      "grad_norm": 0.12740764021873474,
+      "learning_rate": 0.0008491867043847242,
+      "loss": 2.3330631256103516,
+      "step": 5018
+    },
+    {
+      "epoch": 0.5112510884454199,
+      "grad_norm": 0.11171647161245346,
+      "learning_rate": 0.0008488330975954739,
+      "loss": 2.1949644088745117,
+      "step": 5020
+    },
+    {
+      "epoch": 0.5114547741380276,
+      "grad_norm": 0.12620732188224792,
+      "learning_rate": 0.0008484794908062234,
+      "loss": 2.1888999938964844,
+      "step": 5022
+    },
+    {
+      "epoch": 0.5116584598306353,
+      "grad_norm": 0.11070707440376282,
+      "learning_rate": 0.0008481258840169732,
+      "loss": 2.074064254760742,
+      "step": 5024
+    },
+    {
+      "epoch": 0.511862145523243,
+      "grad_norm": 0.1060396358370781,
+      "learning_rate": 0.0008477722772277228,
+      "loss": 2.1421425342559814,
+      "step": 5026
+    },
+    {
+      "epoch": 0.5120658312158508,
+      "grad_norm": 0.17912282049655914,
+      "learning_rate": 0.0008474186704384724,
+      "loss": 2.257978916168213,
+      "step": 5028
+    },
+    {
+      "epoch": 0.5122695169084586,
+      "grad_norm": 0.1068357452750206,
+      "learning_rate": 0.0008470650636492221,
+      "loss": 2.097294330596924,
+      "step": 5030
+    },
+    {
+      "epoch": 0.5124732026010663,
+      "grad_norm": 0.15793606638908386,
+      "learning_rate": 0.0008467114568599717,
+      "loss": 2.034804344177246,
+      "step": 5032
+    },
+    {
+      "epoch": 0.5126768882936741,
+      "grad_norm": 0.1358993947505951,
+      "learning_rate": 0.0008463578500707214,
+      "loss": 2.298523187637329,
+      "step": 5034
+    },
+    {
+      "epoch": 0.5128805739862817,
+      "grad_norm": 0.10322975367307663,
+      "learning_rate": 0.0008460042432814711,
+      "loss": 2.1065778732299805,
+      "step": 5036
+    },
+    {
+      "epoch": 0.5130842596788895,
+      "grad_norm": 0.1718066930770874,
+      "learning_rate": 0.0008456506364922207,
+      "loss": 2.2068498134613037,
+      "step": 5038
+    },
+    {
+      "epoch": 0.5132879453714972,
+      "grad_norm": 0.1205066442489624,
+      "learning_rate": 0.0008452970297029703,
+      "loss": 2.112915515899658,
+      "step": 5040
+    },
+    {
+      "epoch": 0.513491631064105,
+      "grad_norm": 0.1057831197977066,
+      "learning_rate": 0.0008449434229137199,
+      "loss": 2.143975019454956,
+      "step": 5042
+    },
+    {
+      "epoch": 0.5136953167567128,
+      "grad_norm": 0.12325635552406311,
+      "learning_rate": 0.0008445898161244696,
+      "loss": 2.188964366912842,
+      "step": 5044
+    },
+    {
+      "epoch": 0.5138990024493204,
+      "grad_norm": 0.10831008106470108,
+      "learning_rate": 0.0008442362093352192,
+      "loss": 2.17036771774292,
+      "step": 5046
+    },
+    {
+      "epoch": 0.5141026881419282,
+      "grad_norm": 0.11841947585344315,
+      "learning_rate": 0.000843882602545969,
+      "loss": 2.1844377517700195,
+      "step": 5048
+    },
+    {
+      "epoch": 0.5143063738345359,
+      "grad_norm": 0.11877504736185074,
+      "learning_rate": 0.0008435289957567186,
+      "loss": 2.138848304748535,
+      "step": 5050
+    },
+    {
+      "epoch": 0.5145100595271437,
+      "grad_norm": 0.13538970053195953,
+      "learning_rate": 0.0008431753889674682,
+      "loss": 2.0996203422546387,
+      "step": 5052
+    },
+    {
+      "epoch": 0.5147137452197514,
+      "grad_norm": 0.10899586975574493,
+      "learning_rate": 0.0008428217821782178,
+      "loss": 2.1536927223205566,
+      "step": 5054
+    },
+    {
+      "epoch": 0.5149174309123591,
+      "grad_norm": 0.10650411993265152,
+      "learning_rate": 0.0008424681753889674,
+      "loss": 2.200711250305176,
+      "step": 5056
+    },
+    {
+      "epoch": 0.5151211166049668,
+      "grad_norm": 0.11705128103494644,
+      "learning_rate": 0.0008421145685997172,
+      "loss": 2.1684212684631348,
+      "step": 5058
+    },
+    {
+      "epoch": 0.5153248022975746,
+      "grad_norm": 0.1113666370511055,
+      "learning_rate": 0.0008417609618104668,
+      "loss": 2.203496217727661,
+      "step": 5060
+    },
+    {
+      "epoch": 0.5155284879901824,
+      "grad_norm": 0.1223960593342781,
+      "learning_rate": 0.0008414073550212165,
+      "loss": 2.1488654613494873,
+      "step": 5062
+    },
+    {
+      "epoch": 0.5157321736827901,
+      "grad_norm": 0.1194973811507225,
+      "learning_rate": 0.0008410537482319661,
+      "loss": 2.161210536956787,
+      "step": 5064
+    },
+    {
+      "epoch": 0.5159358593753979,
+      "grad_norm": 0.10832330584526062,
+      "learning_rate": 0.0008407001414427157,
+      "loss": 2.2489004135131836,
+      "step": 5066
+    },
+    {
+      "epoch": 0.5161395450680055,
+      "grad_norm": 0.10324008017778397,
+      "learning_rate": 0.0008403465346534653,
+      "loss": 2.126166343688965,
+      "step": 5068
+    },
+    {
+      "epoch": 0.5163432307606133,
+      "grad_norm": 0.16477029025554657,
+      "learning_rate": 0.000839992927864215,
+      "loss": 2.310744285583496,
+      "step": 5070
+    },
+    {
+      "epoch": 0.516546916453221,
+      "grad_norm": 0.1232154369354248,
+      "learning_rate": 0.0008396393210749647,
+      "loss": 2.126646041870117,
+      "step": 5072
+    },
+    {
+      "epoch": 0.5167506021458288,
+      "grad_norm": 0.12828287482261658,
+      "learning_rate": 0.0008392857142857143,
+      "loss": 2.174060821533203,
+      "step": 5074
+    },
+    {
+      "epoch": 0.5169542878384366,
+      "grad_norm": 0.18438594043254852,
+      "learning_rate": 0.000838932107496464,
+      "loss": 2.2895898818969727,
+      "step": 5076
+    },
+    {
+      "epoch": 0.5171579735310442,
+      "grad_norm": 0.12678952515125275,
+      "learning_rate": 0.0008385785007072136,
+      "loss": 2.2002785205841064,
+      "step": 5078
+    },
+    {
+      "epoch": 0.517361659223652,
+      "grad_norm": 0.11629480868577957,
+      "learning_rate": 0.0008382248939179632,
+      "loss": 2.1650257110595703,
+      "step": 5080
+    },
+    {
+      "epoch": 0.5175653449162597,
+      "grad_norm": 0.14037558436393738,
+      "learning_rate": 0.0008378712871287129,
+      "loss": 2.22664737701416,
+      "step": 5082
+    },
+    {
+      "epoch": 0.5177690306088675,
+      "grad_norm": 0.18306361138820648,
+      "learning_rate": 0.0008375176803394625,
+      "loss": 2.2177486419677734,
+      "step": 5084
+    },
+    {
+      "epoch": 0.5179727163014752,
+      "grad_norm": 0.11023323982954025,
+      "learning_rate": 0.0008371640735502122,
+      "loss": 2.1271634101867676,
+      "step": 5086
+    },
+    {
+      "epoch": 0.5181764019940829,
+      "grad_norm": 0.14761903882026672,
+      "learning_rate": 0.0008368104667609618,
+      "loss": 2.2252233028411865,
+      "step": 5088
+    },
+    {
+      "epoch": 0.5183800876866906,
+      "grad_norm": 0.10682391375303268,
+      "learning_rate": 0.0008364568599717115,
+      "loss": 2.1482062339782715,
+      "step": 5090
+    },
+    {
+      "epoch": 0.5185837733792984,
+      "grad_norm": 0.12667791545391083,
+      "learning_rate": 0.0008361032531824611,
+      "loss": 2.166778326034546,
+      "step": 5092
+    },
+    {
+      "epoch": 0.5187874590719062,
+      "grad_norm": 0.12551379203796387,
+      "learning_rate": 0.0008357496463932108,
+      "loss": 2.1661009788513184,
+      "step": 5094
+    },
+    {
+      "epoch": 0.5189911447645139,
+      "grad_norm": 0.12127218395471573,
+      "learning_rate": 0.0008353960396039604,
+      "loss": 2.339672327041626,
+      "step": 5096
+    },
+    {
+      "epoch": 0.5191948304571217,
+      "grad_norm": 0.1296466886997223,
+      "learning_rate": 0.00083504243281471,
+      "loss": 2.3050570487976074,
+      "step": 5098
+    },
+    {
+      "epoch": 0.5193985161497293,
+      "grad_norm": 0.2258855104446411,
+      "learning_rate": 0.0008346888260254597,
+      "loss": 2.049459934234619,
+      "step": 5100
+    },
+    {
+      "epoch": 0.5196022018423371,
+      "grad_norm": 0.12435401231050491,
+      "learning_rate": 0.0008343352192362093,
+      "loss": 2.1512506008148193,
+      "step": 5102
+    },
+    {
+      "epoch": 0.5198058875349448,
+      "grad_norm": 0.14348949491977692,
+      "learning_rate": 0.0008339816124469591,
+      "loss": 2.1663951873779297,
+      "step": 5104
+    },
+    {
+      "epoch": 0.5200095732275526,
+      "grad_norm": 0.11625627428293228,
+      "learning_rate": 0.0008336280056577087,
+      "loss": 2.174859046936035,
+      "step": 5106
+    },
+    {
+      "epoch": 0.5202132589201603,
+      "grad_norm": 0.1265910118818283,
+      "learning_rate": 0.0008332743988684583,
+      "loss": 2.3072218894958496,
+      "step": 5108
+    },
+    {
+      "epoch": 0.520416944612768,
+      "grad_norm": 0.13347850739955902,
+      "learning_rate": 0.0008329207920792079,
+      "loss": 2.4160280227661133,
+      "step": 5110
+    },
+    {
+      "epoch": 0.5206206303053758,
+      "grad_norm": 0.12800730764865875,
+      "learning_rate": 0.0008325671852899575,
+      "loss": 2.0977985858917236,
+      "step": 5112
+    },
+    {
+      "epoch": 0.5208243159979835,
+      "grad_norm": 0.12365824729204178,
+      "learning_rate": 0.0008322135785007072,
+      "loss": 2.1059398651123047,
+      "step": 5114
+    },
+    {
+      "epoch": 0.5210280016905913,
+      "grad_norm": 0.16394305229187012,
+      "learning_rate": 0.0008318599717114569,
+      "loss": 2.170620918273926,
+      "step": 5116
+    },
+    {
+      "epoch": 0.521231687383199,
+      "grad_norm": 0.11819277703762054,
+      "learning_rate": 0.0008315063649222066,
+      "loss": 2.06512451171875,
+      "step": 5118
+    },
+    {
+      "epoch": 0.5214353730758067,
+      "grad_norm": 0.11292362958192825,
+      "learning_rate": 0.0008311527581329562,
+      "loss": 2.1826839447021484,
+      "step": 5120
+    },
+    {
+      "epoch": 0.5216390587684144,
+      "grad_norm": 0.14442545175552368,
+      "learning_rate": 0.0008307991513437058,
+      "loss": 2.203705072402954,
+      "step": 5122
+    },
+    {
+      "epoch": 0.5218427444610222,
+      "grad_norm": 0.14532631635665894,
+      "learning_rate": 0.0008304455445544554,
+      "loss": 2.099902391433716,
+      "step": 5124
+    },
+    {
+      "epoch": 0.52204643015363,
+      "grad_norm": 0.10644169896841049,
+      "learning_rate": 0.000830091937765205,
+      "loss": 2.2501120567321777,
+      "step": 5126
+    },
+    {
+      "epoch": 0.5222501158462377,
+      "grad_norm": 0.12702259421348572,
+      "learning_rate": 0.0008297383309759548,
+      "loss": 2.18904185295105,
+      "step": 5128
+    },
+    {
+      "epoch": 0.5224538015388454,
+      "grad_norm": 0.1601700633764267,
+      "learning_rate": 0.0008293847241867044,
+      "loss": 2.219494104385376,
+      "step": 5130
+    },
+    {
+      "epoch": 0.5226574872314531,
+      "grad_norm": 0.10143869370222092,
+      "learning_rate": 0.0008290311173974541,
+      "loss": 2.105084180831909,
+      "step": 5132
+    },
+    {
+      "epoch": 0.5228611729240609,
+      "grad_norm": 0.13775479793548584,
+      "learning_rate": 0.0008286775106082037,
+      "loss": 2.0944643020629883,
+      "step": 5134
+    },
+    {
+      "epoch": 0.5230648586166686,
+      "grad_norm": 0.10659192502498627,
+      "learning_rate": 0.0008283239038189534,
+      "loss": 2.1481099128723145,
+      "step": 5136
+    },
+    {
+      "epoch": 0.5232685443092764,
+      "grad_norm": 0.16377289593219757,
+      "learning_rate": 0.000827970297029703,
+      "loss": 2.216259717941284,
+      "step": 5138
+    },
+    {
+      "epoch": 0.5234722300018841,
+      "grad_norm": 0.1260034143924713,
+      "learning_rate": 0.0008276166902404526,
+      "loss": 2.189362049102783,
+      "step": 5140
+    },
+    {
+      "epoch": 0.5236759156944918,
+      "grad_norm": 0.12827739119529724,
+      "learning_rate": 0.0008272630834512023,
+      "loss": 2.1100661754608154,
+      "step": 5142
+    },
+    {
+      "epoch": 0.5238796013870995,
+      "grad_norm": 0.1254393309354782,
+      "learning_rate": 0.0008269094766619519,
+      "loss": 2.098095417022705,
+      "step": 5144
+    },
+    {
+      "epoch": 0.5240832870797073,
+      "grad_norm": 0.11370775103569031,
+      "learning_rate": 0.0008265558698727016,
+      "loss": 2.1878561973571777,
+      "step": 5146
+    },
+    {
+      "epoch": 0.5242869727723151,
+      "grad_norm": 0.10757619142532349,
+      "learning_rate": 0.0008262022630834512,
+      "loss": 2.230466365814209,
+      "step": 5148
+    },
+    {
+      "epoch": 0.5244906584649228,
+      "grad_norm": 0.11732494831085205,
+      "learning_rate": 0.000825848656294201,
+      "loss": 2.2152819633483887,
+      "step": 5150
+    },
+    {
+      "epoch": 0.5246943441575305,
+      "grad_norm": 0.1259903460741043,
+      "learning_rate": 0.0008254950495049505,
+      "loss": 2.190828323364258,
+      "step": 5152
+    },
+    {
+      "epoch": 0.5248980298501382,
+      "grad_norm": 0.12724237143993378,
+      "learning_rate": 0.0008251414427157001,
+      "loss": 2.2166922092437744,
+      "step": 5154
+    },
+    {
+      "epoch": 0.525101715542746,
+      "grad_norm": 0.13432280719280243,
+      "learning_rate": 0.0008247878359264498,
+      "loss": 2.0902011394500732,
+      "step": 5156
+    },
+    {
+      "epoch": 0.5253054012353537,
+      "grad_norm": 0.11277803778648376,
+      "learning_rate": 0.0008244342291371994,
+      "loss": 2.297497272491455,
+      "step": 5158
+    },
+    {
+      "epoch": 0.5255090869279615,
+      "grad_norm": 0.11834308505058289,
+      "learning_rate": 0.0008240806223479491,
+      "loss": 2.150355100631714,
+      "step": 5160
+    },
+    {
+      "epoch": 0.5257127726205691,
+      "grad_norm": 0.1385759860277176,
+      "learning_rate": 0.0008237270155586988,
+      "loss": 2.320197105407715,
+      "step": 5162
+    },
+    {
+      "epoch": 0.5259164583131769,
+      "grad_norm": 0.13366083800792694,
+      "learning_rate": 0.0008233734087694485,
+      "loss": 2.198103427886963,
+      "step": 5164
+    },
+    {
+      "epoch": 0.5261201440057847,
+      "grad_norm": 0.11068776994943619,
+      "learning_rate": 0.000823019801980198,
+      "loss": 2.149693489074707,
+      "step": 5166
+    },
+    {
+      "epoch": 0.5263238296983924,
+      "grad_norm": 0.09877748787403107,
+      "learning_rate": 0.0008226661951909476,
+      "loss": 2.2081663608551025,
+      "step": 5168
+    },
+    {
+      "epoch": 0.5265275153910002,
+      "grad_norm": 0.20159295201301575,
+      "learning_rate": 0.0008223125884016973,
+      "loss": 2.3439087867736816,
+      "step": 5170
+    },
+    {
+      "epoch": 0.5267312010836079,
+      "grad_norm": 0.11299239844083786,
+      "learning_rate": 0.0008219589816124469,
+      "loss": 2.18491268157959,
+      "step": 5172
+    },
+    {
+      "epoch": 0.5269348867762156,
+      "grad_norm": 0.16257445514202118,
+      "learning_rate": 0.0008216053748231967,
+      "loss": 2.2650375366210938,
+      "step": 5174
+    },
+    {
+      "epoch": 0.5271385724688233,
+      "grad_norm": 0.13896779716014862,
+      "learning_rate": 0.0008212517680339463,
+      "loss": 2.1850805282592773,
+      "step": 5176
+    },
+    {
+      "epoch": 0.5273422581614311,
+      "grad_norm": 0.1404113918542862,
+      "learning_rate": 0.000820898161244696,
+      "loss": 2.196833610534668,
+      "step": 5178
+    },
+    {
+      "epoch": 0.5275459438540389,
+      "grad_norm": 0.14703549444675446,
+      "learning_rate": 0.0008205445544554455,
+      "loss": 2.084629774093628,
+      "step": 5180
+    },
+    {
+      "epoch": 0.5277496295466466,
+      "grad_norm": 0.11251578480005264,
+      "learning_rate": 0.0008201909476661951,
+      "loss": 2.320702075958252,
+      "step": 5182
+    },
+    {
+      "epoch": 0.5279533152392543,
+      "grad_norm": 0.11673443019390106,
+      "learning_rate": 0.0008198373408769449,
+      "loss": 2.2357163429260254,
+      "step": 5184
+    },
+    {
+      "epoch": 0.528157000931862,
+      "grad_norm": 0.11428599059581757,
+      "learning_rate": 0.0008194837340876945,
+      "loss": 2.124011516571045,
+      "step": 5186
+    },
+    {
+      "epoch": 0.5283606866244698,
+      "grad_norm": 0.11357028037309647,
+      "learning_rate": 0.0008191301272984442,
+      "loss": 2.154174566268921,
+      "step": 5188
+    },
+    {
+      "epoch": 0.5285643723170775,
+      "grad_norm": 0.12181391566991806,
+      "learning_rate": 0.0008187765205091938,
+      "loss": 2.1929473876953125,
+      "step": 5190
+    },
+    {
+      "epoch": 0.5287680580096853,
+      "grad_norm": 0.13221541047096252,
+      "learning_rate": 0.0008184229137199435,
+      "loss": 2.2528162002563477,
+      "step": 5192
+    },
+    {
+      "epoch": 0.5289717437022929,
+      "grad_norm": 0.12194789946079254,
+      "learning_rate": 0.000818069306930693,
+      "loss": 2.2212376594543457,
+      "step": 5194
+    },
+    {
+      "epoch": 0.5291754293949007,
+      "grad_norm": 0.11862846463918686,
+      "learning_rate": 0.0008177157001414427,
+      "loss": 2.129556655883789,
+      "step": 5196
+    },
+    {
+      "epoch": 0.5293791150875085,
+      "grad_norm": 0.13440634310245514,
+      "learning_rate": 0.0008173620933521924,
+      "loss": 2.105417490005493,
+      "step": 5198
+    },
+    {
+      "epoch": 0.5295828007801162,
+      "grad_norm": 0.12092459946870804,
+      "learning_rate": 0.000817008486562942,
+      "loss": 2.2677931785583496,
+      "step": 5200
+    },
+    {
+      "epoch": 0.529786486472724,
+      "grad_norm": 0.1394500583410263,
+      "learning_rate": 0.0008166548797736917,
+      "loss": 2.260242223739624,
+      "step": 5202
+    },
+    {
+      "epoch": 0.5299901721653317,
+      "grad_norm": 0.17945902049541473,
+      "learning_rate": 0.0008163012729844413,
+      "loss": 2.3567299842834473,
+      "step": 5204
+    },
+    {
+      "epoch": 0.5301938578579394,
+      "grad_norm": 0.13393515348434448,
+      "learning_rate": 0.000815947666195191,
+      "loss": 2.176961898803711,
+      "step": 5206
+    },
+    {
+      "epoch": 0.5303975435505471,
+      "grad_norm": 0.12032050639390945,
+      "learning_rate": 0.0008155940594059406,
+      "loss": 2.227409601211548,
+      "step": 5208
+    },
+    {
+      "epoch": 0.5306012292431549,
+      "grad_norm": 0.10939647257328033,
+      "learning_rate": 0.0008152404526166902,
+      "loss": 2.284618854522705,
+      "step": 5210
+    },
+    {
+      "epoch": 0.5308049149357627,
+      "grad_norm": 0.16582220792770386,
+      "learning_rate": 0.0008148868458274399,
+      "loss": 2.064558506011963,
+      "step": 5212
+    },
+    {
+      "epoch": 0.5310086006283704,
+      "grad_norm": 0.10561855137348175,
+      "learning_rate": 0.0008145332390381895,
+      "loss": 2.1174240112304688,
+      "step": 5214
+    },
+    {
+      "epoch": 0.531212286320978,
+      "grad_norm": 0.1343773454427719,
+      "learning_rate": 0.0008141796322489392,
+      "loss": 2.2669007778167725,
+      "step": 5216
+    },
+    {
+      "epoch": 0.5314159720135858,
+      "grad_norm": 0.11250844597816467,
+      "learning_rate": 0.0008138260254596889,
+      "loss": 2.1945903301239014,
+      "step": 5218
+    },
+    {
+      "epoch": 0.5316196577061936,
+      "grad_norm": 0.1587960124015808,
+      "learning_rate": 0.0008134724186704386,
+      "loss": 2.0644850730895996,
+      "step": 5220
+    },
+    {
+      "epoch": 0.5318233433988013,
+      "grad_norm": 0.16016189754009247,
+      "learning_rate": 0.0008131188118811881,
+      "loss": 2.2601006031036377,
+      "step": 5222
+    },
+    {
+      "epoch": 0.5320270290914091,
+      "grad_norm": 0.18519634008407593,
+      "learning_rate": 0.0008127652050919377,
+      "loss": 2.1467206478118896,
+      "step": 5224
+    },
+    {
+      "epoch": 0.5322307147840167,
+      "grad_norm": 0.13050612807273865,
+      "learning_rate": 0.0008124115983026874,
+      "loss": 2.028193473815918,
+      "step": 5226
+    },
+    {
+      "epoch": 0.5324344004766245,
+      "grad_norm": 0.11968324333429337,
+      "learning_rate": 0.000812057991513437,
+      "loss": 2.2259373664855957,
+      "step": 5228
+    },
+    {
+      "epoch": 0.5326380861692322,
+      "grad_norm": 0.14200636744499207,
+      "learning_rate": 0.0008117043847241868,
+      "loss": 2.2132818698883057,
+      "step": 5230
+    },
+    {
+      "epoch": 0.53284177186184,
+      "grad_norm": 0.11914645880460739,
+      "learning_rate": 0.0008113507779349364,
+      "loss": 2.091172456741333,
+      "step": 5232
+    },
+    {
+      "epoch": 0.5330454575544478,
+      "grad_norm": 0.13462969660758972,
+      "learning_rate": 0.0008109971711456861,
+      "loss": 2.2007384300231934,
+      "step": 5234
+    },
+    {
+      "epoch": 0.5332491432470555,
+      "grad_norm": 0.11606946587562561,
+      "learning_rate": 0.0008106435643564357,
+      "loss": 2.2109384536743164,
+      "step": 5236
+    },
+    {
+      "epoch": 0.5334528289396632,
+      "grad_norm": 0.13977740705013275,
+      "learning_rate": 0.0008102899575671852,
+      "loss": 2.2918996810913086,
+      "step": 5238
+    },
+    {
+      "epoch": 0.5336565146322709,
+      "grad_norm": 0.11626478284597397,
+      "learning_rate": 0.0008099363507779349,
+      "loss": 2.0695905685424805,
+      "step": 5240
+    },
+    {
+      "epoch": 0.5338602003248787,
+      "grad_norm": 0.11896582692861557,
+      "learning_rate": 0.0008095827439886846,
+      "loss": 2.181711196899414,
+      "step": 5242
+    },
+    {
+      "epoch": 0.5340638860174864,
+      "grad_norm": 0.14181528985500336,
+      "learning_rate": 0.0008092291371994343,
+      "loss": 2.275689125061035,
+      "step": 5244
+    },
+    {
+      "epoch": 0.5342675717100942,
+      "grad_norm": 0.12781667709350586,
+      "learning_rate": 0.0008088755304101839,
+      "loss": 2.172219753265381,
+      "step": 5246
+    },
+    {
+      "epoch": 0.5344712574027018,
+      "grad_norm": 0.11594336479902267,
+      "learning_rate": 0.0008085219236209336,
+      "loss": 2.1980910301208496,
+      "step": 5248
+    },
+    {
+      "epoch": 0.5346749430953096,
+      "grad_norm": 0.13171595335006714,
+      "learning_rate": 0.0008081683168316832,
+      "loss": 2.2718465328216553,
+      "step": 5250
+    },
+    {
+      "epoch": 0.5348786287879174,
+      "grad_norm": 0.13006249070167542,
+      "learning_rate": 0.0008078147100424327,
+      "loss": 2.0673365592956543,
+      "step": 5252
+    },
+    {
+      "epoch": 0.5350823144805251,
+      "grad_norm": 0.11449848115444183,
+      "learning_rate": 0.0008074611032531825,
+      "loss": 2.250624179840088,
+      "step": 5254
+    },
+    {
+      "epoch": 0.5352860001731329,
+      "grad_norm": 0.14292436838150024,
+      "learning_rate": 0.0008071074964639321,
+      "loss": 2.206151008605957,
+      "step": 5256
+    },
+    {
+      "epoch": 0.5354896858657405,
+      "grad_norm": 0.14645226299762726,
+      "learning_rate": 0.0008067538896746818,
+      "loss": 2.178520679473877,
+      "step": 5258
+    },
+    {
+      "epoch": 0.5356933715583483,
+      "grad_norm": 0.1323077529668808,
+      "learning_rate": 0.0008064002828854314,
+      "loss": 2.115074872970581,
+      "step": 5260
+    },
+    {
+      "epoch": 0.535897057250956,
+      "grad_norm": 0.17293553054332733,
+      "learning_rate": 0.0008060466760961811,
+      "loss": 2.1672232151031494,
+      "step": 5262
+    },
+    {
+      "epoch": 0.5361007429435638,
+      "grad_norm": 0.11623018980026245,
+      "learning_rate": 0.0008056930693069308,
+      "loss": 2.128838062286377,
+      "step": 5264
+    },
+    {
+      "epoch": 0.5363044286361716,
+      "grad_norm": 0.13231678307056427,
+      "learning_rate": 0.0008053394625176803,
+      "loss": 2.2204246520996094,
+      "step": 5266
+    },
+    {
+      "epoch": 0.5365081143287792,
+      "grad_norm": 0.14964033663272858,
+      "learning_rate": 0.00080498585572843,
+      "loss": 2.2563235759735107,
+      "step": 5268
+    },
+    {
+      "epoch": 0.536711800021387,
+      "grad_norm": 0.1569688767194748,
+      "learning_rate": 0.0008046322489391796,
+      "loss": 2.061260461807251,
+      "step": 5270
+    },
+    {
+      "epoch": 0.5369154857139947,
+      "grad_norm": 0.1322789490222931,
+      "learning_rate": 0.0008042786421499293,
+      "loss": 1.9513612985610962,
+      "step": 5272
+    },
+    {
+      "epoch": 0.5371191714066025,
+      "grad_norm": 0.13683097064495087,
+      "learning_rate": 0.0008039250353606789,
+      "loss": 2.367429256439209,
+      "step": 5274
+    },
+    {
+      "epoch": 0.5373228570992102,
+      "grad_norm": 0.13814878463745117,
+      "learning_rate": 0.0008035714285714287,
+      "loss": 2.116466999053955,
+      "step": 5276
+    },
+    {
+      "epoch": 0.537526542791818,
+      "grad_norm": 0.17293033003807068,
+      "learning_rate": 0.0008032178217821783,
+      "loss": 2.247734546661377,
+      "step": 5278
+    },
+    {
+      "epoch": 0.5377302284844256,
+      "grad_norm": 0.13070423901081085,
+      "learning_rate": 0.0008028642149929278,
+      "loss": 2.2992098331451416,
+      "step": 5280
+    },
+    {
+      "epoch": 0.5379339141770334,
+      "grad_norm": 0.12358853220939636,
+      "learning_rate": 0.0008025106082036775,
+      "loss": 2.264075756072998,
+      "step": 5282
+    },
+    {
+      "epoch": 0.5381375998696412,
+      "grad_norm": 0.1677423119544983,
+      "learning_rate": 0.0008021570014144271,
+      "loss": 2.1622865200042725,
+      "step": 5284
+    },
+    {
+      "epoch": 0.5383412855622489,
+      "grad_norm": 0.12399329990148544,
+      "learning_rate": 0.0008018033946251768,
+      "loss": 2.237581968307495,
+      "step": 5286
+    },
+    {
+      "epoch": 0.5385449712548567,
+      "grad_norm": 0.11848261207342148,
+      "learning_rate": 0.0008014497878359265,
+      "loss": 2.143383026123047,
+      "step": 5288
+    },
+    {
+      "epoch": 0.5387486569474643,
+      "grad_norm": 0.13752037286758423,
+      "learning_rate": 0.0008010961810466762,
+      "loss": 2.315373182296753,
+      "step": 5290
+    },
+    {
+      "epoch": 0.5389523426400721,
+      "grad_norm": 0.11655480414628983,
+      "learning_rate": 0.0008007425742574258,
+      "loss": 2.3120508193969727,
+      "step": 5292
+    },
+    {
+      "epoch": 0.5391560283326798,
+      "grad_norm": 0.10640902817249298,
+      "learning_rate": 0.0008003889674681753,
+      "loss": 2.2024996280670166,
+      "step": 5294
+    },
+    {
+      "epoch": 0.5393597140252876,
+      "grad_norm": 0.12252594530582428,
+      "learning_rate": 0.000800035360678925,
+      "loss": 2.2933223247528076,
+      "step": 5296
+    },
+    {
+      "epoch": 0.5395633997178954,
+      "grad_norm": 0.14120176434516907,
+      "learning_rate": 0.0007996817538896746,
+      "loss": 2.2180628776550293,
+      "step": 5298
+    },
+    {
+      "epoch": 0.539767085410503,
+      "grad_norm": 0.141900897026062,
+      "learning_rate": 0.0007993281471004244,
+      "loss": 2.281520366668701,
+      "step": 5300
+    },
+    {
+      "epoch": 0.5399707711031108,
+      "grad_norm": 0.11652051657438278,
+      "learning_rate": 0.000798974540311174,
+      "loss": 2.3110671043395996,
+      "step": 5302
+    },
+    {
+      "epoch": 0.5401744567957185,
+      "grad_norm": 0.1494811475276947,
+      "learning_rate": 0.0007986209335219237,
+      "loss": 2.1971747875213623,
+      "step": 5304
+    },
+    {
+      "epoch": 0.5403781424883263,
+      "grad_norm": 0.18974202871322632,
+      "learning_rate": 0.0007982673267326733,
+      "loss": 2.139044761657715,
+      "step": 5306
+    },
+    {
+      "epoch": 0.540581828180934,
+      "grad_norm": 0.12465883791446686,
+      "learning_rate": 0.0007979137199434228,
+      "loss": 2.184131622314453,
+      "step": 5308
+    },
+    {
+      "epoch": 0.5407855138735418,
+      "grad_norm": 0.11915626376867294,
+      "learning_rate": 0.0007975601131541726,
+      "loss": 2.209097146987915,
+      "step": 5310
+    },
+    {
+      "epoch": 0.5409891995661494,
+      "grad_norm": 0.11856343597173691,
+      "learning_rate": 0.0007972065063649222,
+      "loss": 2.2876620292663574,
+      "step": 5312
+    },
+    {
+      "epoch": 0.5411928852587572,
+      "grad_norm": 0.1093050092458725,
+      "learning_rate": 0.0007968528995756719,
+      "loss": 2.231363296508789,
+      "step": 5314
+    },
+    {
+      "epoch": 0.541396570951365,
+      "grad_norm": 0.12352319806814194,
+      "learning_rate": 0.0007964992927864215,
+      "loss": 2.0712504386901855,
+      "step": 5316
+    },
+    {
+      "epoch": 0.5416002566439727,
+      "grad_norm": 0.1495259702205658,
+      "learning_rate": 0.0007961456859971712,
+      "loss": 2.1918773651123047,
+      "step": 5318
+    },
+    {
+      "epoch": 0.5418039423365805,
+      "grad_norm": 0.12062849849462509,
+      "learning_rate": 0.0007957920792079208,
+      "loss": 2.303311824798584,
+      "step": 5320
+    },
+    {
+      "epoch": 0.5420076280291881,
+      "grad_norm": 0.10673106461763382,
+      "learning_rate": 0.0007954384724186704,
+      "loss": 2.0955119132995605,
+      "step": 5322
+    },
+    {
+      "epoch": 0.5422113137217959,
+      "grad_norm": 0.12796102464199066,
+      "learning_rate": 0.0007950848656294201,
+      "loss": 2.165935754776001,
+      "step": 5324
+    },
+    {
+      "epoch": 0.5424149994144036,
+      "grad_norm": 0.12113739550113678,
+      "learning_rate": 0.0007947312588401697,
+      "loss": 2.181358575820923,
+      "step": 5326
+    },
+    {
+      "epoch": 0.5426186851070114,
+      "grad_norm": 0.1037791296839714,
+      "learning_rate": 0.0007943776520509194,
+      "loss": 2.037444591522217,
+      "step": 5328
+    },
+    {
+      "epoch": 0.5428223707996191,
+      "grad_norm": 0.13072717189788818,
+      "learning_rate": 0.000794024045261669,
+      "loss": 2.267014265060425,
+      "step": 5330
+    },
+    {
+      "epoch": 0.5430260564922268,
+      "grad_norm": 0.12374146282672882,
+      "learning_rate": 0.0007936704384724188,
+      "loss": 2.179870128631592,
+      "step": 5332
+    },
+    {
+      "epoch": 0.5432297421848346,
+      "grad_norm": 0.14277249574661255,
+      "learning_rate": 0.0007933168316831684,
+      "loss": 2.101255416870117,
+      "step": 5334
+    },
+    {
+      "epoch": 0.5434334278774423,
+      "grad_norm": 0.12442793697118759,
+      "learning_rate": 0.000792963224893918,
+      "loss": 2.268251657485962,
+      "step": 5336
+    },
+    {
+      "epoch": 0.5436371135700501,
+      "grad_norm": 0.12436573952436447,
+      "learning_rate": 0.0007926096181046676,
+      "loss": 2.090402126312256,
+      "step": 5338
+    },
+    {
+      "epoch": 0.5438407992626578,
+      "grad_norm": 0.1925506591796875,
+      "learning_rate": 0.0007922560113154172,
+      "loss": 2.272948741912842,
+      "step": 5340
+    },
+    {
+      "epoch": 0.5440444849552656,
+      "grad_norm": 0.10873495042324066,
+      "learning_rate": 0.0007919024045261669,
+      "loss": 2.1838059425354004,
+      "step": 5342
+    },
+    {
+      "epoch": 0.5442481706478732,
+      "grad_norm": 0.10734472423791885,
+      "learning_rate": 0.0007915487977369166,
+      "loss": 2.1729161739349365,
+      "step": 5344
+    },
+    {
+      "epoch": 0.544451856340481,
+      "grad_norm": 0.11548444628715515,
+      "learning_rate": 0.0007911951909476663,
+      "loss": 2.2454967498779297,
+      "step": 5346
+    },
+    {
+      "epoch": 0.5446555420330887,
+      "grad_norm": 0.10911649465560913,
+      "learning_rate": 0.0007908415841584159,
+      "loss": 2.1299619674682617,
+      "step": 5348
+    },
+    {
+      "epoch": 0.5448592277256965,
+      "grad_norm": 0.11679762601852417,
+      "learning_rate": 0.0007904879773691655,
+      "loss": 2.1421523094177246,
+      "step": 5350
+    },
+    {
+      "epoch": 0.5450629134183043,
+      "grad_norm": 0.11888381093740463,
+      "learning_rate": 0.0007901343705799151,
+      "loss": 2.219864845275879,
+      "step": 5352
+    },
+    {
+      "epoch": 0.5452665991109119,
+      "grad_norm": 0.09826654940843582,
+      "learning_rate": 0.0007897807637906647,
+      "loss": 2.044268846511841,
+      "step": 5354
+    },
+    {
+      "epoch": 0.5454702848035197,
+      "grad_norm": 0.11918283253908157,
+      "learning_rate": 0.0007894271570014145,
+      "loss": 2.1726956367492676,
+      "step": 5356
+    },
+    {
+      "epoch": 0.5456739704961274,
+      "grad_norm": 0.12886692583560944,
+      "learning_rate": 0.0007890735502121641,
+      "loss": 2.312138080596924,
+      "step": 5358
+    },
+    {
+      "epoch": 0.5458776561887352,
+      "grad_norm": 0.11691565811634064,
+      "learning_rate": 0.0007887199434229138,
+      "loss": 2.1417927742004395,
+      "step": 5360
+    },
+    {
+      "epoch": 0.5460813418813429,
+      "grad_norm": 0.1122870072722435,
+      "learning_rate": 0.0007883663366336634,
+      "loss": 2.0286943912506104,
+      "step": 5362
+    },
+    {
+      "epoch": 0.5462850275739506,
+      "grad_norm": 0.12238631397485733,
+      "learning_rate": 0.000788012729844413,
+      "loss": 2.246967315673828,
+      "step": 5364
+    },
+    {
+      "epoch": 0.5464887132665583,
+      "grad_norm": 0.1875850111246109,
+      "learning_rate": 0.0007876591230551626,
+      "loss": 2.148320198059082,
+      "step": 5366
+    },
+    {
+      "epoch": 0.5466923989591661,
+      "grad_norm": 0.11179684847593307,
+      "learning_rate": 0.0007873055162659123,
+      "loss": 2.2059571743011475,
+      "step": 5368
+    },
+    {
+      "epoch": 0.5468960846517739,
+      "grad_norm": 0.11295250058174133,
+      "learning_rate": 0.000786951909476662,
+      "loss": 2.225703239440918,
+      "step": 5370
+    },
+    {
+      "epoch": 0.5470997703443816,
+      "grad_norm": 0.20771226286888123,
+      "learning_rate": 0.0007865983026874116,
+      "loss": 2.25679087638855,
+      "step": 5372
+    },
+    {
+      "epoch": 0.5473034560369893,
+      "grad_norm": 0.12048251926898956,
+      "learning_rate": 0.0007862446958981613,
+      "loss": 2.1028501987457275,
+      "step": 5374
+    },
+    {
+      "epoch": 0.547507141729597,
+      "grad_norm": 0.11392420530319214,
+      "learning_rate": 0.0007858910891089109,
+      "loss": 2.274704694747925,
+      "step": 5376
+    },
+    {
+      "epoch": 0.5477108274222048,
+      "grad_norm": 0.12857267260551453,
+      "learning_rate": 0.0007855374823196606,
+      "loss": 2.1960277557373047,
+      "step": 5378
+    },
+    {
+      "epoch": 0.5479145131148125,
+      "grad_norm": 0.10829721391201019,
+      "learning_rate": 0.0007851838755304102,
+      "loss": 2.15274977684021,
+      "step": 5380
+    },
+    {
+      "epoch": 0.5481181988074203,
+      "grad_norm": 0.11893216520547867,
+      "learning_rate": 0.0007848302687411598,
+      "loss": 2.277278423309326,
+      "step": 5382
+    },
+    {
+      "epoch": 0.5483218845000281,
+      "grad_norm": 0.10940895229578018,
+      "learning_rate": 0.0007844766619519095,
+      "loss": 2.2065067291259766,
+      "step": 5384
+    },
+    {
+      "epoch": 0.5485255701926357,
+      "grad_norm": 0.1107495129108429,
+      "learning_rate": 0.0007841230551626591,
+      "loss": 1.988950490951538,
+      "step": 5386
+    },
+    {
+      "epoch": 0.5487292558852435,
+      "grad_norm": 0.1373213827610016,
+      "learning_rate": 0.0007837694483734088,
+      "loss": 2.063143730163574,
+      "step": 5388
+    },
+    {
+      "epoch": 0.5489329415778512,
+      "grad_norm": 0.10859141498804092,
+      "learning_rate": 0.0007834158415841585,
+      "loss": 2.1011669635772705,
+      "step": 5390
+    },
+    {
+      "epoch": 0.549136627270459,
+      "grad_norm": 0.1453084498643875,
+      "learning_rate": 0.0007830622347949081,
+      "loss": 2.3189151287078857,
+      "step": 5392
+    },
+    {
+      "epoch": 0.5493403129630667,
+      "grad_norm": 0.21547430753707886,
+      "learning_rate": 0.0007827086280056577,
+      "loss": 2.242112636566162,
+      "step": 5394
+    },
+    {
+      "epoch": 0.5495439986556744,
+      "grad_norm": 0.12134073674678802,
+      "learning_rate": 0.0007823550212164073,
+      "loss": 2.243335723876953,
+      "step": 5396
+    },
+    {
+      "epoch": 0.5497476843482821,
+      "grad_norm": 0.13093750178813934,
+      "learning_rate": 0.000782001414427157,
+      "loss": 2.253917694091797,
+      "step": 5398
+    },
+    {
+      "epoch": 0.5499513700408899,
+      "grad_norm": 0.12389874458312988,
+      "learning_rate": 0.0007816478076379066,
+      "loss": 2.243673324584961,
+      "step": 5400
+    },
+    {
+      "epoch": 0.5501550557334977,
+      "grad_norm": 0.12094106525182724,
+      "learning_rate": 0.0007812942008486564,
+      "loss": 2.246340751647949,
+      "step": 5402
+    },
+    {
+      "epoch": 0.5503587414261054,
+      "grad_norm": 0.1240958571434021,
+      "learning_rate": 0.000780940594059406,
+      "loss": 2.087345600128174,
+      "step": 5404
+    },
+    {
+      "epoch": 0.5505624271187131,
+      "grad_norm": 0.12217339873313904,
+      "learning_rate": 0.0007805869872701556,
+      "loss": 2.1736154556274414,
+      "step": 5406
+    },
+    {
+      "epoch": 0.5507661128113208,
+      "grad_norm": 0.12415944039821625,
+      "learning_rate": 0.0007802333804809052,
+      "loss": 2.222632884979248,
+      "step": 5408
+    },
+    {
+      "epoch": 0.5509697985039286,
+      "grad_norm": 0.12799328565597534,
+      "learning_rate": 0.0007798797736916548,
+      "loss": 2.200870990753174,
+      "step": 5410
+    },
+    {
+      "epoch": 0.5511734841965363,
+      "grad_norm": 0.11702173203229904,
+      "learning_rate": 0.0007795261669024046,
+      "loss": 2.2857747077941895,
+      "step": 5412
+    },
+    {
+      "epoch": 0.5513771698891441,
+      "grad_norm": 0.12212134152650833,
+      "learning_rate": 0.0007791725601131542,
+      "loss": 2.064748764038086,
+      "step": 5414
+    },
+    {
+      "epoch": 0.5515808555817518,
+      "grad_norm": 0.13553938269615173,
+      "learning_rate": 0.0007788189533239039,
+      "loss": 2.230475902557373,
+      "step": 5416
+    },
+    {
+      "epoch": 0.5517845412743595,
+      "grad_norm": 0.14421720802783966,
+      "learning_rate": 0.0007784653465346535,
+      "loss": 2.0755066871643066,
+      "step": 5418
+    },
+    {
+      "epoch": 0.5519882269669673,
+      "grad_norm": 0.15038596093654633,
+      "learning_rate": 0.0007781117397454031,
+      "loss": 2.349822521209717,
+      "step": 5420
+    },
+    {
+      "epoch": 0.552191912659575,
+      "grad_norm": 0.11526555567979813,
+      "learning_rate": 0.0007777581329561527,
+      "loss": 2.1431446075439453,
+      "step": 5422
+    },
+    {
+      "epoch": 0.5523955983521828,
+      "grad_norm": 0.10479426383972168,
+      "learning_rate": 0.0007774045261669024,
+      "loss": 2.1232223510742188,
+      "step": 5424
+    },
+    {
+      "epoch": 0.5525992840447905,
+      "grad_norm": 0.10967665910720825,
+      "learning_rate": 0.0007770509193776521,
+      "loss": 2.203411340713501,
+      "step": 5426
+    },
+    {
+      "epoch": 0.5528029697373982,
+      "grad_norm": 0.10369928181171417,
+      "learning_rate": 0.0007766973125884017,
+      "loss": 2.1811447143554688,
+      "step": 5428
+    },
+    {
+      "epoch": 0.5530066554300059,
+      "grad_norm": 0.12151315063238144,
+      "learning_rate": 0.0007763437057991514,
+      "loss": 2.2590713500976562,
+      "step": 5430
+    },
+    {
+      "epoch": 0.5532103411226137,
+      "grad_norm": 0.1407015025615692,
+      "learning_rate": 0.000775990099009901,
+      "loss": 2.1766867637634277,
+      "step": 5432
+    },
+    {
+      "epoch": 0.5534140268152214,
+      "grad_norm": 0.10782373696565628,
+      "learning_rate": 0.0007756364922206506,
+      "loss": 2.2598071098327637,
+      "step": 5434
+    },
+    {
+      "epoch": 0.5536177125078292,
+      "grad_norm": 0.12348472326993942,
+      "learning_rate": 0.0007752828854314004,
+      "loss": 2.1248276233673096,
+      "step": 5436
+    },
+    {
+      "epoch": 0.5538213982004369,
+      "grad_norm": 0.14899663627147675,
+      "learning_rate": 0.0007749292786421499,
+      "loss": 2.2195653915405273,
+      "step": 5438
+    },
+    {
+      "epoch": 0.5540250838930446,
+      "grad_norm": 0.10735470056533813,
+      "learning_rate": 0.0007745756718528996,
+      "loss": 2.125946044921875,
+      "step": 5440
+    },
+    {
+      "epoch": 0.5542287695856524,
+      "grad_norm": 0.13414768874645233,
+      "learning_rate": 0.0007742220650636492,
+      "loss": 2.138725757598877,
+      "step": 5442
+    },
+    {
+      "epoch": 0.5544324552782601,
+      "grad_norm": 0.11430314183235168,
+      "learning_rate": 0.0007738684582743989,
+      "loss": 2.265775203704834,
+      "step": 5444
+    },
+    {
+      "epoch": 0.5546361409708679,
+      "grad_norm": 0.11863192915916443,
+      "learning_rate": 0.0007735148514851486,
+      "loss": 2.2101926803588867,
+      "step": 5446
+    },
+    {
+      "epoch": 0.5548398266634756,
+      "grad_norm": 0.12555073201656342,
+      "learning_rate": 0.0007731612446958982,
+      "loss": 2.1564784049987793,
+      "step": 5448
+    },
+    {
+      "epoch": 0.5550435123560833,
+      "grad_norm": 0.12202906608581543,
+      "learning_rate": 0.0007728076379066479,
+      "loss": 2.277492046356201,
+      "step": 5450
+    },
+    {
+      "epoch": 0.555247198048691,
+      "grad_norm": 0.1245780661702156,
+      "learning_rate": 0.0007724540311173974,
+      "loss": 2.208643674850464,
+      "step": 5452
+    },
+    {
+      "epoch": 0.5554508837412988,
+      "grad_norm": 0.12742605805397034,
+      "learning_rate": 0.0007721004243281471,
+      "loss": 2.2650575637817383,
+      "step": 5454
+    },
+    {
+      "epoch": 0.5556545694339066,
+      "grad_norm": 0.18629691004753113,
+      "learning_rate": 0.0007717468175388967,
+      "loss": 2.1824657917022705,
+      "step": 5456
+    },
+    {
+      "epoch": 0.5558582551265143,
+      "grad_norm": 0.14174389839172363,
+      "learning_rate": 0.0007713932107496465,
+      "loss": 2.2312045097351074,
+      "step": 5458
+    },
+    {
+      "epoch": 0.556061940819122,
+      "grad_norm": 0.14883537590503693,
+      "learning_rate": 0.0007710396039603961,
+      "loss": 1.9981105327606201,
+      "step": 5460
+    },
+    {
+      "epoch": 0.5562656265117297,
+      "grad_norm": 0.24698324501514435,
+      "learning_rate": 0.0007706859971711457,
+      "loss": 2.079042911529541,
+      "step": 5462
+    },
+    {
+      "epoch": 0.5564693122043375,
+      "grad_norm": 0.11522044986486435,
+      "learning_rate": 0.0007703323903818954,
+      "loss": 2.243058443069458,
+      "step": 5464
+    },
+    {
+      "epoch": 0.5566729978969452,
+      "grad_norm": 0.11745002120733261,
+      "learning_rate": 0.0007699787835926449,
+      "loss": 2.1751461029052734,
+      "step": 5466
+    },
+    {
+      "epoch": 0.556876683589553,
+      "grad_norm": 0.12648165225982666,
+      "learning_rate": 0.0007696251768033946,
+      "loss": 2.1258010864257812,
+      "step": 5468
+    },
+    {
+      "epoch": 0.5570803692821606,
+      "grad_norm": 0.17080917954444885,
+      "learning_rate": 0.0007692715700141443,
+      "loss": 2.1963648796081543,
+      "step": 5470
+    },
+    {
+      "epoch": 0.5572840549747684,
+      "grad_norm": 0.1391838937997818,
+      "learning_rate": 0.000768917963224894,
+      "loss": 2.2353696823120117,
+      "step": 5472
+    },
+    {
+      "epoch": 0.5574877406673762,
+      "grad_norm": 0.16418743133544922,
+      "learning_rate": 0.0007685643564356436,
+      "loss": 2.17199969291687,
+      "step": 5474
+    },
+    {
+      "epoch": 0.5576914263599839,
+      "grad_norm": 0.13869188725948334,
+      "learning_rate": 0.0007682107496463932,
+      "loss": 2.184211254119873,
+      "step": 5476
+    },
+    {
+      "epoch": 0.5578951120525917,
+      "grad_norm": 0.18197417259216309,
+      "learning_rate": 0.0007678571428571429,
+      "loss": 2.2816295623779297,
+      "step": 5478
+    },
+    {
+      "epoch": 0.5580987977451994,
+      "grad_norm": 0.12123195081949234,
+      "learning_rate": 0.0007675035360678924,
+      "loss": 2.211876392364502,
+      "step": 5480
+    },
+    {
+      "epoch": 0.5583024834378071,
+      "grad_norm": 0.12275488674640656,
+      "learning_rate": 0.0007671499292786422,
+      "loss": 2.184711456298828,
+      "step": 5482
+    },
+    {
+      "epoch": 0.5585061691304148,
+      "grad_norm": 0.1449512541294098,
+      "learning_rate": 0.0007667963224893918,
+      "loss": 2.199005126953125,
+      "step": 5484
+    },
+    {
+      "epoch": 0.5587098548230226,
+      "grad_norm": 0.12805058062076569,
+      "learning_rate": 0.0007664427157001415,
+      "loss": 2.160581588745117,
+      "step": 5486
+    },
+    {
+      "epoch": 0.5589135405156304,
+      "grad_norm": 0.12123409658670425,
+      "learning_rate": 0.0007660891089108911,
+      "loss": 2.1456246376037598,
+      "step": 5488
+    },
+    {
+      "epoch": 0.5591172262082381,
+      "grad_norm": 0.13756166398525238,
+      "learning_rate": 0.0007657355021216407,
+      "loss": 2.2305946350097656,
+      "step": 5490
+    },
+    {
+      "epoch": 0.5593209119008458,
+      "grad_norm": 0.1444600224494934,
+      "learning_rate": 0.0007653818953323905,
+      "loss": 2.309861660003662,
+      "step": 5492
+    },
+    {
+      "epoch": 0.5595245975934535,
+      "grad_norm": 0.12502315640449524,
+      "learning_rate": 0.00076502828854314,
+      "loss": 2.116710662841797,
+      "step": 5494
+    },
+    {
+      "epoch": 0.5597282832860613,
+      "grad_norm": 0.11468110978603363,
+      "learning_rate": 0.0007646746817538897,
+      "loss": 2.125654697418213,
+      "step": 5496
+    },
+    {
+      "epoch": 0.559931968978669,
+      "grad_norm": 0.13653726875782013,
+      "learning_rate": 0.0007643210749646393,
+      "loss": 2.36659836769104,
+      "step": 5498
+    },
+    {
+      "epoch": 0.5601356546712768,
+      "grad_norm": 0.12316544353961945,
+      "learning_rate": 0.000763967468175389,
+      "loss": 2.2145047187805176,
+      "step": 5500
+    },
+    {
+      "epoch": 0.5603393403638844,
+      "grad_norm": 0.10237129032611847,
+      "learning_rate": 0.0007636138613861386,
+      "loss": 2.195134162902832,
+      "step": 5502
+    },
+    {
+      "epoch": 0.5605430260564922,
+      "grad_norm": 0.1693531721830368,
+      "learning_rate": 0.0007632602545968883,
+      "loss": 2.1791422367095947,
+      "step": 5504
+    },
+    {
+      "epoch": 0.5607467117491,
+      "grad_norm": 0.1264389008283615,
+      "learning_rate": 0.000762906647807638,
+      "loss": 2.2286808490753174,
+      "step": 5506
+    },
+    {
+      "epoch": 0.5609503974417077,
+      "grad_norm": 0.09869515150785446,
+      "learning_rate": 0.0007625530410183875,
+      "loss": 2.167285442352295,
+      "step": 5508
+    },
+    {
+      "epoch": 0.5611540831343155,
+      "grad_norm": 0.11070269346237183,
+      "learning_rate": 0.0007621994342291372,
+      "loss": 2.241633892059326,
+      "step": 5510
+    },
+    {
+      "epoch": 0.5613577688269231,
+      "grad_norm": 0.17682640254497528,
+      "learning_rate": 0.0007618458274398868,
+      "loss": 2.249135732650757,
+      "step": 5512
+    },
+    {
+      "epoch": 0.5615614545195309,
+      "grad_norm": 0.1398433893918991,
+      "learning_rate": 0.0007614922206506365,
+      "loss": 2.1333439350128174,
+      "step": 5514
+    },
+    {
+      "epoch": 0.5617651402121386,
+      "grad_norm": 0.14497871696949005,
+      "learning_rate": 0.0007611386138613862,
+      "loss": 2.048008680343628,
+      "step": 5516
+    },
+    {
+      "epoch": 0.5619688259047464,
+      "grad_norm": 0.13310587406158447,
+      "learning_rate": 0.0007607850070721358,
+      "loss": 2.1080758571624756,
+      "step": 5518
+    },
+    {
+      "epoch": 0.5621725115973542,
+      "grad_norm": 0.12043895572423935,
+      "learning_rate": 0.0007604314002828855,
+      "loss": 2.254199981689453,
+      "step": 5520
+    },
+    {
+      "epoch": 0.5623761972899619,
+      "grad_norm": 0.16091550886631012,
+      "learning_rate": 0.000760077793493635,
+      "loss": 2.1024727821350098,
+      "step": 5522
+    },
+    {
+      "epoch": 0.5625798829825696,
+      "grad_norm": 0.13031473755836487,
+      "learning_rate": 0.0007597241867043847,
+      "loss": 2.108842372894287,
+      "step": 5524
+    },
+    {
+      "epoch": 0.5627835686751773,
+      "grad_norm": 0.10596181452274323,
+      "learning_rate": 0.0007593705799151343,
+      "loss": 2.0818216800689697,
+      "step": 5526
+    },
+    {
+      "epoch": 0.5629872543677851,
+      "grad_norm": 0.12174347788095474,
+      "learning_rate": 0.0007590169731258841,
+      "loss": 2.078129768371582,
+      "step": 5528
+    },
+    {
+      "epoch": 0.5631909400603928,
+      "grad_norm": 0.16686631739139557,
+      "learning_rate": 0.0007586633663366337,
+      "loss": 2.076770782470703,
+      "step": 5530
+    },
+    {
+      "epoch": 0.5633946257530006,
+      "grad_norm": 0.14236228168010712,
+      "learning_rate": 0.0007583097595473833,
+      "loss": 2.329357624053955,
+      "step": 5532
+    },
+    {
+      "epoch": 0.5635983114456082,
+      "grad_norm": 0.19253623485565186,
+      "learning_rate": 0.000757956152758133,
+      "loss": 2.218338966369629,
+      "step": 5534
+    },
+    {
+      "epoch": 0.563801997138216,
+      "grad_norm": 0.15200982987880707,
+      "learning_rate": 0.0007576025459688826,
+      "loss": 2.2943201065063477,
+      "step": 5536
+    },
+    {
+      "epoch": 0.5640056828308238,
+      "grad_norm": 0.09773068130016327,
+      "learning_rate": 0.0007572489391796323,
+      "loss": 2.1221587657928467,
+      "step": 5538
+    },
+    {
+      "epoch": 0.5642093685234315,
+      "grad_norm": 0.11191946268081665,
+      "learning_rate": 0.0007568953323903819,
+      "loss": 2.1315903663635254,
+      "step": 5540
+    },
+    {
+      "epoch": 0.5644130542160393,
+      "grad_norm": 0.11184900254011154,
+      "learning_rate": 0.0007565417256011316,
+      "loss": 2.206247329711914,
+      "step": 5542
+    },
+    {
+      "epoch": 0.5646167399086469,
+      "grad_norm": 0.12547892332077026,
+      "learning_rate": 0.0007561881188118812,
+      "loss": 2.2616868019104004,
+      "step": 5544
+    },
+    {
+      "epoch": 0.5648204256012547,
+      "grad_norm": 0.11614930629730225,
+      "learning_rate": 0.0007558345120226308,
+      "loss": 2.156707763671875,
+      "step": 5546
+    },
+    {
+      "epoch": 0.5650241112938624,
+      "grad_norm": 0.12440509349107742,
+      "learning_rate": 0.0007554809052333805,
+      "loss": 2.2248895168304443,
+      "step": 5548
+    },
+    {
+      "epoch": 0.5652277969864702,
+      "grad_norm": 0.12463603168725967,
+      "learning_rate": 0.0007551272984441302,
+      "loss": 2.169832706451416,
+      "step": 5550
+    },
+    {
+      "epoch": 0.565431482679078,
+      "grad_norm": 0.10741818696260452,
+      "learning_rate": 0.0007547736916548798,
+      "loss": 2.042513847351074,
+      "step": 5552
+    },
+    {
+      "epoch": 0.5656351683716857,
+      "grad_norm": 0.18778938055038452,
+      "learning_rate": 0.0007544200848656294,
+      "loss": 2.132786750793457,
+      "step": 5554
+    },
+    {
+      "epoch": 0.5658388540642934,
+      "grad_norm": 0.1224108636379242,
+      "learning_rate": 0.0007540664780763791,
+      "loss": 2.1636898517608643,
+      "step": 5556
+    },
+    {
+      "epoch": 0.5660425397569011,
+      "grad_norm": 0.12876828014850616,
+      "learning_rate": 0.0007537128712871287,
+      "loss": 2.0716824531555176,
+      "step": 5558
+    },
+    {
+      "epoch": 0.5662462254495089,
+      "grad_norm": 0.13119415938854218,
+      "learning_rate": 0.0007533592644978783,
+      "loss": 2.115713119506836,
+      "step": 5560
+    },
+    {
+      "epoch": 0.5664499111421166,
+      "grad_norm": 0.12610168755054474,
+      "learning_rate": 0.0007530056577086281,
+      "loss": 2.246218681335449,
+      "step": 5562
+    },
+    {
+      "epoch": 0.5666535968347244,
+      "grad_norm": 0.11753132939338684,
+      "learning_rate": 0.0007526520509193777,
+      "loss": 2.213016986846924,
+      "step": 5564
+    },
+    {
+      "epoch": 0.566857282527332,
+      "grad_norm": 0.10466507077217102,
+      "learning_rate": 0.0007522984441301273,
+      "loss": 2.2209348678588867,
+      "step": 5566
+    },
+    {
+      "epoch": 0.5670609682199398,
+      "grad_norm": 0.15010905265808105,
+      "learning_rate": 0.0007519448373408769,
+      "loss": 2.1415112018585205,
+      "step": 5568
+    },
+    {
+      "epoch": 0.5672646539125475,
+      "grad_norm": 0.11446774750947952,
+      "learning_rate": 0.0007515912305516266,
+      "loss": 2.2216758728027344,
+      "step": 5570
+    },
+    {
+      "epoch": 0.5674683396051553,
+      "grad_norm": 0.13279752433300018,
+      "learning_rate": 0.0007512376237623763,
+      "loss": 2.256660223007202,
+      "step": 5572
+    },
+    {
+      "epoch": 0.5676720252977631,
+      "grad_norm": 0.12397786974906921,
+      "learning_rate": 0.0007508840169731259,
+      "loss": 2.1019246578216553,
+      "step": 5574
+    },
+    {
+      "epoch": 0.5678757109903707,
+      "grad_norm": 0.11810149997472763,
+      "learning_rate": 0.0007505304101838756,
+      "loss": 2.1080479621887207,
+      "step": 5576
+    },
+    {
+      "epoch": 0.5680793966829785,
+      "grad_norm": 0.12142546474933624,
+      "learning_rate": 0.0007501768033946252,
+      "loss": 2.097409725189209,
+      "step": 5578
+    },
+    {
+      "epoch": 0.5682830823755862,
+      "grad_norm": 0.15604248642921448,
+      "learning_rate": 0.0007498231966053748,
+      "loss": 2.0749728679656982,
+      "step": 5580
+    },
+    {
+      "epoch": 0.568486768068194,
+      "grad_norm": 0.123172327876091,
+      "learning_rate": 0.0007494695898161244,
+      "loss": 2.122084856033325,
+      "step": 5582
+    },
+    {
+      "epoch": 0.5686904537608017,
+      "grad_norm": 0.11206883937120438,
+      "learning_rate": 0.0007491159830268742,
+      "loss": 2.2141404151916504,
+      "step": 5584
+    },
+    {
+      "epoch": 0.5688941394534095,
+      "grad_norm": 0.10153889656066895,
+      "learning_rate": 0.0007487623762376238,
+      "loss": 2.2096760272979736,
+      "step": 5586
+    },
+    {
+      "epoch": 0.5690978251460171,
+      "grad_norm": 0.17403686046600342,
+      "learning_rate": 0.0007484087694483734,
+      "loss": 2.1911303997039795,
+      "step": 5588
+    },
+    {
+      "epoch": 0.5693015108386249,
+      "grad_norm": 0.1021316796541214,
+      "learning_rate": 0.0007480551626591231,
+      "loss": 2.1196603775024414,
+      "step": 5590
+    },
+    {
+      "epoch": 0.5695051965312327,
+      "grad_norm": 0.1253519505262375,
+      "learning_rate": 0.0007477015558698727,
+      "loss": 2.1641898155212402,
+      "step": 5592
+    },
+    {
+      "epoch": 0.5697088822238404,
+      "grad_norm": 0.11909963935613632,
+      "learning_rate": 0.0007473479490806223,
+      "loss": 2.2786197662353516,
+      "step": 5594
+    },
+    {
+      "epoch": 0.5699125679164482,
+      "grad_norm": 0.11770684272050858,
+      "learning_rate": 0.000746994342291372,
+      "loss": 2.2450907230377197,
+      "step": 5596
+    },
+    {
+      "epoch": 0.5701162536090558,
+      "grad_norm": 0.11919151246547699,
+      "learning_rate": 0.0007466407355021217,
+      "loss": 2.061859607696533,
+      "step": 5598
+    },
+    {
+      "epoch": 0.5703199393016636,
+      "grad_norm": 0.11989054828882217,
+      "learning_rate": 0.0007462871287128713,
+      "loss": 2.0634613037109375,
+      "step": 5600
+    },
+    {
+      "epoch": 0.5705236249942713,
+      "grad_norm": 0.12115888297557831,
+      "learning_rate": 0.0007459335219236209,
+      "loss": 2.3590641021728516,
+      "step": 5602
+    },
+    {
+      "epoch": 0.5707273106868791,
+      "grad_norm": 0.12585215270519257,
+      "learning_rate": 0.0007455799151343706,
+      "loss": 2.1100969314575195,
+      "step": 5604
+    },
+    {
+      "epoch": 0.5709309963794869,
+      "grad_norm": 0.13560695946216583,
+      "learning_rate": 0.0007452263083451203,
+      "loss": 2.1116816997528076,
+      "step": 5606
+    },
+    {
+      "epoch": 0.5711346820720945,
+      "grad_norm": 0.12365266680717468,
+      "learning_rate": 0.0007448727015558699,
+      "loss": 2.097095012664795,
+      "step": 5608
+    },
+    {
+      "epoch": 0.5713383677647023,
+      "grad_norm": 0.11030678451061249,
+      "learning_rate": 0.0007445190947666195,
+      "loss": 2.007403612136841,
+      "step": 5610
+    },
+    {
+      "epoch": 0.57154205345731,
+      "grad_norm": 0.11775430291891098,
+      "learning_rate": 0.0007441654879773692,
+      "loss": 2.286966323852539,
+      "step": 5612
+    },
+    {
+      "epoch": 0.5717457391499178,
+      "grad_norm": 0.12257828563451767,
+      "learning_rate": 0.0007438118811881188,
+      "loss": 2.1636693477630615,
+      "step": 5614
+    },
+    {
+      "epoch": 0.5719494248425255,
+      "grad_norm": 0.1327316164970398,
+      "learning_rate": 0.0007434582743988684,
+      "loss": 2.2045092582702637,
+      "step": 5616
+    },
+    {
+      "epoch": 0.5721531105351333,
+      "grad_norm": 0.10372668504714966,
+      "learning_rate": 0.0007431046676096182,
+      "loss": 2.0279693603515625,
+      "step": 5618
+    },
+    {
+      "epoch": 0.5723567962277409,
+      "grad_norm": 0.13285857439041138,
+      "learning_rate": 0.0007427510608203678,
+      "loss": 2.3299806118011475,
+      "step": 5620
+    },
+    {
+      "epoch": 0.5725604819203487,
+      "grad_norm": 0.12562139332294464,
+      "learning_rate": 0.0007423974540311174,
+      "loss": 2.2645797729492188,
+      "step": 5622
+    },
+    {
+      "epoch": 0.5727641676129565,
+      "grad_norm": 0.12214555591344833,
+      "learning_rate": 0.000742043847241867,
+      "loss": 2.2804007530212402,
+      "step": 5624
+    },
+    {
+      "epoch": 0.5729678533055642,
+      "grad_norm": 0.12079360336065292,
+      "learning_rate": 0.0007416902404526167,
+      "loss": 2.2410755157470703,
+      "step": 5626
+    },
+    {
+      "epoch": 0.573171538998172,
+      "grad_norm": 0.12311611324548721,
+      "learning_rate": 0.0007413366336633663,
+      "loss": 2.042483329772949,
+      "step": 5628
+    },
+    {
+      "epoch": 0.5733752246907796,
+      "grad_norm": 0.1292836219072342,
+      "learning_rate": 0.000740983026874116,
+      "loss": 2.2727954387664795,
+      "step": 5630
+    },
+    {
+      "epoch": 0.5735789103833874,
+      "grad_norm": 0.1301746815443039,
+      "learning_rate": 0.0007406294200848657,
+      "loss": 2.1457064151763916,
+      "step": 5632
+    },
+    {
+      "epoch": 0.5737825960759951,
+      "grad_norm": 0.104102224111557,
+      "learning_rate": 0.0007402758132956153,
+      "loss": 2.076968193054199,
+      "step": 5634
+    },
+    {
+      "epoch": 0.5739862817686029,
+      "grad_norm": 0.11525720357894897,
+      "learning_rate": 0.000739922206506365,
+      "loss": 2.312845468521118,
+      "step": 5636
+    },
+    {
+      "epoch": 0.5741899674612106,
+      "grad_norm": 0.12652763724327087,
+      "learning_rate": 0.0007395685997171145,
+      "loss": 2.227560043334961,
+      "step": 5638
+    },
+    {
+      "epoch": 0.5743936531538183,
+      "grad_norm": 0.12284594029188156,
+      "learning_rate": 0.0007392149929278643,
+      "loss": 2.018963098526001,
+      "step": 5640
+    },
+    {
+      "epoch": 0.574597338846426,
+      "grad_norm": 0.1133703663945198,
+      "learning_rate": 0.0007388613861386139,
+      "loss": 2.284489631652832,
+      "step": 5642
+    },
+    {
+      "epoch": 0.5748010245390338,
+      "grad_norm": 0.17900599539279938,
+      "learning_rate": 0.0007385077793493635,
+      "loss": 2.352895975112915,
+      "step": 5644
+    },
+    {
+      "epoch": 0.5750047102316416,
+      "grad_norm": 0.13084252178668976,
+      "learning_rate": 0.0007381541725601132,
+      "loss": 2.2882752418518066,
+      "step": 5646
+    },
+    {
+      "epoch": 0.5752083959242493,
+      "grad_norm": 0.12346002459526062,
+      "learning_rate": 0.0007378005657708628,
+      "loss": 2.0930776596069336,
+      "step": 5648
+    },
+    {
+      "epoch": 0.575412081616857,
+      "grad_norm": 0.14437732100486755,
+      "learning_rate": 0.0007374469589816125,
+      "loss": 2.0397298336029053,
+      "step": 5650
+    },
+    {
+      "epoch": 0.5756157673094647,
+      "grad_norm": 0.13602668046951294,
+      "learning_rate": 0.000737093352192362,
+      "loss": 2.111401319503784,
+      "step": 5652
+    },
+    {
+      "epoch": 0.5758194530020725,
+      "grad_norm": 0.11576951295137405,
+      "learning_rate": 0.0007367397454031118,
+      "loss": 2.060234546661377,
+      "step": 5654
+    },
+    {
+      "epoch": 0.5760231386946802,
+      "grad_norm": 0.14814341068267822,
+      "learning_rate": 0.0007363861386138614,
+      "loss": 2.2040693759918213,
+      "step": 5656
+    },
+    {
+      "epoch": 0.576226824387288,
+      "grad_norm": 0.13323092460632324,
+      "learning_rate": 0.000736032531824611,
+      "loss": 2.215704917907715,
+      "step": 5658
+    },
+    {
+      "epoch": 0.5764305100798958,
+      "grad_norm": 0.1304558962583542,
+      "learning_rate": 0.0007356789250353607,
+      "loss": 2.0584301948547363,
+      "step": 5660
+    },
+    {
+      "epoch": 0.5766341957725034,
+      "grad_norm": 0.11538539081811905,
+      "learning_rate": 0.0007353253182461103,
+      "loss": 2.047435998916626,
+      "step": 5662
+    },
+    {
+      "epoch": 0.5768378814651112,
+      "grad_norm": 0.11744815856218338,
+      "learning_rate": 0.0007349717114568601,
+      "loss": 2.000859022140503,
+      "step": 5664
+    },
+    {
+      "epoch": 0.5770415671577189,
+      "grad_norm": 0.13838565349578857,
+      "learning_rate": 0.0007346181046676096,
+      "loss": 2.26808762550354,
+      "step": 5666
+    },
+    {
+      "epoch": 0.5772452528503267,
+      "grad_norm": 0.12291118502616882,
+      "learning_rate": 0.0007342644978783593,
+      "loss": 2.219853162765503,
+      "step": 5668
+    },
+    {
+      "epoch": 0.5774489385429344,
+      "grad_norm": 0.11459051072597504,
+      "learning_rate": 0.0007339108910891089,
+      "loss": 2.30008602142334,
+      "step": 5670
+    },
+    {
+      "epoch": 0.5776526242355421,
+      "grad_norm": 0.11127769947052002,
+      "learning_rate": 0.0007335572842998585,
+      "loss": 2.097968578338623,
+      "step": 5672
+    },
+    {
+      "epoch": 0.5778563099281498,
+      "grad_norm": 0.1433795541524887,
+      "learning_rate": 0.0007332036775106083,
+      "loss": 2.275020122528076,
+      "step": 5674
+    },
+    {
+      "epoch": 0.5780599956207576,
+      "grad_norm": 0.11843910068273544,
+      "learning_rate": 0.0007328500707213579,
+      "loss": 2.136817216873169,
+      "step": 5676
+    },
+    {
+      "epoch": 0.5782636813133654,
+      "grad_norm": 0.12363915145397186,
+      "learning_rate": 0.0007324964639321076,
+      "loss": 2.180633544921875,
+      "step": 5678
+    },
+    {
+      "epoch": 0.5784673670059731,
+      "grad_norm": 0.1321050524711609,
+      "learning_rate": 0.0007321428571428571,
+      "loss": 2.256535530090332,
+      "step": 5680
+    },
+    {
+      "epoch": 0.5786710526985808,
+      "grad_norm": 0.10442063957452774,
+      "learning_rate": 0.0007317892503536068,
+      "loss": 2.2629504203796387,
+      "step": 5682
+    },
+    {
+      "epoch": 0.5788747383911885,
+      "grad_norm": 0.11953689903020859,
+      "learning_rate": 0.0007314356435643564,
+      "loss": 1.976685881614685,
+      "step": 5684
+    },
+    {
+      "epoch": 0.5790784240837963,
+      "grad_norm": 0.1100454106926918,
+      "learning_rate": 0.000731082036775106,
+      "loss": 2.048116445541382,
+      "step": 5686
+    },
+    {
+      "epoch": 0.579282109776404,
+      "grad_norm": 0.10882994532585144,
+      "learning_rate": 0.0007307284299858558,
+      "loss": 2.152884006500244,
+      "step": 5688
+    },
+    {
+      "epoch": 0.5794857954690118,
+      "grad_norm": 0.1338670253753662,
+      "learning_rate": 0.0007303748231966054,
+      "loss": 2.0614571571350098,
+      "step": 5690
+    },
+    {
+      "epoch": 0.5796894811616196,
+      "grad_norm": 0.12294940650463104,
+      "learning_rate": 0.0007300212164073551,
+      "loss": 2.2152326107025146,
+      "step": 5692
+    },
+    {
+      "epoch": 0.5798931668542272,
+      "grad_norm": 0.12312138825654984,
+      "learning_rate": 0.0007296676096181046,
+      "loss": 2.198913097381592,
+      "step": 5694
+    },
+    {
+      "epoch": 0.580096852546835,
+      "grad_norm": 0.0906839445233345,
+      "learning_rate": 0.0007293140028288543,
+      "loss": 2.0192747116088867,
+      "step": 5696
+    },
+    {
+      "epoch": 0.5803005382394427,
+      "grad_norm": 0.11505401879549026,
+      "learning_rate": 0.000728960396039604,
+      "loss": 2.101466178894043,
+      "step": 5698
+    },
+    {
+      "epoch": 0.5805042239320505,
+      "grad_norm": 0.10482259094715118,
+      "learning_rate": 0.0007286067892503536,
+      "loss": 2.1325016021728516,
+      "step": 5700
+    },
+    {
+      "epoch": 0.5807079096246582,
+      "grad_norm": 0.1126074492931366,
+      "learning_rate": 0.0007282531824611033,
+      "loss": 2.028740167617798,
+      "step": 5702
+    },
+    {
+      "epoch": 0.5809115953172659,
+      "grad_norm": 0.12492992728948593,
+      "learning_rate": 0.0007278995756718529,
+      "loss": 2.2029075622558594,
+      "step": 5704
+    },
+    {
+      "epoch": 0.5811152810098736,
+      "grad_norm": 0.1306290626525879,
+      "learning_rate": 0.0007275459688826026,
+      "loss": 2.2290592193603516,
+      "step": 5706
+    },
+    {
+      "epoch": 0.5813189667024814,
+      "grad_norm": 0.11664531379938126,
+      "learning_rate": 0.0007271923620933521,
+      "loss": 2.061734199523926,
+      "step": 5708
+    },
+    {
+      "epoch": 0.5815226523950892,
+      "grad_norm": 0.12610818445682526,
+      "learning_rate": 0.0007268387553041019,
+      "loss": 2.245943069458008,
+      "step": 5710
+    },
+    {
+      "epoch": 0.5817263380876969,
+      "grad_norm": 0.1164708286523819,
+      "learning_rate": 0.0007264851485148515,
+      "loss": 2.25504732131958,
+      "step": 5712
+    },
+    {
+      "epoch": 0.5819300237803046,
+      "grad_norm": 0.10686644911766052,
+      "learning_rate": 0.0007261315417256011,
+      "loss": 2.2719407081604004,
+      "step": 5714
+    },
+    {
+      "epoch": 0.5821337094729123,
+      "grad_norm": 0.15834969282150269,
+      "learning_rate": 0.0007257779349363508,
+      "loss": 2.2463080883026123,
+      "step": 5716
+    },
+    {
+      "epoch": 0.5823373951655201,
+      "grad_norm": 0.1196233406662941,
+      "learning_rate": 0.0007254243281471004,
+      "loss": 2.190795421600342,
+      "step": 5718
+    },
+    {
+      "epoch": 0.5825410808581278,
+      "grad_norm": 0.1104876697063446,
+      "learning_rate": 0.0007250707213578502,
+      "loss": 2.109438896179199,
+      "step": 5720
+    },
+    {
+      "epoch": 0.5827447665507356,
+      "grad_norm": 0.11524586379528046,
+      "learning_rate": 0.0007247171145685997,
+      "loss": 2.051980972290039,
+      "step": 5722
+    },
+    {
+      "epoch": 0.5829484522433434,
+      "grad_norm": 0.12571680545806885,
+      "learning_rate": 0.0007243635077793494,
+      "loss": 2.22143816947937,
+      "step": 5724
+    },
+    {
+      "epoch": 0.583152137935951,
+      "grad_norm": 0.16392545402050018,
+      "learning_rate": 0.000724009900990099,
+      "loss": 2.080940008163452,
+      "step": 5726
+    },
+    {
+      "epoch": 0.5833558236285588,
+      "grad_norm": 0.12662646174430847,
+      "learning_rate": 0.0007236562942008486,
+      "loss": 2.263650417327881,
+      "step": 5728
+    },
+    {
+      "epoch": 0.5835595093211665,
+      "grad_norm": 0.10644856840372086,
+      "learning_rate": 0.0007233026874115983,
+      "loss": 2.286713123321533,
+      "step": 5730
+    },
+    {
+      "epoch": 0.5837631950137743,
+      "grad_norm": 0.11860610544681549,
+      "learning_rate": 0.000722949080622348,
+      "loss": 2.0691041946411133,
+      "step": 5732
+    },
+    {
+      "epoch": 0.583966880706382,
+      "grad_norm": 0.1357344090938568,
+      "learning_rate": 0.0007225954738330977,
+      "loss": 2.115696430206299,
+      "step": 5734
+    },
+    {
+      "epoch": 0.5841705663989897,
+      "grad_norm": 0.10321585088968277,
+      "learning_rate": 0.0007222418670438473,
+      "loss": 2.1780788898468018,
+      "step": 5736
+    },
+    {
+      "epoch": 0.5843742520915974,
+      "grad_norm": 0.14070770144462585,
+      "learning_rate": 0.0007218882602545969,
+      "loss": 2.0064010620117188,
+      "step": 5738
+    },
+    {
+      "epoch": 0.5845779377842052,
+      "grad_norm": 0.12550899386405945,
+      "learning_rate": 0.0007215346534653465,
+      "loss": 2.2525646686553955,
+      "step": 5740
+    },
+    {
+      "epoch": 0.584781623476813,
+      "grad_norm": 0.1286008208990097,
+      "learning_rate": 0.0007211810466760961,
+      "loss": 2.199039936065674,
+      "step": 5742
+    },
+    {
+      "epoch": 0.5849853091694207,
+      "grad_norm": 0.11532837152481079,
+      "learning_rate": 0.0007208274398868459,
+      "loss": 2.1299610137939453,
+      "step": 5744
+    },
+    {
+      "epoch": 0.5851889948620284,
+      "grad_norm": 0.13768477737903595,
+      "learning_rate": 0.0007204738330975955,
+      "loss": 2.1538450717926025,
+      "step": 5746
+    },
+    {
+      "epoch": 0.5853926805546361,
+      "grad_norm": 0.13155896961688995,
+      "learning_rate": 0.0007201202263083452,
+      "loss": 2.1262364387512207,
+      "step": 5748
+    },
+    {
+      "epoch": 0.5855963662472439,
+      "grad_norm": 0.12181179970502853,
+      "learning_rate": 0.0007197666195190948,
+      "loss": 2.0381970405578613,
+      "step": 5750
+    },
+    {
+      "epoch": 0.5858000519398516,
+      "grad_norm": 0.14482003450393677,
+      "learning_rate": 0.0007194130127298444,
+      "loss": 2.161560535430908,
+      "step": 5752
+    },
+    {
+      "epoch": 0.5860037376324594,
+      "grad_norm": 0.1338665783405304,
+      "learning_rate": 0.000719059405940594,
+      "loss": 2.2674694061279297,
+      "step": 5754
+    },
+    {
+      "epoch": 0.586207423325067,
+      "grad_norm": 0.12887023389339447,
+      "learning_rate": 0.0007187057991513437,
+      "loss": 2.1345934867858887,
+      "step": 5756
+    },
+    {
+      "epoch": 0.5864111090176748,
+      "grad_norm": 0.12575219571590424,
+      "learning_rate": 0.0007183521923620934,
+      "loss": 2.227172374725342,
+      "step": 5758
+    },
+    {
+      "epoch": 0.5866147947102825,
+      "grad_norm": 0.12753604352474213,
+      "learning_rate": 0.000717998585572843,
+      "loss": 2.2868831157684326,
+      "step": 5760
+    },
+    {
+      "epoch": 0.5868184804028903,
+      "grad_norm": 0.16653795540332794,
+      "learning_rate": 0.0007176449787835927,
+      "loss": 2.128230571746826,
+      "step": 5762
+    },
+    {
+      "epoch": 0.5870221660954981,
+      "grad_norm": 0.14026276767253876,
+      "learning_rate": 0.0007172913719943423,
+      "loss": 2.1803252696990967,
+      "step": 5764
+    },
+    {
+      "epoch": 0.5872258517881058,
+      "grad_norm": 0.14044813811779022,
+      "learning_rate": 0.000716937765205092,
+      "loss": 2.224703073501587,
+      "step": 5766
+    },
+    {
+      "epoch": 0.5874295374807135,
+      "grad_norm": 0.12035451084375381,
+      "learning_rate": 0.0007165841584158416,
+      "loss": 2.173762321472168,
+      "step": 5768
+    },
+    {
+      "epoch": 0.5876332231733212,
+      "grad_norm": 0.15759555995464325,
+      "learning_rate": 0.0007162305516265912,
+      "loss": 2.1230368614196777,
+      "step": 5770
+    },
+    {
+      "epoch": 0.587836908865929,
+      "grad_norm": 0.14997094869613647,
+      "learning_rate": 0.0007158769448373409,
+      "loss": 2.2385635375976562,
+      "step": 5772
+    },
+    {
+      "epoch": 0.5880405945585367,
+      "grad_norm": 0.12262008339166641,
+      "learning_rate": 0.0007155233380480905,
+      "loss": 2.1380510330200195,
+      "step": 5774
+    },
+    {
+      "epoch": 0.5882442802511445,
+      "grad_norm": 0.1245741918683052,
+      "learning_rate": 0.0007151697312588402,
+      "loss": 2.101010322570801,
+      "step": 5776
+    },
+    {
+      "epoch": 0.5884479659437521,
+      "grad_norm": 0.12575244903564453,
+      "learning_rate": 0.0007148161244695899,
+      "loss": 2.227003335952759,
+      "step": 5778
+    },
+    {
+      "epoch": 0.5886516516363599,
+      "grad_norm": 0.12538304924964905,
+      "learning_rate": 0.0007144625176803395,
+      "loss": 2.067056655883789,
+      "step": 5780
+    },
+    {
+      "epoch": 0.5888553373289677,
+      "grad_norm": 0.12415127456188202,
+      "learning_rate": 0.0007141089108910891,
+      "loss": 2.156764030456543,
+      "step": 5782
+    },
+    {
+      "epoch": 0.5890590230215754,
+      "grad_norm": 0.10758251696825027,
+      "learning_rate": 0.0007137553041018387,
+      "loss": 2.140799045562744,
+      "step": 5784
+    },
+    {
+      "epoch": 0.5892627087141832,
+      "grad_norm": 0.11932411789894104,
+      "learning_rate": 0.0007134016973125884,
+      "loss": 2.259995460510254,
+      "step": 5786
+    },
+    {
+      "epoch": 0.5894663944067908,
+      "grad_norm": 0.11605558544397354,
+      "learning_rate": 0.000713048090523338,
+      "loss": 2.1587512493133545,
+      "step": 5788
+    },
+    {
+      "epoch": 0.5896700800993986,
+      "grad_norm": 0.10753548890352249,
+      "learning_rate": 0.0007126944837340878,
+      "loss": 2.131270408630371,
+      "step": 5790
+    },
+    {
+      "epoch": 0.5898737657920063,
+      "grad_norm": 0.1256030797958374,
+      "learning_rate": 0.0007123408769448374,
+      "loss": 2.087528705596924,
+      "step": 5792
+    },
+    {
+      "epoch": 0.5900774514846141,
+      "grad_norm": 0.10056347399950027,
+      "learning_rate": 0.000711987270155587,
+      "loss": 2.1330227851867676,
+      "step": 5794
+    },
+    {
+      "epoch": 0.5902811371772219,
+      "grad_norm": 0.12868225574493408,
+      "learning_rate": 0.0007116336633663366,
+      "loss": 2.1285815238952637,
+      "step": 5796
+    },
+    {
+      "epoch": 0.5904848228698296,
+      "grad_norm": 0.14323009550571442,
+      "learning_rate": 0.0007112800565770862,
+      "loss": 2.1502928733825684,
+      "step": 5798
+    },
+    {
+      "epoch": 0.5906885085624373,
+      "grad_norm": 0.14026352763175964,
+      "learning_rate": 0.000710926449787836,
+      "loss": 2.337285280227661,
+      "step": 5800
+    },
+    {
+      "epoch": 0.590892194255045,
+      "grad_norm": 0.13254085183143616,
+      "learning_rate": 0.0007105728429985856,
+      "loss": 2.258711814880371,
+      "step": 5802
+    },
+    {
+      "epoch": 0.5910958799476528,
+      "grad_norm": 0.12581101059913635,
+      "learning_rate": 0.0007102192362093353,
+      "loss": 2.1116037368774414,
+      "step": 5804
+    },
+    {
+      "epoch": 0.5912995656402605,
+      "grad_norm": 0.1658536046743393,
+      "learning_rate": 0.0007098656294200849,
+      "loss": 2.2243106365203857,
+      "step": 5806
+    },
+    {
+      "epoch": 0.5915032513328683,
+      "grad_norm": 0.15318162739276886,
+      "learning_rate": 0.0007095120226308345,
+      "loss": 2.2848992347717285,
+      "step": 5808
+    },
+    {
+      "epoch": 0.5917069370254759,
+      "grad_norm": 0.11438168585300446,
+      "learning_rate": 0.0007091584158415841,
+      "loss": 2.032163381576538,
+      "step": 5810
+    },
+    {
+      "epoch": 0.5919106227180837,
+      "grad_norm": 0.15281060338020325,
+      "learning_rate": 0.0007088048090523338,
+      "loss": 2.310468912124634,
+      "step": 5812
+    },
+    {
+      "epoch": 0.5921143084106915,
+      "grad_norm": 0.12696152925491333,
+      "learning_rate": 0.0007084512022630835,
+      "loss": 2.1293540000915527,
+      "step": 5814
+    },
+    {
+      "epoch": 0.5923179941032992,
+      "grad_norm": 0.11996600031852722,
+      "learning_rate": 0.0007080975954738331,
+      "loss": 2.146444082260132,
+      "step": 5816
+    },
+    {
+      "epoch": 0.592521679795907,
+      "grad_norm": 0.12982875108718872,
+      "learning_rate": 0.0007077439886845828,
+      "loss": 2.2628679275512695,
+      "step": 5818
+    },
+    {
+      "epoch": 0.5927253654885146,
+      "grad_norm": 0.13845832645893097,
+      "learning_rate": 0.0007073903818953324,
+      "loss": 2.2842679023742676,
+      "step": 5820
+    },
+    {
+      "epoch": 0.5929290511811224,
+      "grad_norm": 0.12359467893838882,
+      "learning_rate": 0.000707036775106082,
+      "loss": 2.1193108558654785,
+      "step": 5822
+    },
+    {
+      "epoch": 0.5931327368737301,
+      "grad_norm": 0.1370133012533188,
+      "learning_rate": 0.0007066831683168317,
+      "loss": 2.043365716934204,
+      "step": 5824
+    },
+    {
+      "epoch": 0.5933364225663379,
+      "grad_norm": 0.13645340502262115,
+      "learning_rate": 0.0007063295615275813,
+      "loss": 2.2149620056152344,
+      "step": 5826
+    },
+    {
+      "epoch": 0.5935401082589457,
+      "grad_norm": 0.13821366429328918,
+      "learning_rate": 0.000705975954738331,
+      "loss": 2.1222686767578125,
+      "step": 5828
+    },
+    {
+      "epoch": 0.5937437939515534,
+      "grad_norm": 0.11535792052745819,
+      "learning_rate": 0.0007056223479490806,
+      "loss": 2.037485361099243,
+      "step": 5830
+    },
+    {
+      "epoch": 0.5939474796441611,
+      "grad_norm": 0.13120539486408234,
+      "learning_rate": 0.0007052687411598303,
+      "loss": 2.226588249206543,
+      "step": 5832
+    },
+    {
+      "epoch": 0.5941511653367688,
+      "grad_norm": 0.12012495845556259,
+      "learning_rate": 0.00070491513437058,
+      "loss": 2.239220142364502,
+      "step": 5834
+    },
+    {
+      "epoch": 0.5943548510293766,
+      "grad_norm": 0.14491599798202515,
+      "learning_rate": 0.0007045615275813297,
+      "loss": 2.215017795562744,
+      "step": 5836
+    },
+    {
+      "epoch": 0.5945585367219843,
+      "grad_norm": 0.1036931574344635,
+      "learning_rate": 0.0007042079207920792,
+      "loss": 2.057384967803955,
+      "step": 5838
+    },
+    {
+      "epoch": 0.5947622224145921,
+      "grad_norm": 0.13469237089157104,
+      "learning_rate": 0.0007038543140028288,
+      "loss": 2.252002716064453,
+      "step": 5840
+    },
+    {
+      "epoch": 0.5949659081071997,
+      "grad_norm": 0.12333661317825317,
+      "learning_rate": 0.0007035007072135785,
+      "loss": 2.129938840866089,
+      "step": 5842
+    },
+    {
+      "epoch": 0.5951695937998075,
+      "grad_norm": 0.1126076802611351,
+      "learning_rate": 0.0007031471004243281,
+      "loss": 2.2039663791656494,
+      "step": 5844
+    },
+    {
+      "epoch": 0.5953732794924153,
+      "grad_norm": 0.14256829023361206,
+      "learning_rate": 0.0007027934936350779,
+      "loss": 2.1440048217773438,
+      "step": 5846
+    },
+    {
+      "epoch": 0.595576965185023,
+      "grad_norm": 0.154927060008049,
+      "learning_rate": 0.0007024398868458275,
+      "loss": 2.3388547897338867,
+      "step": 5848
+    },
+    {
+      "epoch": 0.5957806508776308,
+      "grad_norm": 0.12084995210170746,
+      "learning_rate": 0.0007020862800565772,
+      "loss": 2.116058349609375,
+      "step": 5850
+    },
+    {
+      "epoch": 0.5959843365702384,
+      "grad_norm": 0.17354971170425415,
+      "learning_rate": 0.0007017326732673267,
+      "loss": 2.0893397331237793,
+      "step": 5852
+    },
+    {
+      "epoch": 0.5961880222628462,
+      "grad_norm": 0.1491243690252304,
+      "learning_rate": 0.0007013790664780763,
+      "loss": 2.2560250759124756,
+      "step": 5854
+    },
+    {
+      "epoch": 0.5963917079554539,
+      "grad_norm": 0.11963433027267456,
+      "learning_rate": 0.000701025459688826,
+      "loss": 2.1822943687438965,
+      "step": 5856
+    },
+    {
+      "epoch": 0.5965953936480617,
+      "grad_norm": 0.18143661320209503,
+      "learning_rate": 0.0007006718528995757,
+      "loss": 2.164369583129883,
+      "step": 5858
+    },
+    {
+      "epoch": 0.5967990793406694,
+      "grad_norm": 0.13938595354557037,
+      "learning_rate": 0.0007003182461103254,
+      "loss": 2.2488672733306885,
+      "step": 5860
+    },
+    {
+      "epoch": 0.5970027650332772,
+      "grad_norm": 0.13489268720149994,
+      "learning_rate": 0.000699964639321075,
+      "loss": 2.2433359622955322,
+      "step": 5862
+    },
+    {
+      "epoch": 0.5972064507258849,
+      "grad_norm": 0.12128165364265442,
+      "learning_rate": 0.0006996110325318247,
+      "loss": 2.2040345668792725,
+      "step": 5864
+    },
+    {
+      "epoch": 0.5974101364184926,
+      "grad_norm": 0.1320391446352005,
+      "learning_rate": 0.0006992574257425742,
+      "loss": 2.2673254013061523,
+      "step": 5866
+    },
+    {
+      "epoch": 0.5976138221111004,
+      "grad_norm": 0.1891942322254181,
+      "learning_rate": 0.0006989038189533238,
+      "loss": 2.2457022666931152,
+      "step": 5868
+    },
+    {
+      "epoch": 0.5978175078037081,
+      "grad_norm": 0.12701493501663208,
+      "learning_rate": 0.0006985502121640736,
+      "loss": 2.2249765396118164,
+      "step": 5870
+    },
+    {
+      "epoch": 0.5980211934963159,
+      "grad_norm": 0.12259265035390854,
+      "learning_rate": 0.0006981966053748232,
+      "loss": 2.2566633224487305,
+      "step": 5872
+    },
+    {
+      "epoch": 0.5982248791889235,
+      "grad_norm": 0.12629735469818115,
+      "learning_rate": 0.0006978429985855729,
+      "loss": 2.1290676593780518,
+      "step": 5874
+    },
+    {
+      "epoch": 0.5984285648815313,
+      "grad_norm": 0.11066842079162598,
+      "learning_rate": 0.0006974893917963225,
+      "loss": 2.248239278793335,
+      "step": 5876
+    },
+    {
+      "epoch": 0.598632250574139,
+      "grad_norm": 0.10732977837324142,
+      "learning_rate": 0.0006971357850070722,
+      "loss": 2.036114454269409,
+      "step": 5878
+    },
+    {
+      "epoch": 0.5988359362667468,
+      "grad_norm": 0.12938185036182404,
+      "learning_rate": 0.0006967821782178218,
+      "loss": 2.182767868041992,
+      "step": 5880
+    },
+    {
+      "epoch": 0.5990396219593546,
+      "grad_norm": 0.11534034460783005,
+      "learning_rate": 0.0006964285714285714,
+      "loss": 2.2511093616485596,
+      "step": 5882
+    },
+    {
+      "epoch": 0.5992433076519622,
+      "grad_norm": 0.12999317049980164,
+      "learning_rate": 0.0006960749646393211,
+      "loss": 2.2557802200317383,
+      "step": 5884
+    },
+    {
+      "epoch": 0.59944699334457,
+      "grad_norm": 0.1293525993824005,
+      "learning_rate": 0.0006957213578500707,
+      "loss": 2.1462244987487793,
+      "step": 5886
+    },
+    {
+      "epoch": 0.5996506790371777,
+      "grad_norm": 0.10800858587026596,
+      "learning_rate": 0.0006953677510608204,
+      "loss": 2.091259479522705,
+      "step": 5888
+    },
+    {
+      "epoch": 0.5998543647297855,
+      "grad_norm": 0.11408194154500961,
+      "learning_rate": 0.00069501414427157,
+      "loss": 2.2213294506073,
+      "step": 5890
+    },
+    {
+      "epoch": 0.6000580504223932,
+      "grad_norm": 0.19715900719165802,
+      "learning_rate": 0.0006946605374823198,
+      "loss": 2.130643367767334,
+      "step": 5892
     }
   ],
   "logging_steps": 2,
       "attributes": {}
     }
   },
+  "total_flos": 1.8182562217155625e+18,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null