Model save

README.md

@@ -0,0 +1,86 @@
+---
+license: apache-2.0
+base_model: hZzy/qwen2.5-0.5b-sft-news-IFT
+tags:
+- trl
+- expo
+- generated_from_trainer
+model-index:
+- name: qwen2.5-0.5b-expo-DPO-ES-TRY
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/zhiyuzha-university-of-florida/huggingface/runs/gcfd4lf7)
+# qwen2.5-0.5b-expo-DPO-ES-TRY
+
+This model is a fine-tuned version of [hZzy/qwen2.5-0.5b-sft-news-IFT](https://huggingface.co/hZzy/qwen2.5-0.5b-sft-news-IFT) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.6965
+- Logps: -103.5456
+- Logits: -2.4456
+- Objective: 0.7050
+- Dpo Loss: 0.7050
+- Regularize: 0.7050
+- Ranking Simple: 0.5735
+- Ranking Idealized: 0.6046
+- Ranking Idealized Expo: 0.5280
+- Dpo Wo Beta: -3.2166
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-06
+- train_batch_size: 2
+- eval_batch_size: 2
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 6
+- gradient_accumulation_steps: 6
+- total_train_batch_size: 72
+- total_eval_batch_size: 12
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 3
+
+### Training results
+
+| Training Loss | Epoch  | Step | Dpo Loss | Dpo Wo Beta | Logits  | Logps     | Validation Loss | Objective | Ranking Idealized | Ranking Idealized Expo | Ranking Simple | Regularize |
+|:-------------:|:------:|:----:|:--------:|:-----------:|:-------:|:---------:|:---------------:|:---------:|:-----------------:|:----------------------:|:--------------:|:----------:|
+| 0.6857        | 0.0709 | 50   | 0.6927   | -1.2807     | -1.9606 | -88.9841  | 0.6914          | 0.6927    | 0.6046            | 0.5280                 | 0.5362         | 0.6927     |
+| 0.6524        | 0.1417 | 100  | 0.7010   | -1.8911     | -2.0579 | -98.6358  | 0.6922          | 0.7010    | 0.6046            | 0.5280                 | 0.5269         | 0.7010     |
+| 0.6123        | 0.2126 | 150  | 0.7015   | -2.1166     | -1.9033 | -102.8927 | 0.6967          | 0.7015    | 0.6046            | 0.5280                 | 0.5280         | 0.7015     |
+| 0.5779        | 0.2834 | 200  | 0.6816   | -2.1417     | -2.0716 | -106.4944 | 0.6794          | 0.6816    | 0.6046            | 0.5280                 | 0.5507         | 0.6816     |
+| 0.5709        | 0.3543 | 250  | 0.6817   | -2.2676     | -2.2470 | -87.7326  | 0.6883          | 0.6817    | 0.6046            | 0.5280                 | 0.5424         | 0.6817     |
+| 0.5563        | 0.4251 | 300  | 0.6619   | -2.3796     | -2.2697 | -89.5089  | 0.6811          | 0.6619    | 0.6046            | 0.5280                 | 0.5735         | 0.6619     |
+| 0.5321        | 0.4960 | 350  | 0.6773   | -2.6295     | -2.3683 | -99.0927  | 0.6926          | 0.6773    | 0.6046            | 0.5280                 | 0.5735         | 0.6773     |
+| 0.4963        | 0.5668 | 400  | 0.6836   | -2.6913     | -2.2508 | -106.7073 | 0.6914          | 0.6836    | 0.6046            | 0.5280                 | 0.5673         | 0.6836     |
+| 0.4745        | 0.6377 | 450  | 0.6938   | -105.8669   | -2.2347 | 0.6815    | 0.6815          | 0.6815    | 0.5631            | 0.6046                 | 0.5280         | -2.6738    |
+| 0.4867        | 0.7085 | 500  | 0.7040   | -105.1848   | -2.2182 | 0.6995    | 0.6995          | 0.6995    | 0.5507            | 0.6046                 | 0.5280         | -2.7257    |
+| 0.4582        | 0.7794 | 550  | 0.6995   | -102.6643   | -2.3855 | 0.7027    | 0.7027          | 0.7027    | 0.5683            | 0.6046                 | 0.5280         | -3.1023    |
+| 0.4339        | 0.8503 | 600  | 0.6965   | -103.5456   | -2.4456 | 0.7050    | 0.7050          | 0.7050    | 0.5735            | 0.6046                 | 0.5280         | -3.2166    |
+
+
+### Framework versions
+
+- Transformers 4.42.0
+- Pytorch 2.3.0+cu121
+- Datasets 2.19.1
+- Tokenizers 0.19.1

all_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 0.8502598016060463,
+    "total_flos": 0.0,
+    "train_loss": 0.15444423039754232,
+    "train_runtime": 3628.8607,
+    "train_samples": 50802,
+    "train_samples_per_second": 41.998,
+    "train_steps_per_second": 0.583
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "bos_token_id": 151644,
+  "eos_token_id": 151645,
+  "max_new_tokens": 2048,
+  "pad_token_id": 151645,
+  "transformers_version": "4.42.0"
+}

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f9f67c930cb079817a30b62a9d5ce9955a9ce2bfd805f44199310b726da82e8
+oid sha256:5891934e598bd576da95bb0536f8170134dd4e331ed360f27dd151d750c7dfe4
 size 1975192208

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 0.8502598016060463,
+    "total_flos": 0.0,
+    "train_loss": 0.15444423039754232,
+    "train_runtime": 3628.8607,
+    "train_samples": 50802,
+    "train_samples_per_second": 41.998,
+    "train_steps_per_second": 0.583
+}

trainer_state.json

@@ -0,0 +1,463 @@
+{
+  "best_metric": 0.5734989643096924,
+  "best_model_checkpoint": "./qwen2.5-0.5b/qwen2.5-0.5b-expo-DPO-ES-TRY/checkpoint-300",
+  "epoch": 0.8502598016060463,
+  "eval_steps": 50,
+  "global_step": 600,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "dpo_loss": 0.6931471824645996,
+      "dpo_wo_beta": -0.6931471824645996,
+      "epoch": 0.0014170996693434106,
+      "grad_norm": 25.66138500619404,
+      "learning_rate": 2.358490566037736e-08,
+      "logits": -1.7146095037460327,
+      "logps": -79.01810455322266,
+      "loss": 0.6931,
+      "objective": 0.6931471824645996,
+      "ranking_idealized": 0.3333333432674408,
+      "ranking_idealized_expo": 0.3333333432674408,
+      "ranking_simple": 0.3333333432674408,
+      "regularize": 0.6931471824645996,
+      "step": 1
+    },
+    {
+      "dpo_loss": 0.6873584985733032,
+      "dpo_wo_beta": -0.8693115711212158,
+      "epoch": 0.07085498346717052,
+      "grad_norm": 25.93169363980804,
+      "learning_rate": 1.179245283018868e-06,
+      "logits": -1.890508770942688,
+      "logps": -82.390869140625,
+      "loss": 0.6857,
+      "objective": 0.6873584985733032,
+      "ranking_idealized": 0.6258503198623657,
+      "ranking_idealized_expo": 0.5408163070678711,
+      "ranking_simple": 0.5408163070678711,
+      "regularize": 0.6873584985733032,
+      "step": 50
+    },
+    {
+      "epoch": 0.07085498346717052,
+      "eval_dpo_loss": 0.6927401423454285,
+      "eval_dpo_wo_beta": -1.280670404434204,
+      "eval_logits": -1.960647463798523,
+      "eval_logps": -88.98406219482422,
+      "eval_loss": 0.6913570761680603,
+      "eval_objective": 0.6927401423454285,
+      "eval_ranking_idealized": 0.6045548915863037,
+      "eval_ranking_idealized_expo": 0.5279502868652344,
+      "eval_ranking_simple": 0.5362318754196167,
+      "eval_regularize": 0.6927401423454285,
+      "eval_runtime": 318.1168,
+      "eval_samples_per_second": 18.201,
+      "eval_steps_per_second": 1.518,
+      "step": 50
+    },
+    {
+      "dpo_loss": 0.6656978130340576,
+      "dpo_wo_beta": -1.517911434173584,
+      "epoch": 0.14170996693434104,
+      "grad_norm": 29.18536320021953,
+      "learning_rate": 2.358490566037736e-06,
+      "logits": -2.088792085647583,
+      "logps": -82.19146728515625,
+      "loss": 0.6524,
+      "objective": 0.6656978130340576,
+      "ranking_idealized": 0.5950000286102295,
+      "ranking_idealized_expo": 0.5149999856948853,
+      "ranking_simple": 0.5233333110809326,
+      "regularize": 0.6656978130340576,
+      "step": 100
+    },
+    {
+      "epoch": 0.14170996693434104,
+      "eval_dpo_loss": 0.7010491490364075,
+      "eval_dpo_wo_beta": -1.8911339044570923,
+      "eval_logits": -2.0578620433807373,
+      "eval_logps": -98.63578033447266,
+      "eval_loss": 0.6921781897544861,
+      "eval_objective": 0.7010491490364075,
+      "eval_ranking_idealized": 0.6045548915863037,
+      "eval_ranking_idealized_expo": 0.5279502868652344,
+      "eval_ranking_simple": 0.5269151329994202,
+      "eval_regularize": 0.7010491490364075,
+      "eval_runtime": 317.6312,
+      "eval_samples_per_second": 18.229,
+      "eval_steps_per_second": 1.521,
+      "step": 100
+    },
+    {
+      "dpo_loss": 0.6302288770675659,
+      "dpo_wo_beta": -1.9832934141159058,
+      "epoch": 0.21256495040151158,
+      "grad_norm": 31.92092339525771,
+      "learning_rate": 3.5377358490566038e-06,
+      "logits": -2.047361135482788,
+      "logps": -90.97752380371094,
+      "loss": 0.6123,
+      "objective": 0.6302288770675659,
+      "ranking_idealized": 0.6050000190734863,
+      "ranking_idealized_expo": 0.528333306312561,
+      "ranking_simple": 0.5799999833106995,
+      "regularize": 0.6302288770675659,
+      "step": 150
+    },
+    {
+      "epoch": 0.21256495040151158,
+      "eval_dpo_loss": 0.7015214562416077,
+      "eval_dpo_wo_beta": -2.1165764331817627,
+      "eval_logits": -1.9032589197158813,
+      "eval_logps": -102.8927001953125,
+      "eval_loss": 0.6967350840568542,
+      "eval_objective": 0.7015214562416077,
+      "eval_ranking_idealized": 0.6045548915863037,
+      "eval_ranking_idealized_expo": 0.5279502868652344,
+      "eval_ranking_simple": 0.5279502868652344,
+      "eval_regularize": 0.7015214562416077,
+      "eval_runtime": 317.4305,
+      "eval_samples_per_second": 18.24,
+      "eval_steps_per_second": 1.522,
+      "step": 150
+    },
+    {
+      "dpo_loss": 0.5571741461753845,
+      "dpo_wo_beta": -1.7987542152404785,
+      "epoch": 0.2834199338686821,
+      "grad_norm": 22.667783186241508,
+      "learning_rate": 4.716981132075472e-06,
+      "logits": -2.1097896099090576,
+      "logps": -93.05426025390625,
+      "loss": 0.5779,
+      "objective": 0.5571741461753845,
+      "ranking_idealized": 0.6333333253860474,
+      "ranking_idealized_expo": 0.5433333516120911,
+      "ranking_simple": 0.6449999809265137,
+      "regularize": 0.5571741461753845,
+      "step": 200
+    },
+    {
+      "epoch": 0.2834199338686821,
+      "eval_dpo_loss": 0.6816009283065796,
+      "eval_dpo_wo_beta": -2.1417369842529297,
+      "eval_logits": -2.071585178375244,
+      "eval_logps": -106.49442291259766,
+      "eval_loss": 0.6793810129165649,
+      "eval_objective": 0.6816009283065796,
+      "eval_ranking_idealized": 0.6045548915863037,
+      "eval_ranking_idealized_expo": 0.5279502868652344,
+      "eval_ranking_simple": 0.5507246255874634,
+      "eval_regularize": 0.6816009283065796,
+      "eval_runtime": 316.4091,
+      "eval_samples_per_second": 18.299,
+      "eval_steps_per_second": 1.527,
+      "step": 200
+    },
+    {
+      "dpo_loss": 0.5780055522918701,
+      "dpo_wo_beta": -2.330664873123169,
+      "epoch": 0.35427491733585265,
+      "grad_norm": 19.831646672236253,
+      "learning_rate": 4.995082357614404e-06,
+      "logits": -2.255446434020996,
+      "logps": -94.9359130859375,
+      "loss": 0.5709,
+      "objective": 0.5780055522918701,
+      "ranking_idealized": 0.5699999928474426,
+      "ranking_idealized_expo": 0.4833333194255829,
+      "ranking_simple": 0.6083333492279053,
+      "regularize": 0.5780055522918701,
+      "step": 250
+    },
+    {
+      "epoch": 0.35427491733585265,
+      "eval_dpo_loss": 0.6816768646240234,
+      "eval_dpo_wo_beta": -2.267601728439331,
+      "eval_logits": -2.246999740600586,
+      "eval_logps": -87.73257446289062,
+      "eval_loss": 0.6882591843605042,
+      "eval_objective": 0.6816768646240234,
+      "eval_ranking_idealized": 0.6045548915863037,
+      "eval_ranking_idealized_expo": 0.5279502868652344,
+      "eval_ranking_simple": 0.542443037033081,
+      "eval_regularize": 0.6816768646240234,
+      "eval_runtime": 316.123,
+      "eval_samples_per_second": 18.316,
+      "eval_steps_per_second": 1.528,
+      "step": 250
+    },
+    {
+      "dpo_loss": 0.5427210330963135,
+      "dpo_wo_beta": -2.1861753463745117,
+      "epoch": 0.42512990080302315,
+      "grad_norm": 27.500670384351913,
+      "learning_rate": 4.973664984850435e-06,
+      "logits": -2.136077404022217,
+      "logps": -81.2485122680664,
+      "loss": 0.5563,
+      "objective": 0.5427210330963135,
+      "ranking_idealized": 0.6299999952316284,
+      "ranking_idealized_expo": 0.5649999976158142,
+      "ranking_simple": 0.6583333611488342,
+      "regularize": 0.5427210330963135,
+      "step": 300
+    },
+    {
+      "epoch": 0.42512990080302315,
+      "eval_dpo_loss": 0.6618562340736389,
+      "eval_dpo_wo_beta": -2.3796472549438477,
+      "eval_logits": -2.269749641418457,
+      "eval_logps": -89.50890350341797,
+      "eval_loss": 0.6810693740844727,
+      "eval_objective": 0.6618562340736389,
+      "eval_ranking_idealized": 0.6045548915863037,
+      "eval_ranking_idealized_expo": 0.5279502868652344,
+      "eval_ranking_simple": 0.5734989643096924,
+      "eval_regularize": 0.6618562340736389,
+      "eval_runtime": 319.8742,
+      "eval_samples_per_second": 18.101,
+      "eval_steps_per_second": 1.51,
+      "step": 300
+    },
+    {
+      "dpo_loss": 0.5661785006523132,
+      "dpo_wo_beta": -2.481991767883301,
+      "epoch": 0.49598488427019366,
+      "grad_norm": 19.802376166923445,
+      "learning_rate": 4.9354031766005005e-06,
+      "logits": -2.372645616531372,
+      "logps": -87.0498046875,
+      "loss": 0.5321,
+      "objective": 0.5661785006523132,
+      "ranking_idealized": 0.6016666889190674,
+      "ranking_idealized_expo": 0.5233333110809326,
+      "ranking_simple": 0.6499999761581421,
+      "regularize": 0.5661785006523132,
+      "step": 350
+    },
+    {
+      "epoch": 0.49598488427019366,
+      "eval_dpo_loss": 0.6773233413696289,
+      "eval_dpo_wo_beta": -2.6295416355133057,
+      "eval_logits": -2.3682754039764404,
+      "eval_logps": -99.09272766113281,
+      "eval_loss": 0.6925813555717468,
+      "eval_objective": 0.6773233413696289,
+      "eval_ranking_idealized": 0.6045548915863037,
+      "eval_ranking_idealized_expo": 0.5279502868652344,
+      "eval_ranking_simple": 0.5734989643096924,
+      "eval_regularize": 0.6773233413696289,
+      "eval_runtime": 316.8112,
+      "eval_samples_per_second": 18.276,
+      "eval_steps_per_second": 1.525,
+      "step": 350
+    },
+    {
+      "dpo_loss": 0.5010849237442017,
+      "dpo_wo_beta": -2.259007453918457,
+      "epoch": 0.5668398677373642,
+      "grad_norm": 15.355707906669174,
+      "learning_rate": 4.880557476860893e-06,
+      "logits": -2.343498468399048,
+      "logps": -100.16142272949219,
+      "loss": 0.4963,
+      "objective": 0.5010849237442017,
+      "ranking_idealized": 0.6200000047683716,
+      "ranking_idealized_expo": 0.5199999809265137,
+      "ranking_simple": 0.6883333325386047,
+      "regularize": 0.5010849237442017,
+      "step": 400
+    },
+    {
+      "epoch": 0.5668398677373642,
+      "eval_dpo_loss": 0.6835893392562866,
+      "eval_dpo_wo_beta": -2.691314697265625,
+      "eval_logits": -2.250782012939453,
+      "eval_logps": -106.707275390625,
+      "eval_loss": 0.6914249062538147,
+      "eval_objective": 0.6835893392562866,
+      "eval_ranking_idealized": 0.6045548915863037,
+      "eval_ranking_idealized_expo": 0.5279502868652344,
+      "eval_ranking_simple": 0.567287802696228,
+      "eval_regularize": 0.6835893392562866,
+      "eval_runtime": 320.5789,
+      "eval_samples_per_second": 18.061,
+      "eval_steps_per_second": 1.507,
+      "step": 400
+    },
+    {
+      "dpo_loss": 0.47148290276527405,
+      "dpo_wo_beta": -2.062403678894043,
+      "epoch": 0.6376948512045347,
+      "grad_norm": 19.132752913050712,
+      "learning_rate": 4.80950135772933e-06,
+      "logits": -2.2268483638763428,
+      "logps": -102.33979034423828,
+      "loss": 0.4745,
+      "objective": 0.47148290276527405,
+      "ranking_idealized": 0.5916666388511658,
+      "ranking_idealized_expo": 0.4933333396911621,
+      "ranking_simple": 0.675000011920929,
+      "regularize": 0.47148290276527405,
+      "step": 450
+    },
+    {
+      "epoch": 0.6376948512045347,
+      "eval_dpo_loss": 0.681454062461853,
+      "eval_dpo_wo_beta": -2.673811912536621,
+      "eval_logits": -2.2347095012664795,
+      "eval_logps": -105.86691284179688,
+      "eval_loss": 0.6937749981880188,
+      "eval_objective": 0.681454062461853,
+      "eval_ranking_idealized": 0.6045548915863037,
+      "eval_ranking_idealized_expo": 0.5279502868652344,
+      "eval_ranking_simple": 0.5631470084190369,
+      "eval_regularize": 0.681454062461853,
+      "eval_runtime": 319.8507,
+      "eval_samples_per_second": 18.102,
+      "eval_steps_per_second": 1.51,
+      "step": 450
+    },
+    {
+      "dpo_loss": 0.4877893626689911,
+      "dpo_wo_beta": -2.4107022285461426,
+      "epoch": 0.7085498346717053,
+      "grad_norm": 18.950528232263615,
+      "learning_rate": 4.72271867624463e-06,
+      "logits": -2.197690963745117,
+      "logps": -101.995361328125,
+      "loss": 0.4867,
+      "objective": 0.4877893626689911,
+      "ranking_idealized": 0.5933333039283752,
+      "ranking_idealized_expo": 0.5216666460037231,
+      "ranking_simple": 0.699999988079071,
+      "regularize": 0.4877893626689911,
+      "step": 500
+    },
+    {
+      "epoch": 0.7085498346717053,
+      "eval_dpo_loss": 0.6994954347610474,
+      "eval_dpo_wo_beta": -2.7257001399993896,
+      "eval_logits": -2.2181758880615234,
+      "eval_logps": -105.1847915649414,
+      "eval_loss": 0.7040360569953918,
+      "eval_objective": 0.6994954347610474,
+      "eval_ranking_idealized": 0.6045548915863037,
+      "eval_ranking_idealized_expo": 0.5279502868652344,
+      "eval_ranking_simple": 0.5507246255874634,
+      "eval_regularize": 0.6994954347610474,
+      "eval_runtime": 315.9927,
+      "eval_samples_per_second": 18.323,
+      "eval_steps_per_second": 1.529,
+      "step": 500
+    },
+    {
+      "dpo_loss": 0.4837046265602112,
+      "dpo_wo_beta": -2.136967897415161,
+      "epoch": 0.7794048181388757,
+      "grad_norm": 17.007084301353213,
+      "learning_rate": 4.620800379559508e-06,
+      "logits": -2.328810214996338,
+      "logps": -102.86935424804688,
+      "loss": 0.4582,
+      "objective": 0.4837046265602112,
+      "ranking_idealized": 0.5716666579246521,
+      "ranking_idealized_expo": 0.47833332419395447,
+      "ranking_simple": 0.6866666674613953,
+      "regularize": 0.4837046265602112,
+      "step": 550
+    },
+    {
+      "epoch": 0.7794048181388757,
+      "eval_dpo_loss": 0.7027432918548584,
+      "eval_dpo_wo_beta": -3.1023459434509277,
+      "eval_logits": -2.3854899406433105,
+      "eval_logps": -102.664306640625,
+      "eval_loss": 0.6995241045951843,
+      "eval_objective": 0.7027432918548584,
+      "eval_ranking_idealized": 0.6045548915863037,
+      "eval_ranking_idealized_expo": 0.5279502868652344,
+      "eval_ranking_simple": 0.5683229565620422,
+      "eval_regularize": 0.7027432918548584,
+      "eval_runtime": 317.401,
+      "eval_samples_per_second": 18.242,
+      "eval_steps_per_second": 1.522,
+      "step": 550
+    },
+    {
+      "dpo_loss": 0.42498964071273804,
+      "dpo_wo_beta": -1.8326289653778076,
+      "epoch": 0.8502598016060463,
+      "grad_norm": 15.283086339392508,
+      "learning_rate": 4.504440480882651e-06,
+      "logits": -2.4975786209106445,
+      "logps": -99.132568359375,
+      "loss": 0.4339,
+      "objective": 0.42498964071273804,
+      "ranking_idealized": 0.5350000262260437,
+      "ranking_idealized_expo": 0.4749999940395355,
+      "ranking_simple": 0.7083333134651184,
+      "regularize": 0.42498964071273804,
+      "step": 600
+    },
+    {
+      "epoch": 0.8502598016060463,
+      "eval_dpo_loss": 0.7050178647041321,
+      "eval_dpo_wo_beta": -3.216639995574951,
+      "eval_logits": -2.445580005645752,
+      "eval_logps": -103.54557037353516,
+      "eval_loss": 0.6964531540870667,
+      "eval_objective": 0.7050178647041321,
+      "eval_ranking_idealized": 0.6045548915863037,
+      "eval_ranking_idealized_expo": 0.5279502868652344,
+      "eval_ranking_simple": 0.5734989643096924,
+      "eval_regularize": 0.7050178647041321,
+      "eval_runtime": 317.5725,
+      "eval_samples_per_second": 18.232,
+      "eval_steps_per_second": 1.521,
+      "step": 600
+    },
+    {
+      "epoch": 0.8502598016060463,
+      "step": 600,
+      "total_flos": 0.0,
+      "train_loss": 0.15444423039754232,
+      "train_runtime": 3628.8607,
+      "train_samples_per_second": 41.998,
+      "train_steps_per_second": 0.583
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 2115,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 50,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 4,
+        "early_stopping_threshold": 0.0
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 0
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}