Upload 13 files

README.md

@@ -0,0 +1,61 @@
+---
+library_name: transformers
+license: mit
+base_model: agentlans/deberta-v3-xsmall-zyda-2
+tags:
+- generated_from_trainer
+model-index:
+- name: deberta-v3-xsmall-zyda-2-quality-rerun
+  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. -->
+
+# deberta-v3-xsmall-zyda-2-quality-rerun
+
+This model is a fine-tuned version of [agentlans/deberta-v3-xsmall-zyda-2](https://huggingface.co/agentlans/deberta-v3-xsmall-zyda-2) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.3140
+- Mse: 0.3140
+
+## 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-05
+- train_batch_size: 64
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- num_epochs: 3.0
+
+### Training results
+
+| Training Loss | Epoch | Step  | Validation Loss | Mse    |
+|:-------------:|:-----:|:-----:|:---------------:|:------:|
+| 0.3569        | 1.0   | 13316 | 0.3436          | 0.3436 |
+| 0.2857        | 2.0   | 26632 | 0.3209          | 0.3209 |
+| 0.2395        | 3.0   | 39948 | 0.3140          | 0.3140 |
+
+
+### Framework versions
+
+- Transformers 4.46.3
+- Pytorch 2.5.1+cu124
+- Datasets 3.1.0
+- Tokenizers 0.20.3

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "[MASK]": 128000
+}

all_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 3.0,
+    "eval_loss": 0.31399768590927124,
+    "eval_mse": 0.31399767168875364,
+    "eval_runtime": 103.6586,
+    "eval_samples": 100000,
+    "eval_samples_per_second": 964.705,
+    "eval_steps_per_second": 120.588,
+    "total_flos": 4.210143005329459e+16,
+    "train_loss": 0.3187301256067702,
+    "train_runtime": 5274.6963,
+    "train_samples": 852162,
+    "train_samples_per_second": 484.67,
+    "train_steps_per_second": 7.574
+}

config.json

@@ -0,0 +1,43 @@
+{
+  "_name_or_path": "agentlans/deberta-v3-xsmall-zyda-2",
+  "architectures": [
+    "DebertaV2ForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "finetuning_task": "text-classification",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 384,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 1536,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "layer_norm_eps": 1e-07,
+  "max_position_embeddings": 512,
+  "max_relative_positions": -1,
+  "model_type": "deberta-v2",
+  "norm_rel_ebd": "layer_norm",
+  "num_attention_heads": 6,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "pooler_dropout": 0,
+  "pooler_hidden_act": "gelu",
+  "pooler_hidden_size": 384,
+  "pos_att_type": [
+    "p2c",
+    "c2p"
+  ],
+  "position_biased_input": false,
+  "position_buckets": 256,
+  "problem_type": "regression",
+  "relative_attention": true,
+  "share_att_key": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.46.3",
+  "type_vocab_size": 0,
+  "vocab_size": 128100
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 3.0,
+    "eval_loss": 0.31399768590927124,
+    "eval_mse": 0.31399767168875364,
+    "eval_runtime": 103.6586,
+    "eval_samples": 100000,
+    "eval_samples_per_second": 964.705,
+    "eval_steps_per_second": 120.588
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9dcf99ae2334c9277a930b2b386ae99b62a9b86b4ac81089dd5e2ca1d624a67
+size 283345892

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

spm.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
+size 2464616

tokenizer_config.json

@@ -0,0 +1,62 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128000": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "[CLS]",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "eos_token": "[SEP]",
+  "mask_token": "[MASK]",
+  "max_length": 1024,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "sp_model_kwargs": {},
+  "split_by_punct": false,
+  "stride": 0,
+  "tokenizer_class": "DebertaV2Tokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "[UNK]",
+  "vocab_type": "spm"
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 3.0,
+    "total_flos": 4.210143005329459e+16,
+    "train_loss": 0.3187301256067702,
+    "train_runtime": 5274.6963,
+    "train_samples": 852162,
+    "train_samples_per_second": 484.67,
+    "train_steps_per_second": 7.574
+}

trainer_state.json

@@ -0,0 +1,622 @@
+{
+  "best_metric": 0.31399768590927124,
+  "best_model_checkpoint": "deberta-v3-xsmall-zyda-2-quality-rerun/checkpoint-39948",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 39948,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.037548813457494744,
+      "grad_norm": 4.403994560241699,
+      "learning_rate": 4.9374186442375094e-05,
+      "loss": 0.6773,
+      "step": 500
+    },
+    {
+      "epoch": 0.07509762691498949,
+      "grad_norm": 3.1282551288604736,
+      "learning_rate": 4.874837288475018e-05,
+      "loss": 0.5374,
+      "step": 1000
+    },
+    {
+      "epoch": 0.11264644037248422,
+      "grad_norm": 3.248645782470703,
+      "learning_rate": 4.812255932712526e-05,
+      "loss": 0.5056,
+      "step": 1500
+    },
+    {
+      "epoch": 0.15019525382997898,
+      "grad_norm": 3.0767080783843994,
+      "learning_rate": 4.749674576950035e-05,
+      "loss": 0.4772,
+      "step": 2000
+    },
+    {
+      "epoch": 0.18774406728747373,
+      "grad_norm": 4.454887866973877,
+      "learning_rate": 4.687093221187544e-05,
+      "loss": 0.4574,
+      "step": 2500
+    },
+    {
+      "epoch": 0.22529288074496845,
+      "grad_norm": 2.398064613342285,
+      "learning_rate": 4.624511865425053e-05,
+      "loss": 0.4508,
+      "step": 3000
+    },
+    {
+      "epoch": 0.2628416942024632,
+      "grad_norm": 3.7262675762176514,
+      "learning_rate": 4.5619305096625615e-05,
+      "loss": 0.432,
+      "step": 3500
+    },
+    {
+      "epoch": 0.30039050765995795,
+      "grad_norm": 2.6357853412628174,
+      "learning_rate": 4.4993491539000706e-05,
+      "loss": 0.4303,
+      "step": 4000
+    },
+    {
+      "epoch": 0.3379393211174527,
+      "grad_norm": 2.8107378482818604,
+      "learning_rate": 4.436767798137579e-05,
+      "loss": 0.4151,
+      "step": 4500
+    },
+    {
+      "epoch": 0.37548813457494745,
+      "grad_norm": 3.1814627647399902,
+      "learning_rate": 4.3741864423750875e-05,
+      "loss": 0.411,
+      "step": 5000
+    },
+    {
+      "epoch": 0.4130369480324422,
+      "grad_norm": 3.0693929195404053,
+      "learning_rate": 4.3116050866125966e-05,
+      "loss": 0.4013,
+      "step": 5500
+    },
+    {
+      "epoch": 0.4505857614899369,
+      "grad_norm": 3.04325008392334,
+      "learning_rate": 4.249023730850105e-05,
+      "loss": 0.4042,
+      "step": 6000
+    },
+    {
+      "epoch": 0.4881345749474317,
+      "grad_norm": 2.3595287799835205,
+      "learning_rate": 4.186442375087614e-05,
+      "loss": 0.395,
+      "step": 6500
+    },
+    {
+      "epoch": 0.5256833884049265,
+      "grad_norm": 3.9787838459014893,
+      "learning_rate": 4.123861019325123e-05,
+      "loss": 0.3969,
+      "step": 7000
+    },
+    {
+      "epoch": 0.5632322018624212,
+      "grad_norm": 5.200424671173096,
+      "learning_rate": 4.061279663562632e-05,
+      "loss": 0.3919,
+      "step": 7500
+    },
+    {
+      "epoch": 0.6007810153199159,
+      "grad_norm": 4.694857120513916,
+      "learning_rate": 3.99869830780014e-05,
+      "loss": 0.3926,
+      "step": 8000
+    },
+    {
+      "epoch": 0.6383298287774106,
+      "grad_norm": 2.551344633102417,
+      "learning_rate": 3.936116952037649e-05,
+      "loss": 0.3815,
+      "step": 8500
+    },
+    {
+      "epoch": 0.6758786422349053,
+      "grad_norm": 4.175814151763916,
+      "learning_rate": 3.873535596275158e-05,
+      "loss": 0.3805,
+      "step": 9000
+    },
+    {
+      "epoch": 0.7134274556924001,
+      "grad_norm": 3.3641836643218994,
+      "learning_rate": 3.810954240512667e-05,
+      "loss": 0.3813,
+      "step": 9500
+    },
+    {
+      "epoch": 0.7509762691498949,
+      "grad_norm": 4.312653064727783,
+      "learning_rate": 3.7483728847501754e-05,
+      "loss": 0.3687,
+      "step": 10000
+    },
+    {
+      "epoch": 0.7885250826073896,
+      "grad_norm": 2.912576675415039,
+      "learning_rate": 3.6857915289876846e-05,
+      "loss": 0.3669,
+      "step": 10500
+    },
+    {
+      "epoch": 0.8260738960648843,
+      "grad_norm": 3.152151346206665,
+      "learning_rate": 3.623210173225193e-05,
+      "loss": 0.3746,
+      "step": 11000
+    },
+    {
+      "epoch": 0.8636227095223791,
+      "grad_norm": 2.863006830215454,
+      "learning_rate": 3.5606288174627015e-05,
+      "loss": 0.37,
+      "step": 11500
+    },
+    {
+      "epoch": 0.9011715229798738,
+      "grad_norm": 2.383753776550293,
+      "learning_rate": 3.4980474617002106e-05,
+      "loss": 0.3675,
+      "step": 12000
+    },
+    {
+      "epoch": 0.9387203364373686,
+      "grad_norm": 2.4308314323425293,
+      "learning_rate": 3.435466105937719e-05,
+      "loss": 0.3607,
+      "step": 12500
+    },
+    {
+      "epoch": 0.9762691498948634,
+      "grad_norm": 3.8357925415039062,
+      "learning_rate": 3.372884750175228e-05,
+      "loss": 0.3569,
+      "step": 13000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.34360167384147644,
+      "eval_mse": 0.34360167908090056,
+      "eval_runtime": 105.793,
+      "eval_samples_per_second": 945.242,
+      "eval_steps_per_second": 118.155,
+      "step": 13316
+    },
+    {
+      "epoch": 1.013817963352358,
+      "grad_norm": 3.0041775703430176,
+      "learning_rate": 3.310303394412737e-05,
+      "loss": 0.3414,
+      "step": 13500
+    },
+    {
+      "epoch": 1.051366776809853,
+      "grad_norm": 3.3583767414093018,
+      "learning_rate": 3.247722038650246e-05,
+      "loss": 0.3027,
+      "step": 14000
+    },
+    {
+      "epoch": 1.0889155902673475,
+      "grad_norm": 4.092809200286865,
+      "learning_rate": 3.185140682887754e-05,
+      "loss": 0.3098,
+      "step": 14500
+    },
+    {
+      "epoch": 1.1264644037248424,
+      "grad_norm": 2.405085802078247,
+      "learning_rate": 3.122559327125263e-05,
+      "loss": 0.3094,
+      "step": 15000
+    },
+    {
+      "epoch": 1.164013217182337,
+      "grad_norm": 2.9946043491363525,
+      "learning_rate": 3.059977971362772e-05,
+      "loss": 0.3054,
+      "step": 15500
+    },
+    {
+      "epoch": 1.2015620306398318,
+      "grad_norm": 2.638746976852417,
+      "learning_rate": 2.9973966156002803e-05,
+      "loss": 0.3053,
+      "step": 16000
+    },
+    {
+      "epoch": 1.2391108440973264,
+      "grad_norm": 2.7500743865966797,
+      "learning_rate": 2.9348152598377894e-05,
+      "loss": 0.3027,
+      "step": 16500
+    },
+    {
+      "epoch": 1.2766596575548212,
+      "grad_norm": 2.1603994369506836,
+      "learning_rate": 2.8722339040752982e-05,
+      "loss": 0.2978,
+      "step": 17000
+    },
+    {
+      "epoch": 1.314208471012316,
+      "grad_norm": 3.147937774658203,
+      "learning_rate": 2.8096525483128067e-05,
+      "loss": 0.3065,
+      "step": 17500
+    },
+    {
+      "epoch": 1.3517572844698107,
+      "grad_norm": 2.8613197803497314,
+      "learning_rate": 2.7470711925503158e-05,
+      "loss": 0.3034,
+      "step": 18000
+    },
+    {
+      "epoch": 1.3893060979273055,
+      "grad_norm": 2.1770453453063965,
+      "learning_rate": 2.684489836787824e-05,
+      "loss": 0.296,
+      "step": 18500
+    },
+    {
+      "epoch": 1.4268549113848001,
+      "grad_norm": 3.3030712604522705,
+      "learning_rate": 2.621908481025333e-05,
+      "loss": 0.2953,
+      "step": 19000
+    },
+    {
+      "epoch": 1.464403724842295,
+      "grad_norm": 2.322561025619507,
+      "learning_rate": 2.559327125262842e-05,
+      "loss": 0.3018,
+      "step": 19500
+    },
+    {
+      "epoch": 1.5019525382997898,
+      "grad_norm": 3.038954496383667,
+      "learning_rate": 2.4967457695003503e-05,
+      "loss": 0.2969,
+      "step": 20000
+    },
+    {
+      "epoch": 1.5395013517572844,
+      "grad_norm": 2.606443405151367,
+      "learning_rate": 2.4341644137378594e-05,
+      "loss": 0.2901,
+      "step": 20500
+    },
+    {
+      "epoch": 1.5770501652147793,
+      "grad_norm": 2.5407485961914062,
+      "learning_rate": 2.3715830579753682e-05,
+      "loss": 0.2962,
+      "step": 21000
+    },
+    {
+      "epoch": 1.6145989786722739,
+      "grad_norm": 2.8466265201568604,
+      "learning_rate": 2.3090017022128767e-05,
+      "loss": 0.2967,
+      "step": 21500
+    },
+    {
+      "epoch": 1.6521477921297687,
+      "grad_norm": 3.01155161857605,
+      "learning_rate": 2.2464203464503855e-05,
+      "loss": 0.294,
+      "step": 22000
+    },
+    {
+      "epoch": 1.6896966055872635,
+      "grad_norm": 3.2597897052764893,
+      "learning_rate": 2.1838389906878946e-05,
+      "loss": 0.2938,
+      "step": 22500
+    },
+    {
+      "epoch": 1.7272454190447581,
+      "grad_norm": 2.202085256576538,
+      "learning_rate": 2.121257634925403e-05,
+      "loss": 0.2852,
+      "step": 23000
+    },
+    {
+      "epoch": 1.764794232502253,
+      "grad_norm": 2.2789671421051025,
+      "learning_rate": 2.058676279162912e-05,
+      "loss": 0.2927,
+      "step": 23500
+    },
+    {
+      "epoch": 1.8023430459597476,
+      "grad_norm": 2.1892921924591064,
+      "learning_rate": 1.9960949234004207e-05,
+      "loss": 0.2912,
+      "step": 24000
+    },
+    {
+      "epoch": 1.8398918594172424,
+      "grad_norm": 2.7529070377349854,
+      "learning_rate": 1.9335135676379295e-05,
+      "loss": 0.2886,
+      "step": 24500
+    },
+    {
+      "epoch": 1.8774406728747373,
+      "grad_norm": 2.7882585525512695,
+      "learning_rate": 1.8709322118754383e-05,
+      "loss": 0.2933,
+      "step": 25000
+    },
+    {
+      "epoch": 1.9149894863322319,
+      "grad_norm": 2.5822184085845947,
+      "learning_rate": 1.808350856112947e-05,
+      "loss": 0.2883,
+      "step": 25500
+    },
+    {
+      "epoch": 1.9525382997897265,
+      "grad_norm": 2.326474666595459,
+      "learning_rate": 1.7457695003504555e-05,
+      "loss": 0.2887,
+      "step": 26000
+    },
+    {
+      "epoch": 1.9900871132472213,
+      "grad_norm": 3.619825601577759,
+      "learning_rate": 1.6831881445879643e-05,
+      "loss": 0.2857,
+      "step": 26500
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.3208652436733246,
+      "eval_mse": 0.3208652417918357,
+      "eval_runtime": 108.1625,
+      "eval_samples_per_second": 924.535,
+      "eval_steps_per_second": 115.567,
+      "step": 26632
+    },
+    {
+      "epoch": 2.027635926704716,
+      "grad_norm": 3.537344217300415,
+      "learning_rate": 1.620606788825473e-05,
+      "loss": 0.2578,
+      "step": 27000
+    },
+    {
+      "epoch": 2.065184740162211,
+      "grad_norm": 2.6542530059814453,
+      "learning_rate": 1.558025433062982e-05,
+      "loss": 0.2438,
+      "step": 27500
+    },
+    {
+      "epoch": 2.102733553619706,
+      "grad_norm": 3.0753347873687744,
+      "learning_rate": 1.4954440773004907e-05,
+      "loss": 0.2493,
+      "step": 28000
+    },
+    {
+      "epoch": 2.1402823670772,
+      "grad_norm": 2.988065004348755,
+      "learning_rate": 1.4328627215379995e-05,
+      "loss": 0.2484,
+      "step": 28500
+    },
+    {
+      "epoch": 2.177831180534695,
+      "grad_norm": 2.041884422302246,
+      "learning_rate": 1.3702813657755081e-05,
+      "loss": 0.2509,
+      "step": 29000
+    },
+    {
+      "epoch": 2.21537999399219,
+      "grad_norm": 3.0710532665252686,
+      "learning_rate": 1.307700010013017e-05,
+      "loss": 0.2471,
+      "step": 29500
+    },
+    {
+      "epoch": 2.2529288074496847,
+      "grad_norm": 2.620396852493286,
+      "learning_rate": 1.2451186542505257e-05,
+      "loss": 0.245,
+      "step": 30000
+    },
+    {
+      "epoch": 2.290477620907179,
+      "grad_norm": 3.103252410888672,
+      "learning_rate": 1.1825372984880345e-05,
+      "loss": 0.2468,
+      "step": 30500
+    },
+    {
+      "epoch": 2.328026434364674,
+      "grad_norm": 2.4032323360443115,
+      "learning_rate": 1.1199559427255433e-05,
+      "loss": 0.2441,
+      "step": 31000
+    },
+    {
+      "epoch": 2.3655752478221688,
+      "grad_norm": 3.1325552463531494,
+      "learning_rate": 1.057374586963052e-05,
+      "loss": 0.2431,
+      "step": 31500
+    },
+    {
+      "epoch": 2.4031240612796636,
+      "grad_norm": 3.0277721881866455,
+      "learning_rate": 9.947932312005607e-06,
+      "loss": 0.2414,
+      "step": 32000
+    },
+    {
+      "epoch": 2.4406728747371584,
+      "grad_norm": 2.5161995887756348,
+      "learning_rate": 9.322118754380697e-06,
+      "loss": 0.2412,
+      "step": 32500
+    },
+    {
+      "epoch": 2.478221688194653,
+      "grad_norm": 1.7039533853530884,
+      "learning_rate": 8.696305196755783e-06,
+      "loss": 0.2434,
+      "step": 33000
+    },
+    {
+      "epoch": 2.5157705016521477,
+      "grad_norm": 2.513314723968506,
+      "learning_rate": 8.07049163913087e-06,
+      "loss": 0.2438,
+      "step": 33500
+    },
+    {
+      "epoch": 2.5533193151096425,
+      "grad_norm": 2.314403772354126,
+      "learning_rate": 7.444678081505959e-06,
+      "loss": 0.2441,
+      "step": 34000
+    },
+    {
+      "epoch": 2.5908681285671373,
+      "grad_norm": 2.855802536010742,
+      "learning_rate": 6.818864523881045e-06,
+      "loss": 0.2408,
+      "step": 34500
+    },
+    {
+      "epoch": 2.628416942024632,
+      "grad_norm": 2.636925458908081,
+      "learning_rate": 6.193050966256133e-06,
+      "loss": 0.2433,
+      "step": 35000
+    },
+    {
+      "epoch": 2.6659657554821266,
+      "grad_norm": 2.4678878784179688,
+      "learning_rate": 5.567237408631221e-06,
+      "loss": 0.2367,
+      "step": 35500
+    },
+    {
+      "epoch": 2.7035145689396214,
+      "grad_norm": 2.2376275062561035,
+      "learning_rate": 4.941423851006309e-06,
+      "loss": 0.2353,
+      "step": 36000
+    },
+    {
+      "epoch": 2.741063382397116,
+      "grad_norm": 2.5792624950408936,
+      "learning_rate": 4.315610293381396e-06,
+      "loss": 0.2402,
+      "step": 36500
+    },
+    {
+      "epoch": 2.778612195854611,
+      "grad_norm": 3.4142560958862305,
+      "learning_rate": 3.6897967357564838e-06,
+      "loss": 0.2345,
+      "step": 37000
+    },
+    {
+      "epoch": 2.816161009312106,
+      "grad_norm": 2.2159926891326904,
+      "learning_rate": 3.063983178131571e-06,
+      "loss": 0.2378,
+      "step": 37500
+    },
+    {
+      "epoch": 2.8537098227696003,
+      "grad_norm": 2.577420711517334,
+      "learning_rate": 2.438169620506659e-06,
+      "loss": 0.233,
+      "step": 38000
+    },
+    {
+      "epoch": 2.891258636227095,
+      "grad_norm": 2.7511062622070312,
+      "learning_rate": 1.8123560628817465e-06,
+      "loss": 0.2374,
+      "step": 38500
+    },
+    {
+      "epoch": 2.92880744968459,
+      "grad_norm": 2.820404529571533,
+      "learning_rate": 1.186542505256834e-06,
+      "loss": 0.2413,
+      "step": 39000
+    },
+    {
+      "epoch": 2.966356263142085,
+      "grad_norm": 2.4552481174468994,
+      "learning_rate": 5.607289476319215e-07,
+      "loss": 0.2395,
+      "step": 39500
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.31399768590927124,
+      "eval_mse": 0.31399767168875364,
+      "eval_runtime": 104.865,
+      "eval_samples_per_second": 953.607,
+      "eval_steps_per_second": 119.201,
+      "step": 39948
+    },
+    {
+      "epoch": 3.0,
+      "step": 39948,
+      "total_flos": 4.210143005329459e+16,
+      "train_loss": 0.3187301256067702,
+      "train_runtime": 5274.6963,
+      "train_samples_per_second": 484.67,
+      "train_steps_per_second": 7.574
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 39948,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4.210143005329459e+16,
+  "train_batch_size": 64,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9064ce0bea9b811acb2ea615c64dbf8e938c12cde30e373e640b30639802ea9b
+size 5368