Upload folder using huggingface_hub

20_128_e3_3e-5/.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

20_128_e3_3e-5/README.md

@@ -0,0 +1,63 @@
+---
+library_name: peft
+license: apache-2.0
+base_model: ibm-granite/granite-3.3-8b-base
+tags:
+- alignment-handbook
+- generated_from_trainer
+datasets:
+- data/knowledge_lora_training_data_1000
+model-index:
+- name: 20_128_e3_3e-5
+  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. -->
+
+# 20_128_e3_3e-5
+
+This model is a fine-tuned version of [ibm-granite/granite-3.3-8b-base](https://huggingface.co/ibm-granite/granite-3.3-8b-base) on the data/knowledge_lora_training_data_1000 dataset.
+
+## 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: 3e-05
+- train_batch_size: 2
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 8
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 32
+- total_eval_batch_size: 64
+- optimizer: Use adamw_torch with betas=(0.9,0.95) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.05
+- num_epochs: 3.0
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.15.2
+- Transformers 4.52.4
+- Pytorch 2.7.0+cu126
+- Datasets 3.6.0
+- Tokenizers 0.21.2

20_128_e3_3e-5/adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "ibm-granite/granite-3.3-8b-base",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 256,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 128,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "v_proj",
+    "up_proj",
+    "gate_proj",
+    "o_proj",
+    "down_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

20_128_e3_3e-5/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:688a2d52ed12b61dcac3158c66c202b3b9228b0a1ce238817e65ea4c2b625aca
+size 791751704

20_128_e3_3e-5/all_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 3.0,
+    "total_flos": 7.451297465719849e+17,
+    "train_loss": 0.5084822381997586,
+    "train_runtime": 374.6048,
+    "train_samples": 5847,
+    "train_samples_per_second": 46.825,
+    "train_steps_per_second": 1.466
+}

20_128_e3_3e-5/config.json

@@ -0,0 +1,32 @@
+{
+  "architectures": [
+    "GraniteForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0,
+  "attention_multiplier": 0.0078125,
+  "bos_token_id": 0,
+  "embedding_multiplier": 12.0,
+  "eos_token_id": 0,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 12800,
+  "logits_scaling": 16.0,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "granite",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 8,
+  "pad_token_id": 0,
+  "residual_multiplier": 0.22,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000000.0,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.52.4",
+  "use_cache": true,
+  "vocab_size": 49152
+}

20_128_e3_3e-5/special_tokens_map.json

@@ -0,0 +1,45 @@
+{
+  "additional_special_tokens": [
+    "<|endoftext|>",
+    "<fim_prefix>",
+    "<fim_middle>",
+    "<fim_suffix>",
+    "<fim_pad>",
+    "<filename>",
+    "<gh_stars>",
+    "<issue_start>",
+    "<issue_comment>",
+    "<issue_closed>",
+    "<jupyter_start>",
+    "<jupyter_text>",
+    "<jupyter_code>",
+    "<jupyter_output>",
+    "<empty_output>",
+    "<commit_before>",
+    "<commit_msg>",
+    "<commit_after>",
+    "<reponame>"
+  ],
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<reponame>",
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

20_128_e3_3e-5/tokenizer_config.json

@@ -0,0 +1,188 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<fim_prefix>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<fim_middle>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<fim_suffix>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<fim_pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "<filename>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "<gh_stars>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "7": {
+      "content": "<issue_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "8": {
+      "content": "<issue_comment>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "9": {
+      "content": "<issue_closed>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "10": {
+      "content": "<jupyter_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "11": {
+      "content": "<jupyter_text>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "12": {
+      "content": "<jupyter_code>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "13": {
+      "content": "<jupyter_output>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "14": {
+      "content": "<empty_output>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "15": {
+      "content": "<commit_before>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "16": {
+      "content": "<commit_msg>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "17": {
+      "content": "<commit_after>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "18": {
+      "content": "<reponame>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|endoftext|>",
+    "<fim_prefix>",
+    "<fim_middle>",
+    "<fim_suffix>",
+    "<fim_pad>",
+    "<filename>",
+    "<gh_stars>",
+    "<issue_start>",
+    "<issue_comment>",
+    "<issue_closed>",
+    "<jupyter_start>",
+    "<jupyter_text>",
+    "<jupyter_code>",
+    "<jupyter_output>",
+    "<empty_output>",
+    "<commit_before>",
+    "<commit_msg>",
+    "<commit_after>",
+    "<reponame>"
+  ],
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "extra_special_tokens": {},
+  "model_max_length": 8192,
+  "pad_token": "<reponame>",
+  "padding_side": "left",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>",
+  "vocab_size": 49152
+}

20_128_e3_3e-5/train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 3.0,
+    "total_flos": 7.451297465719849e+17,
+    "train_loss": 0.5084822381997586,
+    "train_runtime": 374.6048,
+    "train_samples": 5847,
+    "train_samples_per_second": 46.825,
+    "train_steps_per_second": 1.466
+}

20_128_e3_3e-5/trainer_state.json

@@ -0,0 +1,806 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 549,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0273224043715847,
+      "grad_norm": 1.0141438245773315,
+      "learning_rate": 4.2857142857142855e-06,
+      "loss": 1.3391,
+      "step": 5
+    },
+    {
+      "epoch": 0.0546448087431694,
+      "grad_norm": 0.6949726343154907,
+      "learning_rate": 9.642857142857144e-06,
+      "loss": 1.3782,
+      "step": 10
+    },
+    {
+      "epoch": 0.08196721311475409,
+      "grad_norm": 0.6441673040390015,
+      "learning_rate": 1.5e-05,
+      "loss": 1.2395,
+      "step": 15
+    },
+    {
+      "epoch": 0.1092896174863388,
+      "grad_norm": 0.6060148477554321,
+      "learning_rate": 2.0357142857142858e-05,
+      "loss": 1.2866,
+      "step": 20
+    },
+    {
+      "epoch": 0.1366120218579235,
+      "grad_norm": 0.6738765835762024,
+      "learning_rate": 2.5714285714285714e-05,
+      "loss": 1.1891,
+      "step": 25
+    },
+    {
+      "epoch": 0.16393442622950818,
+      "grad_norm": 0.519775927066803,
+      "learning_rate": 2.9999727300559898e-05,
+      "loss": 1.2258,
+      "step": 30
+    },
+    {
+      "epoch": 0.1912568306010929,
+      "grad_norm": 0.4643530547618866,
+      "learning_rate": 2.9990183861225638e-05,
+      "loss": 1.0641,
+      "step": 35
+    },
+    {
+      "epoch": 0.2185792349726776,
+      "grad_norm": 0.5083030462265015,
+      "learning_rate": 2.996701536359701e-05,
+      "loss": 1.1646,
+      "step": 40
+    },
+    {
+      "epoch": 0.2459016393442623,
+      "grad_norm": 0.5160901546478271,
+      "learning_rate": 2.993024286626367e-05,
+      "loss": 1.07,
+      "step": 45
+    },
+    {
+      "epoch": 0.273224043715847,
+      "grad_norm": 0.5701006650924683,
+      "learning_rate": 2.987989979292638e-05,
+      "loss": 1.0412,
+      "step": 50
+    },
+    {
+      "epoch": 0.3005464480874317,
+      "grad_norm": 0.5380054116249084,
+      "learning_rate": 2.981603190201714e-05,
+      "loss": 1.0139,
+      "step": 55
+    },
+    {
+      "epoch": 0.32786885245901637,
+      "grad_norm": 0.49321410059928894,
+      "learning_rate": 2.97386972451079e-05,
+      "loss": 1.0186,
+      "step": 60
+    },
+    {
+      "epoch": 0.3551912568306011,
+      "grad_norm": 0.644487202167511,
+      "learning_rate": 2.9647966114145582e-05,
+      "loss": 0.9889,
+      "step": 65
+    },
+    {
+      "epoch": 0.3825136612021858,
+      "grad_norm": 0.5875224471092224,
+      "learning_rate": 2.954392097756154e-05,
+      "loss": 0.9945,
+      "step": 70
+    },
+    {
+      "epoch": 0.4098360655737705,
+      "grad_norm": 0.6051636338233948,
+      "learning_rate": 2.9426656405313292e-05,
+      "loss": 0.9486,
+      "step": 75
+    },
+    {
+      "epoch": 0.4371584699453552,
+      "grad_norm": 0.6338690519332886,
+      "learning_rate": 2.9296278982926918e-05,
+      "loss": 0.9587,
+      "step": 80
+    },
+    {
+      "epoch": 0.4644808743169399,
+      "grad_norm": 0.6188762784004211,
+      "learning_rate": 2.9152907214618022e-05,
+      "loss": 0.9721,
+      "step": 85
+    },
+    {
+      "epoch": 0.4918032786885246,
+      "grad_norm": 0.7837534546852112,
+      "learning_rate": 2.8996671415579474e-05,
+      "loss": 0.8907,
+      "step": 90
+    },
+    {
+      "epoch": 0.5191256830601093,
+      "grad_norm": 0.6192768812179565,
+      "learning_rate": 2.8827713593533747e-05,
+      "loss": 0.8892,
+      "step": 95
+    },
+    {
+      "epoch": 0.546448087431694,
+      "grad_norm": 0.7909646034240723,
+      "learning_rate": 2.864618731965754e-05,
+      "loss": 0.7792,
+      "step": 100
+    },
+    {
+      "epoch": 0.5737704918032787,
+      "grad_norm": 0.6482694149017334,
+      "learning_rate": 2.845225758899605e-05,
+      "loss": 0.8621,
+      "step": 105
+    },
+    {
+      "epoch": 0.6010928961748634,
+      "grad_norm": 0.7391148805618286,
+      "learning_rate": 2.8246100670493656e-05,
+      "loss": 0.832,
+      "step": 110
+    },
+    {
+      "epoch": 0.6284153005464481,
+      "grad_norm": 0.781980037689209,
+      "learning_rate": 2.8027903946777434e-05,
+      "loss": 0.7328,
+      "step": 115
+    },
+    {
+      "epoch": 0.6557377049180327,
+      "grad_norm": 0.9218024611473083,
+      "learning_rate": 2.7797865743839104e-05,
+      "loss": 0.8268,
+      "step": 120
+    },
+    {
+      "epoch": 0.6830601092896175,
+      "grad_norm": 0.8340065479278564,
+      "learning_rate": 2.7556195150770166e-05,
+      "loss": 0.781,
+      "step": 125
+    },
+    {
+      "epoch": 0.7103825136612022,
+      "grad_norm": 0.997643232345581,
+      "learning_rate": 2.7303111829714135e-05,
+      "loss": 0.7286,
+      "step": 130
+    },
+    {
+      "epoch": 0.7377049180327869,
+      "grad_norm": 1.0612376928329468,
+      "learning_rate": 2.703884581620857e-05,
+      "loss": 0.7246,
+      "step": 135
+    },
+    {
+      "epoch": 0.7650273224043715,
+      "grad_norm": 0.9626303315162659,
+      "learning_rate": 2.6763637310098427e-05,
+      "loss": 0.7142,
+      "step": 140
+    },
+    {
+      "epoch": 0.7923497267759563,
+      "grad_norm": 0.8147085905075073,
+      "learning_rate": 2.6477736457210703e-05,
+      "loss": 0.7322,
+      "step": 145
+    },
+    {
+      "epoch": 0.819672131147541,
+      "grad_norm": 0.9698754549026489,
+      "learning_rate": 2.618140312198889e-05,
+      "loss": 0.6196,
+      "step": 150
+    },
+    {
+      "epoch": 0.8469945355191257,
+      "grad_norm": 0.9555173516273499,
+      "learning_rate": 2.5874906651293877e-05,
+      "loss": 0.6847,
+      "step": 155
+    },
+    {
+      "epoch": 0.8743169398907104,
+      "grad_norm": 1.260975956916809,
+      "learning_rate": 2.5558525629585913e-05,
+      "loss": 0.6209,
+      "step": 160
+    },
+    {
+      "epoch": 0.9016393442622951,
+      "grad_norm": 1.0865294933319092,
+      "learning_rate": 2.5232547625710324e-05,
+      "loss": 0.6791,
+      "step": 165
+    },
+    {
+      "epoch": 0.9289617486338798,
+      "grad_norm": 1.3132290840148926,
+      "learning_rate": 2.4897268931516927e-05,
+      "loss": 0.6178,
+      "step": 170
+    },
+    {
+      "epoch": 0.9562841530054644,
+      "grad_norm": 0.8079626560211182,
+      "learning_rate": 2.4552994292550906e-05,
+      "loss": 0.5514,
+      "step": 175
+    },
+    {
+      "epoch": 0.9836065573770492,
+      "grad_norm": 0.9637578725814819,
+      "learning_rate": 2.4200036631059834e-05,
+      "loss": 0.6481,
+      "step": 180
+    },
+    {
+      "epoch": 1.010928961748634,
+      "grad_norm": 1.034854531288147,
+      "learning_rate": 2.383871676156858e-05,
+      "loss": 0.5723,
+      "step": 185
+    },
+    {
+      "epoch": 1.0382513661202186,
+      "grad_norm": 1.0636274814605713,
+      "learning_rate": 2.3469363099280743e-05,
+      "loss": 0.5164,
+      "step": 190
+    },
+    {
+      "epoch": 1.0655737704918034,
+      "grad_norm": 0.9724008440971375,
+      "learning_rate": 2.3092311361571534e-05,
+      "loss": 0.4775,
+      "step": 195
+    },
+    {
+      "epoch": 1.092896174863388,
+      "grad_norm": 1.0907925367355347,
+      "learning_rate": 2.2707904262843523e-05,
+      "loss": 0.4899,
+      "step": 200
+    },
+    {
+      "epoch": 1.1202185792349726,
+      "grad_norm": 1.1355890035629272,
+      "learning_rate": 2.2316491203022513e-05,
+      "loss": 0.4835,
+      "step": 205
+    },
+    {
+      "epoch": 1.1475409836065573,
+      "grad_norm": 0.919542670249939,
+      "learning_rate": 2.191842794997677e-05,
+      "loss": 0.4539,
+      "step": 210
+    },
+    {
+      "epoch": 1.174863387978142,
+      "grad_norm": 1.0718759298324585,
+      "learning_rate": 2.1514076316148202e-05,
+      "loss": 0.4581,
+      "step": 215
+    },
+    {
+      "epoch": 1.2021857923497268,
+      "grad_norm": 1.053702712059021,
+      "learning_rate": 2.1103803829689464e-05,
+      "loss": 0.4936,
+      "step": 220
+    },
+    {
+      "epoch": 1.2295081967213115,
+      "grad_norm": 1.5437586307525635,
+      "learning_rate": 2.0687983400405826e-05,
+      "loss": 0.4709,
+      "step": 225
+    },
+    {
+      "epoch": 1.2568306010928962,
+      "grad_norm": 1.172194004058838,
+      "learning_rate": 2.0266992980805497e-05,
+      "loss": 0.444,
+      "step": 230
+    },
+    {
+      "epoch": 1.2841530054644807,
+      "grad_norm": 1.1436392068862915,
+      "learning_rate": 1.9841215222566506e-05,
+      "loss": 0.395,
+      "step": 235
+    },
+    {
+      "epoch": 1.3114754098360657,
+      "grad_norm": 1.0586868524551392,
+      "learning_rate": 1.9411037128732317e-05,
+      "loss": 0.4816,
+      "step": 240
+    },
+    {
+      "epoch": 1.3387978142076502,
+      "grad_norm": 1.2341119050979614,
+      "learning_rate": 1.897684970195238e-05,
+      "loss": 0.4373,
+      "step": 245
+    },
+    {
+      "epoch": 1.366120218579235,
+      "grad_norm": 1.1912099123001099,
+      "learning_rate": 1.8539047589087297e-05,
+      "loss": 0.3919,
+      "step": 250
+    },
+    {
+      "epoch": 1.3934426229508197,
+      "grad_norm": 1.0452800989151,
+      "learning_rate": 1.8098028722501626e-05,
+      "loss": 0.3975,
+      "step": 255
+    },
+    {
+      "epoch": 1.4207650273224044,
+      "grad_norm": 1.2034565210342407,
+      "learning_rate": 1.7654193958370436e-05,
+      "loss": 0.4235,
+      "step": 260
+    },
+    {
+      "epoch": 1.4480874316939891,
+      "grad_norm": 1.1712170839309692,
+      "learning_rate": 1.720794671232827e-05,
+      "loss": 0.3882,
+      "step": 265
+    },
+    {
+      "epoch": 1.4754098360655736,
+      "grad_norm": 1.2399131059646606,
+      "learning_rate": 1.675969259279177e-05,
+      "loss": 0.3837,
+      "step": 270
+    },
+    {
+      "epoch": 1.5027322404371586,
+      "grad_norm": 1.2458595037460327,
+      "learning_rate": 1.6309839032289168e-05,
+      "loss": 0.3747,
+      "step": 275
+    },
+    {
+      "epoch": 1.530054644808743,
+      "grad_norm": 1.15314519405365,
+      "learning_rate": 1.5858794917131847e-05,
+      "loss": 0.3643,
+      "step": 280
+    },
+    {
+      "epoch": 1.5573770491803278,
+      "grad_norm": 1.157686471939087,
+      "learning_rate": 1.540697021576443e-05,
+      "loss": 0.343,
+      "step": 285
+    },
+    {
+      "epoch": 1.5846994535519126,
+      "grad_norm": 1.2145419120788574,
+      "learning_rate": 1.4954775606131366e-05,
+      "loss": 0.3896,
+      "step": 290
+    },
+    {
+      "epoch": 1.6120218579234973,
+      "grad_norm": 1.3542180061340332,
+      "learning_rate": 1.4502622102398571e-05,
+      "loss": 0.3556,
+      "step": 295
+    },
+    {
+      "epoch": 1.639344262295082,
+      "grad_norm": 1.1979490518569946,
+      "learning_rate": 1.4050920681369484e-05,
+      "loss": 0.3662,
+      "step": 300
+    },
+    {
+      "epoch": 1.6666666666666665,
+      "grad_norm": 1.2574388980865479,
+      "learning_rate": 1.360008190893511e-05,
+      "loss": 0.3623,
+      "step": 305
+    },
+    {
+      "epoch": 1.6939890710382515,
+      "grad_norm": 1.1358075141906738,
+      "learning_rate": 1.3150515566897501e-05,
+      "loss": 0.3667,
+      "step": 310
+    },
+    {
+      "epoch": 1.721311475409836,
+      "grad_norm": 1.4042322635650635,
+      "learning_rate": 1.270263028050596e-05,
+      "loss": 0.366,
+      "step": 315
+    },
+    {
+      "epoch": 1.748633879781421,
+      "grad_norm": 1.2038304805755615,
+      "learning_rate": 1.2256833147044474e-05,
+      "loss": 0.3434,
+      "step": 320
+    },
+    {
+      "epoch": 1.7759562841530054,
+      "grad_norm": 1.108481526374817,
+      "learning_rate": 1.1813529365807926e-05,
+      "loss": 0.3373,
+      "step": 325
+    },
+    {
+      "epoch": 1.8032786885245902,
+      "grad_norm": 1.164162516593933,
+      "learning_rate": 1.1373121869803509e-05,
+      "loss": 0.3689,
+      "step": 330
+    },
+    {
+      "epoch": 1.830601092896175,
+      "grad_norm": 1.2950106859207153,
+      "learning_rate": 1.0936010959511984e-05,
+      "loss": 0.3473,
+      "step": 335
+    },
+    {
+      "epoch": 1.8579234972677594,
+      "grad_norm": 1.2520761489868164,
+      "learning_rate": 1.0502593939041751e-05,
+      "loss": 0.3322,
+      "step": 340
+    },
+    {
+      "epoch": 1.8852459016393444,
+      "grad_norm": 1.1723130941390991,
+      "learning_rate": 1.0073264755006438e-05,
+      "loss": 0.3156,
+      "step": 345
+    },
+    {
+      "epoch": 1.9125683060109289,
+      "grad_norm": 1.1497845649719238,
+      "learning_rate": 9.648413638454175e-06,
+      "loss": 0.3129,
+      "step": 350
+    },
+    {
+      "epoch": 1.9398907103825138,
+      "grad_norm": 1.3707916736602783,
+      "learning_rate": 9.22842675017412e-06,
+      "loss": 0.3087,
+      "step": 355
+    },
+    {
+      "epoch": 1.9672131147540983,
+      "grad_norm": 1.17500901222229,
+      "learning_rate": 8.813685829702549e-06,
+      "loss": 0.316,
+      "step": 360
+    },
+    {
+      "epoch": 1.994535519125683,
+      "grad_norm": 1.0315008163452148,
+      "learning_rate": 8.404567848347521e-06,
+      "loss": 0.2897,
+      "step": 365
+    },
+    {
+      "epoch": 2.021857923497268,
+      "grad_norm": 1.3879927396774292,
+      "learning_rate": 8.001444666547644e-06,
+      "loss": 0.2611,
+      "step": 370
+    },
+    {
+      "epoch": 2.0491803278688523,
+      "grad_norm": 1.248242974281311,
+      "learning_rate": 7.604682695876156e-06,
+      "loss": 0.2337,
+      "step": 375
+    },
+    {
+      "epoch": 2.0765027322404372,
+      "grad_norm": 1.2371301651000977,
+      "learning_rate": 7.214642565997741e-06,
+      "loss": 0.2417,
+      "step": 380
+    },
+    {
+      "epoch": 2.1038251366120218,
+      "grad_norm": 1.0253205299377441,
+      "learning_rate": 6.83167879688066e-06,
+      "loss": 0.2098,
+      "step": 385
+    },
+    {
+      "epoch": 2.1311475409836067,
+      "grad_norm": 1.2057701349258423,
+      "learning_rate": 6.456139476562203e-06,
+      "loss": 0.252,
+      "step": 390
+    },
+    {
+      "epoch": 2.158469945355191,
+      "grad_norm": 1.1099334955215454,
+      "learning_rate": 6.088365944760323e-06,
+      "loss": 0.2477,
+      "step": 395
+    },
+    {
+      "epoch": 2.185792349726776,
+      "grad_norm": 1.190049648284912,
+      "learning_rate": 5.728692482619012e-06,
+      "loss": 0.2387,
+      "step": 400
+    },
+    {
+      "epoch": 2.2131147540983607,
+      "grad_norm": 1.1209639310836792,
+      "learning_rate": 5.377446008869484e-06,
+      "loss": 0.255,
+      "step": 405
+    },
+    {
+      "epoch": 2.240437158469945,
+      "grad_norm": 1.1923847198486328,
+      "learning_rate": 5.0349457826832804e-06,
+      "loss": 0.2498,
+      "step": 410
+    },
+    {
+      "epoch": 2.26775956284153,
+      "grad_norm": 1.2907756567001343,
+      "learning_rate": 4.7015031134873315e-06,
+      "loss": 0.2355,
+      "step": 415
+    },
+    {
+      "epoch": 2.2950819672131146,
+      "grad_norm": 1.1045355796813965,
+      "learning_rate": 4.377421078004895e-06,
+      "loss": 0.2266,
+      "step": 420
+    },
+    {
+      "epoch": 2.3224043715846996,
+      "grad_norm": 1.2086292505264282,
+      "learning_rate": 4.062994244779387e-06,
+      "loss": 0.187,
+      "step": 425
+    },
+    {
+      "epoch": 2.349726775956284,
+      "grad_norm": 1.4669852256774902,
+      "learning_rate": 3.7585084064316085e-06,
+      "loss": 0.214,
+      "step": 430
+    },
+    {
+      "epoch": 2.3770491803278686,
+      "grad_norm": 1.05766761302948,
+      "learning_rate": 3.46424031989369e-06,
+      "loss": 0.2255,
+      "step": 435
+    },
+    {
+      "epoch": 2.4043715846994536,
+      "grad_norm": 1.0683411359786987,
+      "learning_rate": 3.180457454855807e-06,
+      "loss": 0.2305,
+      "step": 440
+    },
+    {
+      "epoch": 2.431693989071038,
+      "grad_norm": 1.1828384399414062,
+      "learning_rate": 2.907417750654462e-06,
+      "loss": 0.2364,
+      "step": 445
+    },
+    {
+      "epoch": 2.459016393442623,
+      "grad_norm": 1.2708568572998047,
+      "learning_rate": 2.6453693818231173e-06,
+      "loss": 0.2121,
+      "step": 450
+    },
+    {
+      "epoch": 2.4863387978142075,
+      "grad_norm": 1.2584352493286133,
+      "learning_rate": 2.3945505325184473e-06,
+      "loss": 0.2022,
+      "step": 455
+    },
+    {
+      "epoch": 2.5136612021857925,
+      "grad_norm": 1.3101749420166016,
+      "learning_rate": 2.1551891800271096e-06,
+      "loss": 0.2347,
+      "step": 460
+    },
+    {
+      "epoch": 2.540983606557377,
+      "grad_norm": 1.194317102432251,
+      "learning_rate": 1.927502887549872e-06,
+      "loss": 0.1953,
+      "step": 465
+    },
+    {
+      "epoch": 2.5683060109289615,
+      "grad_norm": 1.1450414657592773,
+      "learning_rate": 1.7116986064514828e-06,
+      "loss": 0.2184,
+      "step": 470
+    },
+    {
+      "epoch": 2.5956284153005464,
+      "grad_norm": 1.3117111921310425,
+      "learning_rate": 1.5079724881559243e-06,
+      "loss": 0.2076,
+      "step": 475
+    },
+    {
+      "epoch": 2.6229508196721314,
+      "grad_norm": 1.1989983320236206,
+      "learning_rate": 1.3165097058581055e-06,
+      "loss": 0.1942,
+      "step": 480
+    },
+    {
+      "epoch": 2.650273224043716,
+      "grad_norm": 1.1527259349822998,
+      "learning_rate": 1.1374842862140188e-06,
+      "loss": 0.2187,
+      "step": 485
+    },
+    {
+      "epoch": 2.6775956284153004,
+      "grad_norm": 1.2920244932174683,
+      "learning_rate": 9.710589511623196e-07,
+      "loss": 0.2135,
+      "step": 490
+    },
+    {
+      "epoch": 2.7049180327868854,
+      "grad_norm": 1.1743979454040527,
+      "learning_rate": 8.173849700211694e-07,
+      "loss": 0.2361,
+      "step": 495
+    },
+    {
+      "epoch": 2.73224043715847,
+      "grad_norm": 1.197568655014038,
+      "learning_rate": 6.766020219946895e-07,
+      "loss": 0.2066,
+      "step": 500
+    },
+    {
+      "epoch": 2.7595628415300544,
+      "grad_norm": 1.1356133222579956,
+      "learning_rate": 5.488380692140644e-07,
+      "loss": 0.2156,
+      "step": 505
+    },
+    {
+      "epoch": 2.7868852459016393,
+      "grad_norm": 1.1338391304016113,
+      "learning_rate": 4.3420924042865904e-07,
+      "loss": 0.259,
+      "step": 510
+    },
+    {
+      "epoch": 2.8142076502732243,
+      "grad_norm": 1.0881953239440918,
+      "learning_rate": 3.3281972545287807e-07,
+      "loss": 0.2046,
+      "step": 515
+    },
+    {
+      "epoch": 2.841530054644809,
+      "grad_norm": 1.2116326093673706,
+      "learning_rate": 2.4476168046471016e-07,
+      "loss": 0.2418,
+      "step": 520
+    },
+    {
+      "epoch": 2.8688524590163933,
+      "grad_norm": 1.2079471349716187,
+      "learning_rate": 1.7011514424202236e-07,
+      "loss": 0.2373,
+      "step": 525
+    },
+    {
+      "epoch": 2.8961748633879782,
+      "grad_norm": 1.35047447681427,
+      "learning_rate": 1.0894796541275065e-07,
+      "loss": 0.2169,
+      "step": 530
+    },
+    {
+      "epoch": 2.9234972677595628,
+      "grad_norm": 1.138166904449463,
+      "learning_rate": 6.131574078511226e-08,
+      "loss": 0.2194,
+      "step": 535
+    },
+    {
+      "epoch": 2.9508196721311473,
+      "grad_norm": 1.0978237390518188,
+      "learning_rate": 2.7261764813880098e-08,
+      "loss": 0.2312,
+      "step": 540
+    },
+    {
+      "epoch": 2.978142076502732,
+      "grad_norm": 1.2585736513137817,
+      "learning_rate": 6.81699024867255e-09,
+      "loss": 0.2086,
+      "step": 545
+    },
+    {
+      "epoch": 3.0,
+      "step": 549,
+      "total_flos": 7.451297465719849e+17,
+      "train_loss": 0.5084822381997586,
+      "train_runtime": 374.6048,
+      "train_samples_per_second": 46.825,
+      "train_steps_per_second": 1.466
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 549,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 2000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": false,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 7.451297465719849e+17,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

20_128_e3_3e-5/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e21741956ee7b4645d39519595990b34a412e73f077e66f671c7f38fb5b19fad
+size 8145