Upload folder using huggingface_hub

3_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

3_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: 3_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. -->
+
+# 3_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

3_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": [
+    "down_proj",
+    "up_proj",
+    "o_proj",
+    "v_proj",
+    "k_proj",
+    "gate_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

3_128_e3_3e-5/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43ba5818ddffd05378741047c6759199f748afd1a17fb980ff9878772673ea60
+size 791751704

3_128_e3_3e-5/all_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 3.0,
+    "total_flos": 9.147954492048671e+17,
+    "train_loss": 0.5655180328549483,
+    "train_runtime": 449.7283,
+    "train_samples": 6627,
+    "train_samples_per_second": 44.207,
+    "train_steps_per_second": 1.388
+}

3_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
+}

3_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
+  }
+}

3_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
+}

3_128_e3_3e-5/train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 3.0,
+    "total_flos": 9.147954492048671e+17,
+    "train_loss": 0.5655180328549483,
+    "train_runtime": 449.7283,
+    "train_samples": 6627,
+    "train_samples_per_second": 44.207,
+    "train_steps_per_second": 1.388
+}

3_128_e3_3e-5/trainer_state.json

@@ -0,0 +1,911 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 624,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.024096385542168676,
+      "grad_norm": 0.9984562993049622,
+      "learning_rate": 3.75e-06,
+      "loss": 1.3067,
+      "step": 5
+    },
+    {
+      "epoch": 0.04819277108433735,
+      "grad_norm": 0.7414852976799011,
+      "learning_rate": 8.4375e-06,
+      "loss": 1.3033,
+      "step": 10
+    },
+    {
+      "epoch": 0.07228915662650602,
+      "grad_norm": 0.6542924046516418,
+      "learning_rate": 1.3125e-05,
+      "loss": 1.2766,
+      "step": 15
+    },
+    {
+      "epoch": 0.0963855421686747,
+      "grad_norm": 0.7500748634338379,
+      "learning_rate": 1.78125e-05,
+      "loss": 1.2971,
+      "step": 20
+    },
+    {
+      "epoch": 0.12048192771084337,
+      "grad_norm": 0.5532894134521484,
+      "learning_rate": 2.25e-05,
+      "loss": 1.2578,
+      "step": 25
+    },
+    {
+      "epoch": 0.14457831325301204,
+      "grad_norm": 0.5548573732376099,
+      "learning_rate": 2.71875e-05,
+      "loss": 1.2315,
+      "step": 30
+    },
+    {
+      "epoch": 0.1686746987951807,
+      "grad_norm": 0.4389966130256653,
+      "learning_rate": 2.9999155161863672e-05,
+      "loss": 1.2126,
+      "step": 35
+    },
+    {
+      "epoch": 0.1927710843373494,
+      "grad_norm": 0.5462283492088318,
+      "learning_rate": 2.998965182572804e-05,
+      "loss": 1.221,
+      "step": 40
+    },
+    {
+      "epoch": 0.21686746987951808,
+      "grad_norm": 0.486116498708725,
+      "learning_rate": 2.996959581841219e-05,
+      "loss": 1.2334,
+      "step": 45
+    },
+    {
+      "epoch": 0.24096385542168675,
+      "grad_norm": 0.4679025113582611,
+      "learning_rate": 2.9939001259286775e-05,
+      "loss": 1.1515,
+      "step": 50
+    },
+    {
+      "epoch": 0.26506024096385544,
+      "grad_norm": 0.4766799807548523,
+      "learning_rate": 2.989788968683223e-05,
+      "loss": 1.1116,
+      "step": 55
+    },
+    {
+      "epoch": 0.2891566265060241,
+      "grad_norm": 0.4348437190055847,
+      "learning_rate": 2.984629004347569e-05,
+      "loss": 1.0809,
+      "step": 60
+    },
+    {
+      "epoch": 0.3132530120481928,
+      "grad_norm": 0.5816547274589539,
+      "learning_rate": 2.9784238655215627e-05,
+      "loss": 1.1096,
+      "step": 65
+    },
+    {
+      "epoch": 0.3373493975903614,
+      "grad_norm": 0.6274300217628479,
+      "learning_rate": 2.9711779206048457e-05,
+      "loss": 1.0734,
+      "step": 70
+    },
+    {
+      "epoch": 0.3614457831325301,
+      "grad_norm": 0.6238059997558594,
+      "learning_rate": 2.9628962707215126e-05,
+      "loss": 1.0568,
+      "step": 75
+    },
+    {
+      "epoch": 0.3855421686746988,
+      "grad_norm": 0.5170210599899292,
+      "learning_rate": 2.953584746128934e-05,
+      "loss": 0.9898,
+      "step": 80
+    },
+    {
+      "epoch": 0.40963855421686746,
+      "grad_norm": 0.6345047950744629,
+      "learning_rate": 2.943249902113274e-05,
+      "loss": 1.0368,
+      "step": 85
+    },
+    {
+      "epoch": 0.43373493975903615,
+      "grad_norm": 0.6085061430931091,
+      "learning_rate": 2.931899014374587e-05,
+      "loss": 0.9804,
+      "step": 90
+    },
+    {
+      "epoch": 0.4578313253012048,
+      "grad_norm": 0.636981725692749,
+      "learning_rate": 2.9195400739047443e-05,
+      "loss": 0.9992,
+      "step": 95
+    },
+    {
+      "epoch": 0.4819277108433735,
+      "grad_norm": 0.8020745515823364,
+      "learning_rate": 2.906181781361803e-05,
+      "loss": 0.9558,
+      "step": 100
+    },
+    {
+      "epoch": 0.5060240963855421,
+      "grad_norm": 0.6857292652130127,
+      "learning_rate": 2.8918335409447642e-05,
+      "loss": 0.9352,
+      "step": 105
+    },
+    {
+      "epoch": 0.5301204819277109,
+      "grad_norm": 0.7014384269714355,
+      "learning_rate": 2.8765054537730465e-05,
+      "loss": 0.9395,
+      "step": 110
+    },
+    {
+      "epoch": 0.5542168674698795,
+      "grad_norm": 0.7099854350090027,
+      "learning_rate": 2.8602083107753276e-05,
+      "loss": 0.9163,
+      "step": 115
+    },
+    {
+      "epoch": 0.5783132530120482,
+      "grad_norm": 0.83394855260849,
+      "learning_rate": 2.8429535850927593e-05,
+      "loss": 0.8944,
+      "step": 120
+    },
+    {
+      "epoch": 0.6024096385542169,
+      "grad_norm": 0.790526270866394,
+      "learning_rate": 2.8247534240019142e-05,
+      "loss": 0.8406,
+      "step": 125
+    },
+    {
+      "epoch": 0.6265060240963856,
+      "grad_norm": 0.7931944131851196,
+      "learning_rate": 2.8056206403631336e-05,
+      "loss": 0.8787,
+      "step": 130
+    },
+    {
+      "epoch": 0.6506024096385542,
+      "grad_norm": 0.8070971369743347,
+      "learning_rate": 2.7855687036003138e-05,
+      "loss": 0.7993,
+      "step": 135
+    },
+    {
+      "epoch": 0.6746987951807228,
+      "grad_norm": 0.6747024655342102,
+      "learning_rate": 2.7646117302184716e-05,
+      "loss": 0.8298,
+      "step": 140
+    },
+    {
+      "epoch": 0.6987951807228916,
+      "grad_norm": 0.8380255699157715,
+      "learning_rate": 2.7427644738657635e-05,
+      "loss": 0.846,
+      "step": 145
+    },
+    {
+      "epoch": 0.7228915662650602,
+      "grad_norm": 0.8906871676445007,
+      "learning_rate": 2.7200423149469613e-05,
+      "loss": 0.8109,
+      "step": 150
+    },
+    {
+      "epoch": 0.7469879518072289,
+      "grad_norm": 1.006729006767273,
+      "learning_rate": 2.696461249795695e-05,
+      "loss": 0.7465,
+      "step": 155
+    },
+    {
+      "epoch": 0.7710843373493976,
+      "grad_norm": 0.8761392831802368,
+      "learning_rate": 2.6720378794130745e-05,
+      "loss": 0.7947,
+      "step": 160
+    },
+    {
+      "epoch": 0.7951807228915663,
+      "grad_norm": 0.874119222164154,
+      "learning_rate": 2.646789397780639e-05,
+      "loss": 0.8063,
+      "step": 165
+    },
+    {
+      "epoch": 0.8192771084337349,
+      "grad_norm": 1.0964432954788208,
+      "learning_rate": 2.620733579755841e-05,
+      "loss": 0.7193,
+      "step": 170
+    },
+    {
+      "epoch": 0.8433734939759037,
+      "grad_norm": 0.8752394318580627,
+      "learning_rate": 2.5938887685586e-05,
+      "loss": 0.7241,
+      "step": 175
+    },
+    {
+      "epoch": 0.8674698795180723,
+      "grad_norm": 0.9127100706100464,
+      "learning_rate": 2.5662738628577266e-05,
+      "loss": 0.7205,
+      "step": 180
+    },
+    {
+      "epoch": 0.891566265060241,
+      "grad_norm": 0.8772941827774048,
+      "learning_rate": 2.5379083034663196e-05,
+      "loss": 0.6809,
+      "step": 185
+    },
+    {
+      "epoch": 0.9156626506024096,
+      "grad_norm": 0.970665454864502,
+      "learning_rate": 2.508812059655484e-05,
+      "loss": 0.751,
+      "step": 190
+    },
+    {
+      "epoch": 0.9397590361445783,
+      "grad_norm": 0.9547798037528992,
+      "learning_rate": 2.4790056150960283e-05,
+      "loss": 0.6522,
+      "step": 195
+    },
+    {
+      "epoch": 0.963855421686747,
+      "grad_norm": 0.9481868743896484,
+      "learning_rate": 2.448509953438015e-05,
+      "loss": 0.6537,
+      "step": 200
+    },
+    {
+      "epoch": 0.9879518072289156,
+      "grad_norm": 0.9636387228965759,
+      "learning_rate": 2.417346543538337e-05,
+      "loss": 0.6383,
+      "step": 205
+    },
+    {
+      "epoch": 1.0096385542168675,
+      "grad_norm": 1.0214289426803589,
+      "learning_rate": 2.3855373243467005e-05,
+      "loss": 0.6541,
+      "step": 210
+    },
+    {
+      "epoch": 1.033734939759036,
+      "grad_norm": 1.0764989852905273,
+      "learning_rate": 2.3531046894606703e-05,
+      "loss": 0.5373,
+      "step": 215
+    },
+    {
+      "epoch": 1.0578313253012048,
+      "grad_norm": 1.231276273727417,
+      "learning_rate": 2.3200714713606435e-05,
+      "loss": 0.5782,
+      "step": 220
+    },
+    {
+      "epoch": 1.0819277108433736,
+      "grad_norm": 1.1948630809783936,
+      "learning_rate": 2.2864609253358477e-05,
+      "loss": 0.5548,
+      "step": 225
+    },
+    {
+      "epoch": 1.106024096385542,
+      "grad_norm": 1.006903886795044,
+      "learning_rate": 2.2522967131126864e-05,
+      "loss": 0.5357,
+      "step": 230
+    },
+    {
+      "epoch": 1.1301204819277109,
+      "grad_norm": 1.250080943107605,
+      "learning_rate": 2.217602886196954e-05,
+      "loss": 0.5381,
+      "step": 235
+    },
+    {
+      "epoch": 1.1542168674698796,
+      "grad_norm": 1.0537941455841064,
+      "learning_rate": 2.1824038689416413e-05,
+      "loss": 0.5312,
+      "step": 240
+    },
+    {
+      "epoch": 1.1783132530120481,
+      "grad_norm": 0.9598286151885986,
+      "learning_rate": 2.1467244413522675e-05,
+      "loss": 0.5167,
+      "step": 245
+    },
+    {
+      "epoch": 1.202409638554217,
+      "grad_norm": 0.9252039194107056,
+      "learning_rate": 2.110589721641826e-05,
+      "loss": 0.5332,
+      "step": 250
+    },
+    {
+      "epoch": 1.2265060240963854,
+      "grad_norm": 1.1583731174468994,
+      "learning_rate": 2.074025148547635e-05,
+      "loss": 0.5455,
+      "step": 255
+    },
+    {
+      "epoch": 1.2506024096385542,
+      "grad_norm": 1.1703979969024658,
+      "learning_rate": 2.0370564634225415e-05,
+      "loss": 0.5162,
+      "step": 260
+    },
+    {
+      "epoch": 1.274698795180723,
+      "grad_norm": 1.1499130725860596,
+      "learning_rate": 1.9997096921130865e-05,
+      "loss": 0.5186,
+      "step": 265
+    },
+    {
+      "epoch": 1.2987951807228915,
+      "grad_norm": 1.134293556213379,
+      "learning_rate": 1.962011126637379e-05,
+      "loss": 0.5095,
+      "step": 270
+    },
+    {
+      "epoch": 1.3228915662650602,
+      "grad_norm": 1.092170000076294,
+      "learning_rate": 1.923987306675597e-05,
+      "loss": 0.533,
+      "step": 275
+    },
+    {
+      "epoch": 1.346987951807229,
+      "grad_norm": 1.1463792324066162,
+      "learning_rate": 1.885665000886128e-05,
+      "loss": 0.4739,
+      "step": 280
+    },
+    {
+      "epoch": 1.3710843373493975,
+      "grad_norm": 1.250999093055725,
+      "learning_rate": 1.8470711880605125e-05,
+      "loss": 0.4777,
+      "step": 285
+    },
+    {
+      "epoch": 1.3951807228915662,
+      "grad_norm": 1.0375468730926514,
+      "learning_rate": 1.8082330381304522e-05,
+      "loss": 0.4483,
+      "step": 290
+    },
+    {
+      "epoch": 1.419277108433735,
+      "grad_norm": 1.2541416883468628,
+      "learning_rate": 1.7691778930402584e-05,
+      "loss": 0.4817,
+      "step": 295
+    },
+    {
+      "epoch": 1.4433734939759035,
+      "grad_norm": 1.082485318183899,
+      "learning_rate": 1.7299332474982012e-05,
+      "loss": 0.5083,
+      "step": 300
+    },
+    {
+      "epoch": 1.4674698795180723,
+      "grad_norm": 1.2707996368408203,
+      "learning_rate": 1.6905267296203182e-05,
+      "loss": 0.4566,
+      "step": 305
+    },
+    {
+      "epoch": 1.491566265060241,
+      "grad_norm": 1.2368968725204468,
+      "learning_rate": 1.6509860814802984e-05,
+      "loss": 0.4806,
+      "step": 310
+    },
+    {
+      "epoch": 1.5156626506024096,
+      "grad_norm": 1.4017459154129028,
+      "learning_rate": 1.6113391395791438e-05,
+      "loss": 0.4735,
+      "step": 315
+    },
+    {
+      "epoch": 1.5397590361445783,
+      "grad_norm": 1.1039509773254395,
+      "learning_rate": 1.5716138152483553e-05,
+      "loss": 0.4448,
+      "step": 320
+    },
+    {
+      "epoch": 1.563855421686747,
+      "grad_norm": 1.4038370847702026,
+      "learning_rate": 1.5318380750004355e-05,
+      "loss": 0.4451,
+      "step": 325
+    },
+    {
+      "epoch": 1.5879518072289156,
+      "grad_norm": 1.2977184057235718,
+      "learning_rate": 1.4920399208405453e-05,
+      "loss": 0.4227,
+      "step": 330
+    },
+    {
+      "epoch": 1.6120481927710844,
+      "grad_norm": 1.3206188678741455,
+      "learning_rate": 1.4522473705531738e-05,
+      "loss": 0.4253,
+      "step": 335
+    },
+    {
+      "epoch": 1.636144578313253,
+      "grad_norm": 1.3497966527938843,
+      "learning_rate": 1.4124884379777012e-05,
+      "loss": 0.4385,
+      "step": 340
+    },
+    {
+      "epoch": 1.6602409638554216,
+      "grad_norm": 1.254149079322815,
+      "learning_rate": 1.3727911132867368e-05,
+      "loss": 0.4172,
+      "step": 345
+    },
+    {
+      "epoch": 1.6843373493975904,
+      "grad_norm": 1.027902364730835,
+      "learning_rate": 1.3331833432811166e-05,
+      "loss": 0.4197,
+      "step": 350
+    },
+    {
+      "epoch": 1.7084337349397591,
+      "grad_norm": 1.1875572204589844,
+      "learning_rate": 1.2936930117154428e-05,
+      "loss": 0.4065,
+      "step": 355
+    },
+    {
+      "epoch": 1.7325301204819277,
+      "grad_norm": 1.2602832317352295,
+      "learning_rate": 1.2543479196679951e-05,
+      "loss": 0.405,
+      "step": 360
+    },
+    {
+      "epoch": 1.7566265060240964,
+      "grad_norm": 1.220045804977417,
+      "learning_rate": 1.2151757659688572e-05,
+      "loss": 0.3921,
+      "step": 365
+    },
+    {
+      "epoch": 1.7807228915662652,
+      "grad_norm": 1.3419684171676636,
+      "learning_rate": 1.1762041277000205e-05,
+      "loss": 0.3798,
+      "step": 370
+    },
+    {
+      "epoch": 1.8048192771084337,
+      "grad_norm": 1.1922122240066528,
+      "learning_rate": 1.1374604407811963e-05,
+      "loss": 0.4269,
+      "step": 375
+    },
+    {
+      "epoch": 1.8289156626506025,
+      "grad_norm": 1.223863959312439,
+      "learning_rate": 1.0989719806550112e-05,
+      "loss": 0.3997,
+      "step": 380
+    },
+    {
+      "epoch": 1.8530120481927712,
+      "grad_norm": 1.1763914823532104,
+      "learning_rate": 1.0607658430851745e-05,
+      "loss": 0.3821,
+      "step": 385
+    },
+    {
+      "epoch": 1.8771084337349397,
+      "grad_norm": 1.127062439918518,
+      "learning_rate": 1.0228689250811378e-05,
+      "loss": 0.3835,
+      "step": 390
+    },
+    {
+      "epoch": 1.9012048192771083,
+      "grad_norm": 1.155310034751892,
+      "learning_rate": 9.853079059626806e-06,
+      "loss": 0.3253,
+      "step": 395
+    },
+    {
+      "epoch": 1.9253012048192772,
+      "grad_norm": 1.2986888885498047,
+      "learning_rate": 9.481092285777462e-06,
+      "loss": 0.3839,
+      "step": 400
+    },
+    {
+      "epoch": 1.9493975903614458,
+      "grad_norm": 1.245671272277832,
+      "learning_rate": 9.112990806867544e-06,
+      "loss": 0.3669,
+      "step": 405
+    },
+    {
+      "epoch": 1.9734939759036143,
+      "grad_norm": 1.1917442083358765,
+      "learning_rate": 8.749033765264936e-06,
+      "loss": 0.3401,
+      "step": 410
+    },
+    {
+      "epoch": 1.9975903614457833,
+      "grad_norm": 1.3621636629104614,
+      "learning_rate": 8.389477385665734e-06,
+      "loss": 0.382,
+      "step": 415
+    },
+    {
+      "epoch": 2.019277108433735,
+      "grad_norm": 1.2822985649108887,
+      "learning_rate": 8.034574794712838e-06,
+      "loss": 0.3274,
+      "step": 420
+    },
+    {
+      "epoch": 2.0433734939759036,
+      "grad_norm": 1.1362680196762085,
+      "learning_rate": 7.684575842795486e-06,
+      "loss": 0.313,
+      "step": 425
+    },
+    {
+      "epoch": 2.067469879518072,
+      "grad_norm": 1.1908901929855347,
+      "learning_rate": 7.339726928155336e-06,
+      "loss": 0.2912,
+      "step": 430
+    },
+    {
+      "epoch": 2.091566265060241,
+      "grad_norm": 1.3592913150787354,
+      "learning_rate": 7.000270823422838e-06,
+      "loss": 0.2978,
+      "step": 435
+    },
+    {
+      "epoch": 2.1156626506024097,
+      "grad_norm": 1.225220799446106,
+      "learning_rate": 6.666446504705971e-06,
+      "loss": 0.3073,
+      "step": 440
+    },
+    {
+      "epoch": 2.139759036144578,
+      "grad_norm": 1.1758791208267212,
+      "learning_rate": 6.338488983351778e-06,
+      "loss": 0.3098,
+      "step": 445
+    },
+    {
+      "epoch": 2.163855421686747,
+      "grad_norm": 1.2707329988479614,
+      "learning_rate": 6.016629140499085e-06,
+      "loss": 0.2908,
+      "step": 450
+    },
+    {
+      "epoch": 2.1879518072289157,
+      "grad_norm": 1.1393632888793945,
+      "learning_rate": 5.7010935645388064e-06,
+      "loss": 0.269,
+      "step": 455
+    },
+    {
+      "epoch": 2.212048192771084,
+      "grad_norm": 1.266993761062622,
+      "learning_rate": 5.392104391596428e-06,
+      "loss": 0.2846,
+      "step": 460
+    },
+    {
+      "epoch": 2.236144578313253,
+      "grad_norm": 1.1452138423919678,
+      "learning_rate": 5.089879149148781e-06,
+      "loss": 0.2836,
+      "step": 465
+    },
+    {
+      "epoch": 2.2602409638554217,
+      "grad_norm": 1.2505812644958496,
+      "learning_rate": 4.79463060288535e-06,
+      "loss": 0.272,
+      "step": 470
+    },
+    {
+      "epoch": 2.2843373493975903,
+      "grad_norm": 1.3206887245178223,
+      "learning_rate": 4.5065666069218645e-06,
+      "loss": 0.2971,
+      "step": 475
+    },
+    {
+      "epoch": 2.3084337349397592,
+      "grad_norm": 1.3298640251159668,
+      "learning_rate": 4.2258899574715716e-06,
+      "loss": 0.2911,
+      "step": 480
+    },
+    {
+      "epoch": 2.3325301204819278,
+      "grad_norm": 1.338782548904419,
+      "learning_rate": 3.952798250077318e-06,
+      "loss": 0.3018,
+      "step": 485
+    },
+    {
+      "epoch": 2.3566265060240963,
+      "grad_norm": 1.1768049001693726,
+      "learning_rate": 3.6874837405048665e-06,
+      "loss": 0.2971,
+      "step": 490
+    },
+    {
+      "epoch": 2.380722891566265,
+      "grad_norm": 1.424782395362854,
+      "learning_rate": 3.4301332093953815e-06,
+      "loss": 0.3017,
+      "step": 495
+    },
+    {
+      "epoch": 2.404819277108434,
+      "grad_norm": 1.3253031969070435,
+      "learning_rate": 3.1809278307724054e-06,
+      "loss": 0.2957,
+      "step": 500
+    },
+    {
+      "epoch": 2.4289156626506023,
+      "grad_norm": 1.2620375156402588,
+      "learning_rate": 2.940043044495894e-06,
+      "loss": 0.2421,
+      "step": 505
+    },
+    {
+      "epoch": 2.453012048192771,
+      "grad_norm": 1.1867514848709106,
+      "learning_rate": 2.707648432753037e-06,
+      "loss": 0.3248,
+      "step": 510
+    },
+    {
+      "epoch": 2.47710843373494,
+      "grad_norm": 1.157029390335083,
+      "learning_rate": 2.4839076006729085e-06,
+      "loss": 0.2659,
+      "step": 515
+    },
+    {
+      "epoch": 2.5012048192771084,
+      "grad_norm": 1.3968316316604614,
+      "learning_rate": 2.2689780611489424e-06,
+      "loss": 0.2545,
+      "step": 520
+    },
+    {
+      "epoch": 2.525301204819277,
+      "grad_norm": 1.337080955505371,
+      "learning_rate": 2.0630111239502954e-06,
+      "loss": 0.2698,
+      "step": 525
+    },
+    {
+      "epoch": 2.549397590361446,
+      "grad_norm": 1.1819453239440918,
+      "learning_rate": 1.866151789200215e-06,
+      "loss": 0.2836,
+      "step": 530
+    },
+    {
+      "epoch": 2.5734939759036144,
+      "grad_norm": 1.1866703033447266,
+      "learning_rate": 1.6785386452963914e-06,
+      "loss": 0.2779,
+      "step": 535
+    },
+    {
+      "epoch": 2.597590361445783,
+      "grad_norm": 1.335201382637024,
+      "learning_rate": 1.5003037713451146e-06,
+      "loss": 0.2583,
+      "step": 540
+    },
+    {
+      "epoch": 2.621686746987952,
+      "grad_norm": 1.2616256475448608,
+      "learning_rate": 1.331572644177963e-06,
+      "loss": 0.2519,
+      "step": 545
+    },
+    {
+      "epoch": 2.6457831325301204,
+      "grad_norm": 1.3554015159606934,
+      "learning_rate": 1.1724640500165024e-06,
+      "loss": 0.2767,
+      "step": 550
+    },
+    {
+      "epoch": 2.669879518072289,
+      "grad_norm": 1.2319148778915405,
+      "learning_rate": 1.0230900008471072e-06,
+      "loss": 0.2836,
+      "step": 555
+    },
+    {
+      "epoch": 2.693975903614458,
+      "grad_norm": 1.1905972957611084,
+      "learning_rate": 8.83555655564866e-07,
+      "loss": 0.2769,
+      "step": 560
+    },
+    {
+      "epoch": 2.7180722891566265,
+      "grad_norm": 1.2920160293579102,
+      "learning_rate": 7.539592459420219e-07,
+      "loss": 0.2643,
+      "step": 565
+    },
+    {
+      "epoch": 2.742168674698795,
+      "grad_norm": 1.337218165397644,
+      "learning_rate": 6.343920074730841e-07,
+      "loss": 0.2624,
+      "step": 570
+    },
+    {
+      "epoch": 2.766265060240964,
+      "grad_norm": 1.2163718938827515,
+      "learning_rate": 5.249381151453164e-07,
+      "loss": 0.26,
+      "step": 575
+    },
+    {
+      "epoch": 2.7903614457831325,
+      "grad_norm": 1.126735806465149,
+      "learning_rate": 4.256746241797843e-07,
+      "loss": 0.2838,
+      "step": 580
+    },
+    {
+      "epoch": 2.814457831325301,
+      "grad_norm": 1.3277732133865356,
+      "learning_rate": 3.3667141578470785e-07,
+      "loss": 0.2706,
+      "step": 585
+    },
+    {
+      "epoch": 2.83855421686747,
+      "grad_norm": 1.2749162912368774,
+      "learning_rate": 2.579911479592878e-07,
+      "loss": 0.2874,
+      "step": 590
+    },
+    {
+      "epoch": 2.8626506024096385,
+      "grad_norm": 1.2339216470718384,
+      "learning_rate": 1.8968921138267093e-07,
+      "loss": 0.2436,
+      "step": 595
+    },
+    {
+      "epoch": 2.886746987951807,
+      "grad_norm": 1.2548739910125732,
+      "learning_rate": 1.318136904190592e-07,
+      "loss": 0.255,
+      "step": 600
+    },
+    {
+      "epoch": 2.910843373493976,
+      "grad_norm": 1.1932353973388672,
+      "learning_rate": 8.440532926646315e-08,
+      "loss": 0.2514,
+      "step": 605
+    },
+    {
+      "epoch": 2.9349397590361446,
+      "grad_norm": 1.1958482265472412,
+      "learning_rate": 4.749750327290636e-08,
+      "loss": 0.2566,
+      "step": 610
+    },
+    {
+      "epoch": 2.959036144578313,
+      "grad_norm": 1.1997336149215698,
+      "learning_rate": 2.1116195440278873e-08,
+      "loss": 0.2296,
+      "step": 615
+    },
+    {
+      "epoch": 2.983132530120482,
+      "grad_norm": 1.1634202003479004,
+      "learning_rate": 5.279978132372576e-09,
+      "loss": 0.2643,
+      "step": 620
+    },
+    {
+      "epoch": 3.0,
+      "step": 624,
+      "total_flos": 9.147954492048671e+17,
+      "train_loss": 0.5655180328549483,
+      "train_runtime": 449.7283,
+      "train_samples_per_second": 44.207,
+      "train_steps_per_second": 1.388
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 624,
+  "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": 9.147954492048671e+17,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

3_128_e3_3e-5/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69c3db3db23ee7299caa65f6be708d0ab64b6142b5906da851ec9208bd336e68
+size 8145