Upload folder using huggingface_hub

17_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

17_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: 17_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. -->
+
+# 17_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

17_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": [
+    "q_proj",
+    "k_proj",
+    "up_proj",
+    "o_proj",
+    "down_proj",
+    "gate_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

17_128_e3_3e-5/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:321dc25fa34227f89759fca50be934ee8b0f52a57d48d06188b37d43f140b610
+size 791751704

17_128_e3_3e-5/all_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 3.0,
+    "total_flos": 1.129602491848065e+18,
+    "train_loss": 0.5587638872675598,
+    "train_runtime": 537.1777,
+    "train_samples": 8178,
+    "train_samples_per_second": 45.672,
+    "train_steps_per_second": 1.43
+}

17_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
+}

17_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
+  }
+}

17_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
+}

17_128_e3_3e-5/train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 3.0,
+    "total_flos": 1.129602491848065e+18,
+    "train_loss": 0.5587638872675598,
+    "train_runtime": 537.1777,
+    "train_samples": 8178,
+    "train_samples_per_second": 45.672,
+    "train_steps_per_second": 1.43
+}

17_128_e3_3e-5/trainer_state.json

@@ -0,0 +1,1114 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 768,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01953125,
+      "grad_norm": 1.3195412158966064,
+      "learning_rate": 3.076923076923077e-06,
+      "loss": 1.3336,
+      "step": 5
+    },
+    {
+      "epoch": 0.0390625,
+      "grad_norm": 0.887927234172821,
+      "learning_rate": 6.923076923076923e-06,
+      "loss": 1.3182,
+      "step": 10
+    },
+    {
+      "epoch": 0.05859375,
+      "grad_norm": 0.8733654022216797,
+      "learning_rate": 1.076923076923077e-05,
+      "loss": 1.2282,
+      "step": 15
+    },
+    {
+      "epoch": 0.078125,
+      "grad_norm": 0.6923812031745911,
+      "learning_rate": 1.4615384615384615e-05,
+      "loss": 1.2206,
+      "step": 20
+    },
+    {
+      "epoch": 0.09765625,
+      "grad_norm": 0.5073327422142029,
+      "learning_rate": 1.8461538461538465e-05,
+      "loss": 1.2516,
+      "step": 25
+    },
+    {
+      "epoch": 0.1171875,
+      "grad_norm": 0.5044897198677063,
+      "learning_rate": 2.230769230769231e-05,
+      "loss": 1.2381,
+      "step": 30
+    },
+    {
+      "epoch": 0.13671875,
+      "grad_norm": 0.4931105673313141,
+      "learning_rate": 2.6153846153846157e-05,
+      "loss": 1.1772,
+      "step": 35
+    },
+    {
+      "epoch": 0.15625,
+      "grad_norm": 0.42662668228149414,
+      "learning_rate": 3e-05,
+      "loss": 1.1865,
+      "step": 40
+    },
+    {
+      "epoch": 0.17578125,
+      "grad_norm": 0.4316219091415405,
+      "learning_rate": 2.999651799686565e-05,
+      "loss": 1.1242,
+      "step": 45
+    },
+    {
+      "epoch": 0.1953125,
+      "grad_norm": 0.41592851281166077,
+      "learning_rate": 2.9986073604042044e-05,
+      "loss": 1.1529,
+      "step": 50
+    },
+    {
+      "epoch": 0.21484375,
+      "grad_norm": 0.4789750277996063,
+      "learning_rate": 2.9968671670516984e-05,
+      "loss": 1.0709,
+      "step": 55
+    },
+    {
+      "epoch": 0.234375,
+      "grad_norm": 0.5076216459274292,
+      "learning_rate": 2.9944320275435414e-05,
+      "loss": 1.1365,
+      "step": 60
+    },
+    {
+      "epoch": 0.25390625,
+      "grad_norm": 0.5781316757202148,
+      "learning_rate": 2.9913030724348538e-05,
+      "loss": 1.0986,
+      "step": 65
+    },
+    {
+      "epoch": 0.2734375,
+      "grad_norm": 0.7199118733406067,
+      "learning_rate": 2.9874817543965017e-05,
+      "loss": 1.0621,
+      "step": 70
+    },
+    {
+      "epoch": 0.29296875,
+      "grad_norm": 0.6049282550811768,
+      "learning_rate": 2.98296984754067e-05,
+      "loss": 1.0846,
+      "step": 75
+    },
+    {
+      "epoch": 0.3125,
+      "grad_norm": 0.5661935210227966,
+      "learning_rate": 2.9777694465972e-05,
+      "loss": 1.0294,
+      "step": 80
+    },
+    {
+      "epoch": 0.33203125,
+      "grad_norm": 0.5328531265258789,
+      "learning_rate": 2.9718829659410772e-05,
+      "loss": 1.0101,
+      "step": 85
+    },
+    {
+      "epoch": 0.3515625,
+      "grad_norm": 0.5904419422149658,
+      "learning_rate": 2.965313138471513e-05,
+      "loss": 1.0287,
+      "step": 90
+    },
+    {
+      "epoch": 0.37109375,
+      "grad_norm": 0.5858999490737915,
+      "learning_rate": 2.958063014343155e-05,
+      "loss": 1.045,
+      "step": 95
+    },
+    {
+      "epoch": 0.390625,
+      "grad_norm": 0.6289122700691223,
+      "learning_rate": 2.9501359595499933e-05,
+      "loss": 0.9557,
+      "step": 100
+    },
+    {
+      "epoch": 0.41015625,
+      "grad_norm": 0.5885446071624756,
+      "learning_rate": 2.9415356543626463e-05,
+      "loss": 0.9268,
+      "step": 105
+    },
+    {
+      "epoch": 0.4296875,
+      "grad_norm": 0.7269174456596375,
+      "learning_rate": 2.93226609161973e-05,
+      "loss": 0.9452,
+      "step": 110
+    },
+    {
+      "epoch": 0.44921875,
+      "grad_norm": 0.5957064628601074,
+      "learning_rate": 2.9223315748741146e-05,
+      "loss": 0.9441,
+      "step": 115
+    },
+    {
+      "epoch": 0.46875,
+      "grad_norm": 0.7111753821372986,
+      "learning_rate": 2.9117367163949264e-05,
+      "loss": 0.9714,
+      "step": 120
+    },
+    {
+      "epoch": 0.48828125,
+      "grad_norm": 0.812457799911499,
+      "learning_rate": 2.9004864350262227e-05,
+      "loss": 0.9706,
+      "step": 125
+    },
+    {
+      "epoch": 0.5078125,
+      "grad_norm": 0.7122654914855957,
+      "learning_rate": 2.888585953903336e-05,
+      "loss": 0.9154,
+      "step": 130
+    },
+    {
+      "epoch": 0.52734375,
+      "grad_norm": 0.780986487865448,
+      "learning_rate": 2.876040798027941e-05,
+      "loss": 0.9045,
+      "step": 135
+    },
+    {
+      "epoch": 0.546875,
+      "grad_norm": 0.681101381778717,
+      "learning_rate": 2.862856791702982e-05,
+      "loss": 0.8637,
+      "step": 140
+    },
+    {
+      "epoch": 0.56640625,
+      "grad_norm": 0.821196973323822,
+      "learning_rate": 2.8490400558286396e-05,
+      "loss": 0.8688,
+      "step": 145
+    },
+    {
+      "epoch": 0.5859375,
+      "grad_norm": 0.8540089130401611,
+      "learning_rate": 2.8345970050605957e-05,
+      "loss": 0.8657,
+      "step": 150
+    },
+    {
+      "epoch": 0.60546875,
+      "grad_norm": 0.8492436408996582,
+      "learning_rate": 2.819534344831923e-05,
+      "loss": 0.8641,
+      "step": 155
+    },
+    {
+      "epoch": 0.625,
+      "grad_norm": 0.8150472640991211,
+      "learning_rate": 2.8038590682399716e-05,
+      "loss": 0.8316,
+      "step": 160
+    },
+    {
+      "epoch": 0.64453125,
+      "grad_norm": 0.7924156188964844,
+      "learning_rate": 2.7875784527997054e-05,
+      "loss": 0.8021,
+      "step": 165
+    },
+    {
+      "epoch": 0.6640625,
+      "grad_norm": 0.8386889100074768,
+      "learning_rate": 2.77070005706499e-05,
+      "loss": 0.7997,
+      "step": 170
+    },
+    {
+      "epoch": 0.68359375,
+      "grad_norm": 0.9122767448425293,
+      "learning_rate": 2.753231717119405e-05,
+      "loss": 0.7763,
+      "step": 175
+    },
+    {
+      "epoch": 0.703125,
+      "grad_norm": 1.0265560150146484,
+      "learning_rate": 2.7351815429382094e-05,
+      "loss": 0.7774,
+      "step": 180
+    },
+    {
+      "epoch": 0.72265625,
+      "grad_norm": 0.8809930086135864,
+      "learning_rate": 2.716557914623147e-05,
+      "loss": 0.78,
+      "step": 185
+    },
+    {
+      "epoch": 0.7421875,
+      "grad_norm": 0.9025191068649292,
+      "learning_rate": 2.6973694785118392e-05,
+      "loss": 0.7712,
+      "step": 190
+    },
+    {
+      "epoch": 0.76171875,
+      "grad_norm": 0.7722713351249695,
+      "learning_rate": 2.677625143163578e-05,
+      "loss": 0.7578,
+      "step": 195
+    },
+    {
+      "epoch": 0.78125,
+      "grad_norm": 0.962631344795227,
+      "learning_rate": 2.6573340752233722e-05,
+      "loss": 0.7666,
+      "step": 200
+    },
+    {
+      "epoch": 0.80078125,
+      "grad_norm": 0.9630898237228394,
+      "learning_rate": 2.636505695166177e-05,
+      "loss": 0.735,
+      "step": 205
+    },
+    {
+      "epoch": 0.8203125,
+      "grad_norm": 0.9051881432533264,
+      "learning_rate": 2.6151496729232783e-05,
+      "loss": 0.7507,
+      "step": 210
+    },
+    {
+      "epoch": 0.83984375,
+      "grad_norm": 1.0465737581253052,
+      "learning_rate": 2.593275923392861e-05,
+      "loss": 0.7527,
+      "step": 215
+    },
+    {
+      "epoch": 0.859375,
+      "grad_norm": 0.9470021724700928,
+      "learning_rate": 2.570894601836849e-05,
+      "loss": 0.7183,
+      "step": 220
+    },
+    {
+      "epoch": 0.87890625,
+      "grad_norm": 1.055437684059143,
+      "learning_rate": 2.5480160991661486e-05,
+      "loss": 0.7355,
+      "step": 225
+    },
+    {
+      "epoch": 0.8984375,
+      "grad_norm": 0.9368035793304443,
+      "learning_rate": 2.5246510371164962e-05,
+      "loss": 0.6927,
+      "step": 230
+    },
+    {
+      "epoch": 0.91796875,
+      "grad_norm": 1.0200940370559692,
+      "learning_rate": 2.500810263317129e-05,
+      "loss": 0.6837,
+      "step": 235
+    },
+    {
+      "epoch": 0.9375,
+      "grad_norm": 0.9064467549324036,
+      "learning_rate": 2.4765048462545948e-05,
+      "loss": 0.6701,
+      "step": 240
+    },
+    {
+      "epoch": 0.95703125,
+      "grad_norm": 0.9298158884048462,
+      "learning_rate": 2.451746070134011e-05,
+      "loss": 0.6594,
+      "step": 245
+    },
+    {
+      "epoch": 0.9765625,
+      "grad_norm": 0.9122622013092041,
+      "learning_rate": 2.4265454296401857e-05,
+      "loss": 0.6793,
+      "step": 250
+    },
+    {
+      "epoch": 0.99609375,
+      "grad_norm": 0.9756189584732056,
+      "learning_rate": 2.4009146246010104e-05,
+      "loss": 0.6034,
+      "step": 255
+    },
+    {
+      "epoch": 1.015625,
+      "grad_norm": 1.1787760257720947,
+      "learning_rate": 2.374865554555616e-05,
+      "loss": 0.6248,
+      "step": 260
+    },
+    {
+      "epoch": 1.03515625,
+      "grad_norm": 1.0016402006149292,
+      "learning_rate": 2.3484103132298082e-05,
+      "loss": 0.5249,
+      "step": 265
+    },
+    {
+      "epoch": 1.0546875,
+      "grad_norm": 1.110153317451477,
+      "learning_rate": 2.3215611829213494e-05,
+      "loss": 0.5773,
+      "step": 270
+    },
+    {
+      "epoch": 1.07421875,
+      "grad_norm": 1.0106018781661987,
+      "learning_rate": 2.294330628797692e-05,
+      "loss": 0.5263,
+      "step": 275
+    },
+    {
+      "epoch": 1.09375,
+      "grad_norm": 1.0548104047775269,
+      "learning_rate": 2.2667312931088098e-05,
+      "loss": 0.5313,
+      "step": 280
+    },
+    {
+      "epoch": 1.11328125,
+      "grad_norm": 1.0433807373046875,
+      "learning_rate": 2.2387759893178198e-05,
+      "loss": 0.5371,
+      "step": 285
+    },
+    {
+      "epoch": 1.1328125,
+      "grad_norm": 1.1982029676437378,
+      "learning_rate": 2.2104776961521112e-05,
+      "loss": 0.4879,
+      "step": 290
+    },
+    {
+      "epoch": 1.15234375,
+      "grad_norm": 1.0445747375488281,
+      "learning_rate": 2.181849551577751e-05,
+      "loss": 0.526,
+      "step": 295
+    },
+    {
+      "epoch": 1.171875,
+      "grad_norm": 1.0809053182601929,
+      "learning_rate": 2.1529048466999575e-05,
+      "loss": 0.5555,
+      "step": 300
+    },
+    {
+      "epoch": 1.19140625,
+      "grad_norm": 1.1874393224716187,
+      "learning_rate": 2.123657019592479e-05,
+      "loss": 0.6174,
+      "step": 305
+    },
+    {
+      "epoch": 1.2109375,
+      "grad_norm": 1.2840501070022583,
+      "learning_rate": 2.0941196490587352e-05,
+      "loss": 0.4825,
+      "step": 310
+    },
+    {
+      "epoch": 1.23046875,
+      "grad_norm": 1.1347434520721436,
+      "learning_rate": 2.064306448327632e-05,
+      "loss": 0.4992,
+      "step": 315
+    },
+    {
+      "epoch": 1.25,
+      "grad_norm": 1.2234936952590942,
+      "learning_rate": 2.034231258686954e-05,
+      "loss": 0.5092,
+      "step": 320
+    },
+    {
+      "epoch": 1.26953125,
+      "grad_norm": 1.0852220058441162,
+      "learning_rate": 2.0039080430573133e-05,
+      "loss": 0.4715,
+      "step": 325
+    },
+    {
+      "epoch": 1.2890625,
+      "grad_norm": 1.2671151161193848,
+      "learning_rate": 1.9733508795096263e-05,
+      "loss": 0.5066,
+      "step": 330
+    },
+    {
+      "epoch": 1.30859375,
+      "grad_norm": 1.1809030771255493,
+      "learning_rate": 1.942573954729126e-05,
+      "loss": 0.5265,
+      "step": 335
+    },
+    {
+      "epoch": 1.328125,
+      "grad_norm": 1.3064501285552979,
+      "learning_rate": 1.9115915574289523e-05,
+      "loss": 0.5091,
+      "step": 340
+    },
+    {
+      "epoch": 1.34765625,
+      "grad_norm": 1.1759586334228516,
+      "learning_rate": 1.8804180717163732e-05,
+      "loss": 0.5031,
+      "step": 345
+    },
+    {
+      "epoch": 1.3671875,
+      "grad_norm": 1.2991793155670166,
+      "learning_rate": 1.849067970414717e-05,
+      "loss": 0.4859,
+      "step": 350
+    },
+    {
+      "epoch": 1.38671875,
+      "grad_norm": 1.12126886844635,
+      "learning_rate": 1.8175558083441162e-05,
+      "loss": 0.4948,
+      "step": 355
+    },
+    {
+      "epoch": 1.40625,
+      "grad_norm": 1.1345394849777222,
+      "learning_rate": 1.7858962155641842e-05,
+      "loss": 0.4665,
+      "step": 360
+    },
+    {
+      "epoch": 1.42578125,
+      "grad_norm": 1.2230706214904785,
+      "learning_rate": 1.754103890581759e-05,
+      "loss": 0.4654,
+      "step": 365
+    },
+    {
+      "epoch": 1.4453125,
+      "grad_norm": 1.1890556812286377,
+      "learning_rate": 1.7221935935268736e-05,
+      "loss": 0.507,
+      "step": 370
+    },
+    {
+      "epoch": 1.46484375,
+      "grad_norm": 1.2429966926574707,
+      "learning_rate": 1.6901801393001082e-05,
+      "loss": 0.5104,
+      "step": 375
+    },
+    {
+      "epoch": 1.484375,
+      "grad_norm": 1.1942497491836548,
+      "learning_rate": 1.658078390694526e-05,
+      "loss": 0.4281,
+      "step": 380
+    },
+    {
+      "epoch": 1.50390625,
+      "grad_norm": 1.1649296283721924,
+      "learning_rate": 1.62590325149536e-05,
+      "loss": 0.4853,
+      "step": 385
+    },
+    {
+      "epoch": 1.5234375,
+      "grad_norm": 1.1775391101837158,
+      "learning_rate": 1.593669659560684e-05,
+      "loss": 0.4313,
+      "step": 390
+    },
+    {
+      "epoch": 1.54296875,
+      "grad_norm": 1.2446919679641724,
+      "learning_rate": 1.5613925798862497e-05,
+      "loss": 0.5094,
+      "step": 395
+    },
+    {
+      "epoch": 1.5625,
+      "grad_norm": 1.0660845041275024,
+      "learning_rate": 1.5290869976577365e-05,
+      "loss": 0.4183,
+      "step": 400
+    },
+    {
+      "epoch": 1.58203125,
+      "grad_norm": 1.2674548625946045,
+      "learning_rate": 1.4967679112936222e-05,
+      "loss": 0.4424,
+      "step": 405
+    },
+    {
+      "epoch": 1.6015625,
+      "grad_norm": 1.2434098720550537,
+      "learning_rate": 1.4644503254819081e-05,
+      "loss": 0.4388,
+      "step": 410
+    },
+    {
+      "epoch": 1.62109375,
+      "grad_norm": 1.1896209716796875,
+      "learning_rate": 1.4321492442139406e-05,
+      "loss": 0.4536,
+      "step": 415
+    },
+    {
+      "epoch": 1.640625,
+      "grad_norm": 1.3423725366592407,
+      "learning_rate": 1.3998796638185483e-05,
+      "loss": 0.3818,
+      "step": 420
+    },
+    {
+      "epoch": 1.66015625,
+      "grad_norm": 1.1418654918670654,
+      "learning_rate": 1.3676565659997423e-05,
+      "loss": 0.4365,
+      "step": 425
+    },
+    {
+      "epoch": 1.6796875,
+      "grad_norm": 1.203896164894104,
+      "learning_rate": 1.3354949108812026e-05,
+      "loss": 0.4051,
+      "step": 430
+    },
+    {
+      "epoch": 1.69921875,
+      "grad_norm": 1.146031141281128,
+      "learning_rate": 1.3034096300607871e-05,
+      "loss": 0.4624,
+      "step": 435
+    },
+    {
+      "epoch": 1.71875,
+      "grad_norm": 1.1522107124328613,
+      "learning_rate": 1.2714156196782793e-05,
+      "loss": 0.3809,
+      "step": 440
+    },
+    {
+      "epoch": 1.73828125,
+      "grad_norm": 1.3355379104614258,
+      "learning_rate": 1.2395277334996045e-05,
+      "loss": 0.4004,
+      "step": 445
+    },
+    {
+      "epoch": 1.7578125,
+      "grad_norm": 1.2131156921386719,
+      "learning_rate": 1.2077607760207115e-05,
+      "loss": 0.3721,
+      "step": 450
+    },
+    {
+      "epoch": 1.77734375,
+      "grad_norm": 1.1521196365356445,
+      "learning_rate": 1.1761294955943357e-05,
+      "loss": 0.4,
+      "step": 455
+    },
+    {
+      "epoch": 1.796875,
+      "grad_norm": 1.25234055519104,
+      "learning_rate": 1.1446485775828212e-05,
+      "loss": 0.4256,
+      "step": 460
+    },
+    {
+      "epoch": 1.81640625,
+      "grad_norm": 1.3488880395889282,
+      "learning_rate": 1.1133326375401943e-05,
+      "loss": 0.403,
+      "step": 465
+    },
+    {
+      "epoch": 1.8359375,
+      "grad_norm": 1.2184321880340576,
+      "learning_rate": 1.0821962144266382e-05,
+      "loss": 0.3841,
+      "step": 470
+    },
+    {
+      "epoch": 1.85546875,
+      "grad_norm": 1.2045531272888184,
+      "learning_rate": 1.0512537638585379e-05,
+      "loss": 0.3881,
+      "step": 475
+    },
+    {
+      "epoch": 1.875,
+      "grad_norm": 1.2304943799972534,
+      "learning_rate": 1.0205196513972067e-05,
+      "loss": 0.3514,
+      "step": 480
+    },
+    {
+      "epoch": 1.89453125,
+      "grad_norm": 1.1658762693405151,
+      "learning_rate": 9.900081458794346e-06,
+      "loss": 0.3582,
+      "step": 485
+    },
+    {
+      "epoch": 1.9140625,
+      "grad_norm": 1.2731722593307495,
+      "learning_rate": 9.597334127929346e-06,
+      "loss": 0.3891,
+      "step": 490
+    },
+    {
+      "epoch": 1.93359375,
+      "grad_norm": 1.2798595428466797,
+      "learning_rate": 9.297095076997733e-06,
+      "loss": 0.4051,
+      "step": 495
+    },
+    {
+      "epoch": 1.953125,
+      "grad_norm": 1.254543423652649,
+      "learning_rate": 8.99950369710836e-06,
+      "loss": 0.4021,
+      "step": 500
+    },
+    {
+      "epoch": 1.97265625,
+      "grad_norm": 1.2314881086349487,
+      "learning_rate": 8.704698150143564e-06,
+      "loss": 0.3569,
+      "step": 505
+    },
+    {
+      "epoch": 1.9921875,
+      "grad_norm": 1.3078426122665405,
+      "learning_rate": 8.412815304615157e-06,
+      "loss": 0.3819,
+      "step": 510
+    },
+    {
+      "epoch": 2.01171875,
+      "grad_norm": 0.9951373338699341,
+      "learning_rate": 8.123990672120862e-06,
+      "loss": 0.3365,
+      "step": 515
+    },
+    {
+      "epoch": 2.03125,
+      "grad_norm": 1.599310040473938,
+      "learning_rate": 7.838358344430765e-06,
+      "loss": 0.2686,
+      "step": 520
+    },
+    {
+      "epoch": 2.05078125,
+      "grad_norm": 1.2330049276351929,
+      "learning_rate": 7.55605093123291e-06,
+      "loss": 0.2991,
+      "step": 525
+    },
+    {
+      "epoch": 2.0703125,
+      "grad_norm": 1.1340687274932861,
+      "learning_rate": 7.277199498566976e-06,
+      "loss": 0.2869,
+      "step": 530
+    },
+    {
+      "epoch": 2.08984375,
+      "grad_norm": 1.2110050916671753,
+      "learning_rate": 7.001933507974635e-06,
+      "loss": 0.29,
+      "step": 535
+    },
+    {
+      "epoch": 2.109375,
+      "grad_norm": 1.176186442375183,
+      "learning_rate": 6.730380756394818e-06,
+      "loss": 0.3021,
+      "step": 540
+    },
+    {
+      "epoch": 2.12890625,
+      "grad_norm": 1.217549204826355,
+      "learning_rate": 6.462667316831824e-06,
+      "loss": 0.2881,
+      "step": 545
+    },
+    {
+      "epoch": 2.1484375,
+      "grad_norm": 1.2813860177993774,
+      "learning_rate": 6.198917479823733e-06,
+      "loss": 0.2777,
+      "step": 550
+    },
+    {
+      "epoch": 2.16796875,
+      "grad_norm": 1.3627424240112305,
+      "learning_rate": 5.939253695738434e-06,
+      "loss": 0.2532,
+      "step": 555
+    },
+    {
+      "epoch": 2.1875,
+      "grad_norm": 1.1819356679916382,
+      "learning_rate": 5.68379651792393e-06,
+      "loss": 0.294,
+      "step": 560
+    },
+    {
+      "epoch": 2.20703125,
+      "grad_norm": 1.1795055866241455,
+      "learning_rate": 5.4326645467394085e-06,
+      "loss": 0.2935,
+      "step": 565
+    },
+    {
+      "epoch": 2.2265625,
+      "grad_norm": 1.1804410219192505,
+      "learning_rate": 5.185974374492979e-06,
+      "loss": 0.2931,
+      "step": 570
+    },
+    {
+      "epoch": 2.24609375,
+      "grad_norm": 1.5301036834716797,
+      "learning_rate": 4.943840531311686e-06,
+      "loss": 0.286,
+      "step": 575
+    },
+    {
+      "epoch": 2.265625,
+      "grad_norm": 1.734044075012207,
+      "learning_rate": 4.706375431968998e-06,
+      "loss": 0.2608,
+      "step": 580
+    },
+    {
+      "epoch": 2.28515625,
+      "grad_norm": 1.202544927597046,
+      "learning_rate": 4.4736893236942735e-06,
+      "loss": 0.2852,
+      "step": 585
+    },
+    {
+      "epoch": 2.3046875,
+      "grad_norm": 1.522388219833374,
+      "learning_rate": 4.245890234988621e-06,
+      "loss": 0.3045,
+      "step": 590
+    },
+    {
+      "epoch": 2.32421875,
+      "grad_norm": 1.278516411781311,
+      "learning_rate": 4.0230839254708196e-06,
+      "loss": 0.2878,
+      "step": 595
+    },
+    {
+      "epoch": 2.34375,
+      "grad_norm": 1.4243446588516235,
+      "learning_rate": 3.8053738367766254e-06,
+      "loss": 0.3046,
+      "step": 600
+    },
+    {
+      "epoch": 2.36328125,
+      "grad_norm": 1.1980564594268799,
+      "learning_rate": 3.5928610445341937e-06,
+      "loss": 0.307,
+      "step": 605
+    },
+    {
+      "epoch": 2.3828125,
+      "grad_norm": 1.1453922986984253,
+      "learning_rate": 3.3856442114380132e-06,
+      "loss": 0.2887,
+      "step": 610
+    },
+    {
+      "epoch": 2.40234375,
+      "grad_norm": 1.3073961734771729,
+      "learning_rate": 3.183819541443068e-06,
+      "loss": 0.327,
+      "step": 615
+    },
+    {
+      "epoch": 2.421875,
+      "grad_norm": 1.3009051084518433,
+      "learning_rate": 2.98748073510049e-06,
+      "loss": 0.2918,
+      "step": 620
+    },
+    {
+      "epoch": 2.44140625,
+      "grad_norm": 1.2180997133255005,
+      "learning_rate": 2.7967189460554876e-06,
+      "loss": 0.3016,
+      "step": 625
+    },
+    {
+      "epoch": 2.4609375,
+      "grad_norm": 1.227953553199768,
+      "learning_rate": 2.6116227387277087e-06,
+      "loss": 0.2793,
+      "step": 630
+    },
+    {
+      "epoch": 2.48046875,
+      "grad_norm": 1.2680697441101074,
+      "learning_rate": 2.432278047193703e-06,
+      "loss": 0.2915,
+      "step": 635
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 1.1802301406860352,
+      "learning_rate": 2.2587681352905404e-06,
+      "loss": 0.2843,
+      "step": 640
+    },
+    {
+      "epoch": 2.51953125,
+      "grad_norm": 1.2685930728912354,
+      "learning_rate": 2.091173557959164e-06,
+      "loss": 0.305,
+      "step": 645
+    },
+    {
+      "epoch": 2.5390625,
+      "grad_norm": 1.170775294303894,
+      "learning_rate": 1.9295721238453816e-06,
+      "loss": 0.2883,
+      "step": 650
+    },
+    {
+      "epoch": 2.55859375,
+      "grad_norm": 1.2129031419754028,
+      "learning_rate": 1.77403885917588e-06,
+      "loss": 0.2999,
+      "step": 655
+    },
+    {
+      "epoch": 2.578125,
+      "grad_norm": 1.3644816875457764,
+      "learning_rate": 1.6246459729259978e-06,
+      "loss": 0.2833,
+      "step": 660
+    },
+    {
+      "epoch": 2.59765625,
+      "grad_norm": 1.2289398908615112,
+      "learning_rate": 1.481462823295492e-06,
+      "loss": 0.2452,
+      "step": 665
+    },
+    {
+      "epoch": 2.6171875,
+      "grad_norm": 1.378744125366211,
+      "learning_rate": 1.3445558855078017e-06,
+      "loss": 0.3102,
+      "step": 670
+    },
+    {
+      "epoch": 2.63671875,
+      "grad_norm": 1.2663036584854126,
+      "learning_rate": 1.2139887209477923e-06,
+      "loss": 0.2908,
+      "step": 675
+    },
+    {
+      "epoch": 2.65625,
+      "grad_norm": 1.237650990486145,
+      "learning_rate": 1.0898219476522992e-06,
+      "loss": 0.3005,
+      "step": 680
+    },
+    {
+      "epoch": 2.67578125,
+      "grad_norm": 1.25255286693573,
+      "learning_rate": 9.721132121671556e-07,
+      "loss": 0.2617,
+      "step": 685
+    },
+    {
+      "epoch": 2.6953125,
+      "grad_norm": 1.2143943309783936,
+      "learning_rate": 8.609171627838202e-07,
+      "loss": 0.2833,
+      "step": 690
+    },
+    {
+      "epoch": 2.71484375,
+      "grad_norm": 1.3464289903640747,
+      "learning_rate": 7.562854241679573e-07,
+      "loss": 0.3068,
+      "step": 695
+    },
+    {
+      "epoch": 2.734375,
+      "grad_norm": 1.2480183839797974,
+      "learning_rate": 6.582665733918064e-07,
+      "loss": 0.2784,
+      "step": 700
+    },
+    {
+      "epoch": 2.75390625,
+      "grad_norm": 1.0904308557510376,
+      "learning_rate": 5.669061173814499e-07,
+      "loss": 0.2706,
+      "step": 705
+    },
+    {
+      "epoch": 2.7734375,
+      "grad_norm": 1.2050496339797974,
+      "learning_rate": 4.822464717894482e-07,
+      "loss": 0.2671,
+      "step": 710
+    },
+    {
+      "epoch": 2.79296875,
+      "grad_norm": 1.3271524906158447,
+      "learning_rate": 4.043269413026429e-07,
+      "loss": 0.257,
+      "step": 715
+    },
+    {
+      "epoch": 2.8125,
+      "grad_norm": 1.2165964841842651,
+      "learning_rate": 3.331837013942829e-07,
+      "loss": 0.3122,
+      "step": 720
+    },
+    {
+      "epoch": 2.83203125,
+      "grad_norm": 1.0533255338668823,
+      "learning_rate": 2.688497815289465e-07,
+      "loss": 0.3064,
+      "step": 725
+    },
+    {
+      "epoch": 2.8515625,
+      "grad_norm": 1.3498057126998901,
+      "learning_rate": 2.113550498280531e-07,
+      "loss": 0.2668,
+      "step": 730
+    },
+    {
+      "epoch": 2.87109375,
+      "grad_norm": 1.2211068868637085,
+      "learning_rate": 1.6072619920306563e-07,
+      "loss": 0.2734,
+      "step": 735
+    },
+    {
+      "epoch": 2.890625,
+      "grad_norm": 1.257903814315796,
+      "learning_rate": 1.1698673496285839e-07,
+      "loss": 0.2501,
+      "step": 740
+    },
+    {
+      "epoch": 2.91015625,
+      "grad_norm": 1.1989271640777588,
+      "learning_rate": 8.015696390097805e-08,
+      "loss": 0.2614,
+      "step": 745
+    },
+    {
+      "epoch": 2.9296875,
+      "grad_norm": 1.2453311681747437,
+      "learning_rate": 5.025398486786015e-08,
+      "loss": 0.2695,
+      "step": 750
+    },
+    {
+      "epoch": 2.94921875,
+      "grad_norm": 1.1606556177139282,
+      "learning_rate": 2.7291680832400854e-08,
+      "loss": 0.2824,
+      "step": 755
+    },
+    {
+      "epoch": 2.96875,
+      "grad_norm": 1.2463587522506714,
+      "learning_rate": 1.1280712436549379e-08,
+      "loss": 0.273,
+      "step": 760
+    },
+    {
+      "epoch": 2.98828125,
+      "grad_norm": 1.1878907680511475,
+      "learning_rate": 2.2285130459237523e-09,
+      "loss": 0.2726,
+      "step": 765
+    },
+    {
+      "epoch": 3.0,
+      "step": 768,
+      "total_flos": 1.129602491848065e+18,
+      "train_loss": 0.5587638872675598,
+      "train_runtime": 537.1777,
+      "train_samples_per_second": 45.672,
+      "train_steps_per_second": 1.43
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 768,
+  "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": 1.129602491848065e+18,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

17_128_e3_3e-5/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:329361aedcbe9505fde2a03a8bb4983d8260fb2f31d4d4caebad99b3aaeb516f
+size 8145