Training in progress, epoch 0

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* 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
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,68 @@
+---
+library_name: peft
+license: mit
+base_model: microsoft/Phi-4-mini-instruct
+tags:
+- llama-factory
+- lora
+- generated_from_trainer
+model-index:
+- name: Phi-4-mini-instruct_sft_sg_values
+  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. -->
+
+# Phi-4-mini-instruct_sft_sg_values
+
+This model is a fine-tuned version of [microsoft/Phi-4-mini-instruct](https://huggingface.co/microsoft/Phi-4-mini-instruct) on the sft_sg_values dataset.
+It achieves the following results on the evaluation set:
+- Loss: 2.3848
+
+## 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: 1e-06
+- train_batch_size: 2
+- eval_batch_size: 2
+- seed: 42
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 8
+- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 1.0
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 4.3614        | 0.1869 | 250  | 4.1655          |
+| 3.3914        | 0.3738 | 500  | 3.1697          |
+| 2.684         | 0.5607 | 750  | 2.6262          |
+| 2.5099        | 0.7477 | 1000 | 2.4442          |
+| 2.3706        | 0.9346 | 1250 | 2.3880          |
+
+
+### Framework versions
+
+- PEFT 0.15.2
+- Transformers 4.51.1
+- Pytorch 2.6.0+cu124
+- Datasets 3.2.0
+- Tokenizers 0.21.1

adapter_config.json

@@ -0,0 +1,36 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "microsoft/Phi-4-mini-instruct",
+  "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": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_up_proj",
+    "o_proj",
+    "down_proj",
+    "qkv_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a85aa260d38a7c48c9d05e7914d7f5b776c97353b40c5c5380c63da095d1afa6
+size 46171456

added_tokens.json

@@ -0,0 +1,13 @@
+{
+  "<|/tool_call|>": 200026,
+  "<|/tool|>": 200024,
+  "<|assistant|>": 200019,
+  "<|end|>": 200020,
+  "<|im_end|>": 200029,
+  "<|system|>": 200022,
+  "<|tag|>": 200028,
+  "<|tool_call|>": 200025,
+  "<|tool_response|>": 200027,
+  "<|tool|>": 200023,
+  "<|user|>": 200021
+}

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 0.9996261682242991,
+    "eval_loss": 2.384812116622925,
+    "eval_runtime": 18.1789,
+    "eval_samples_per_second": 27.504,
+    "eval_steps_per_second": 13.752,
+    "total_flos": 4.450466167504896e+16,
+    "train_loss": 3.11931433781101,
+    "train_runtime": 1360.775,
+    "train_samples_per_second": 7.863,
+    "train_steps_per_second": 0.983
+}

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 0.9996261682242991,
+    "eval_loss": 2.384812116622925,
+    "eval_runtime": 18.1789,
+    "eval_samples_per_second": 27.504,
+    "eval_steps_per_second": 13.752
+}

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8799b7ce62bf40e724f80af87b9545f9d9043778f435040a6c08e834dc047b69
+size 15524282

tokenizer_config.json

@@ -0,0 +1,122 @@
+{
+  "add_bos_token": false,
+  "add_eos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "199999": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200018": {
+      "content": "<|endofprompt|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "200019": {
+      "content": "<|assistant|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "200020": {
+      "content": "<|end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "200021": {
+      "content": "<|user|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "200022": {
+      "content": "<|system|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "200023": {
+      "content": "<|tool|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "200024": {
+      "content": "<|/tool|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "200025": {
+      "content": "<|tool_call|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "200026": {
+      "content": "<|/tool_call|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "200027": {
+      "content": "<|tool_response|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "200028": {
+      "content": "<|tag|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "200029": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "chat_template": "{% for message in messages %}{% if message['role'] == 'system' and 'tools' in message and message['tools'] is not none %}{{ '<|' + message['role'] + '|>' + message['content'] + '<|tool|>' + message['tools'] + '<|/tool|>' + '<|end|>' }}{% else %}{{ '<|' + message['role'] + '|>' + message['content'] + '<|end|>' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>' }}{% else %}{{ eos_token }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.9996261682242991,
+    "total_flos": 4.450466167504896e+16,
+    "train_loss": 3.11931433781101,
+    "train_runtime": 1360.775,
+    "train_samples_per_second": 7.863,
+    "train_steps_per_second": 0.983
+}

trainer_log.jsonl

@@ -0,0 +1,25 @@
+{"current_steps": 74, "total_steps": 1462, "loss": 4.4344, "lr": 4.965986394557823e-07, "epoch": 0.05060694135749701, "percentage": 5.06, "elapsed_time": "0:01:08", "remaining_time": "0:21:30"}
+{"current_steps": 148, "total_steps": 1462, "loss": 4.4596, "lr": 1e-06, "epoch": 0.10121388271499401, "percentage": 10.12, "elapsed_time": "0:02:18", "remaining_time": "0:20:25"}
+{"current_steps": 222, "total_steps": 1462, "loss": 4.3698, "lr": 9.437262357414448e-07, "epoch": 0.15182082407249103, "percentage": 15.18, "elapsed_time": "0:03:27", "remaining_time": "0:19:17"}
+{"current_steps": 250, "total_steps": 1462, "eval_loss": 4.173080921173096, "epoch": 0.17096939647803044, "percentage": 17.1, "elapsed_time": "0:04:11", "remaining_time": "0:20:21"}
+{"current_steps": 296, "total_steps": 1462, "loss": 4.1264, "lr": 8.874524714828897e-07, "epoch": 0.20242776542998803, "percentage": 20.25, "elapsed_time": "0:04:54", "remaining_time": "0:19:21"}
+{"current_steps": 370, "total_steps": 1462, "loss": 3.8829, "lr": 8.311787072243346e-07, "epoch": 0.253034706787485, "percentage": 25.31, "elapsed_time": "0:06:04", "remaining_time": "0:17:55"}
+{"current_steps": 444, "total_steps": 1462, "loss": 3.5096, "lr": 7.749049429657795e-07, "epoch": 0.30364164814498207, "percentage": 30.37, "elapsed_time": "0:07:13", "remaining_time": "0:16:33"}
+{"current_steps": 500, "total_steps": 1462, "eval_loss": 3.149691581726074, "epoch": 0.3419387929560609, "percentage": 34.2, "elapsed_time": "0:08:23", "remaining_time": "0:16:09"}
+{"current_steps": 518, "total_steps": 1462, "loss": 3.1506, "lr": 7.186311787072243e-07, "epoch": 0.35424858950247906, "percentage": 35.43, "elapsed_time": "0:08:40", "remaining_time": "0:15:48"}
+{"current_steps": 592, "total_steps": 1462, "loss": 2.9908, "lr": 6.623574144486692e-07, "epoch": 0.40485553085997605, "percentage": 40.49, "elapsed_time": "0:09:49", "remaining_time": "0:14:26"}
+{"current_steps": 666, "total_steps": 1462, "loss": 2.7593, "lr": 6.060836501901141e-07, "epoch": 0.45546247221747305, "percentage": 45.55, "elapsed_time": "0:10:58", "remaining_time": "0:13:07"}
+{"current_steps": 740, "total_steps": 1462, "loss": 2.6213, "lr": 5.498098859315589e-07, "epoch": 0.50606941357497, "percentage": 50.62, "elapsed_time": "0:12:07", "remaining_time": "0:11:50"}
+{"current_steps": 750, "total_steps": 1462, "eval_loss": 2.573621988296509, "epoch": 0.5129081894340913, "percentage": 51.3, "elapsed_time": "0:12:35", "remaining_time": "0:11:57"}
+{"current_steps": 814, "total_steps": 1462, "loss": 2.5332, "lr": 4.935361216730038e-07, "epoch": 0.5566763549324671, "percentage": 55.68, "elapsed_time": "0:13:34", "remaining_time": "0:10:48"}
+{"current_steps": 888, "total_steps": 1462, "loss": 2.484, "lr": 4.372623574144487e-07, "epoch": 0.6072832962899641, "percentage": 60.74, "elapsed_time": "0:14:44", "remaining_time": "0:09:31"}
+{"current_steps": 962, "total_steps": 1462, "loss": 2.4305, "lr": 3.8098859315589356e-07, "epoch": 0.6578902376474611, "percentage": 65.8, "elapsed_time": "0:15:52", "remaining_time": "0:08:15"}
+{"current_steps": 1000, "total_steps": 1462, "eval_loss": 2.3979878425598145, "epoch": 0.6838775859121218, "percentage": 68.4, "elapsed_time": "0:16:46", "remaining_time": "0:07:45"}
+{"current_steps": 1036, "total_steps": 1462, "loss": 2.3982, "lr": 3.247148288973384e-07, "epoch": 0.7084971790049581, "percentage": 70.86, "elapsed_time": "0:17:20", "remaining_time": "0:07:07"}
+{"current_steps": 1110, "total_steps": 1462, "loss": 2.3504, "lr": 2.6844106463878326e-07, "epoch": 0.7591041203624551, "percentage": 75.92, "elapsed_time": "0:18:28", "remaining_time": "0:05:51"}
+{"current_steps": 1184, "total_steps": 1462, "loss": 2.3653, "lr": 2.1216730038022811e-07, "epoch": 0.8097110617199521, "percentage": 80.98, "elapsed_time": "0:19:37", "remaining_time": "0:04:36"}
+{"current_steps": 1250, "total_steps": 1462, "eval_loss": 2.334463119506836, "epoch": 0.8548469823901521, "percentage": 85.5, "elapsed_time": "0:20:57", "remaining_time": "0:03:33"}
+{"current_steps": 1258, "total_steps": 1462, "loss": 2.317, "lr": 1.55893536121673e-07, "epoch": 0.8603180030774491, "percentage": 86.05, "elapsed_time": "0:21:05", "remaining_time": "0:03:25"}
+{"current_steps": 1332, "total_steps": 1462, "loss": 2.3346, "lr": 9.961977186311786e-08, "epoch": 0.9109249444349461, "percentage": 91.11, "elapsed_time": "0:22:15", "remaining_time": "0:02:10"}
+{"current_steps": 1406, "total_steps": 1462, "loss": 2.3081, "lr": 4.3346007604562734e-08, "epoch": 0.9615318857924432, "percentage": 96.17, "elapsed_time": "0:23:24", "remaining_time": "0:00:55"}
+{"current_steps": 1462, "total_steps": 1462, "epoch": 0.999829030603522, "percentage": 100.0, "elapsed_time": "0:24:18", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,216 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9996261682242991,
+  "eval_steps": 250,
+  "global_step": 1337,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.05009345794392523,
+      "grad_norm": 3.513535261154175,
+      "learning_rate": 4.925373134328357e-07,
+      "loss": 4.4864,
+      "step": 67
+    },
+    {
+      "epoch": 0.10018691588785046,
+      "grad_norm": 4.232038974761963,
+      "learning_rate": 9.925373134328357e-07,
+      "loss": 4.4815,
+      "step": 134
+    },
+    {
+      "epoch": 0.1502803738317757,
+      "grad_norm": 3.0024209022521973,
+      "learning_rate": 9.451371571072319e-07,
+      "loss": 4.3614,
+      "step": 201
+    },
+    {
+      "epoch": 0.18691588785046728,
+      "eval_loss": 4.165477752685547,
+      "eval_runtime": 18.4458,
+      "eval_samples_per_second": 27.107,
+      "eval_steps_per_second": 13.553,
+      "step": 250
+    },
+    {
+      "epoch": 0.20037383177570092,
+      "grad_norm": 4.35124397277832,
+      "learning_rate": 8.894430590191188e-07,
+      "loss": 4.1954,
+      "step": 268
+    },
+    {
+      "epoch": 0.2504672897196262,
+      "grad_norm": 4.761136531829834,
+      "learning_rate": 8.337489609310058e-07,
+      "loss": 3.9922,
+      "step": 335
+    },
+    {
+      "epoch": 0.3005607476635514,
+      "grad_norm": 5.12410831451416,
+      "learning_rate": 7.780548628428927e-07,
+      "loss": 3.6946,
+      "step": 402
+    },
+    {
+      "epoch": 0.3506542056074766,
+      "grad_norm": 4.370376110076904,
+      "learning_rate": 7.223607647547797e-07,
+      "loss": 3.3914,
+      "step": 469
+    },
+    {
+      "epoch": 0.37383177570093457,
+      "eval_loss": 3.1697182655334473,
+      "eval_runtime": 18.4011,
+      "eval_samples_per_second": 27.172,
+      "eval_steps_per_second": 13.586,
+      "step": 500
+    },
+    {
+      "epoch": 0.40074766355140184,
+      "grad_norm": 3.3430747985839844,
+      "learning_rate": 6.666666666666666e-07,
+      "loss": 3.154,
+      "step": 536
+    },
+    {
+      "epoch": 0.4508411214953271,
+      "grad_norm": 4.1145734786987305,
+      "learning_rate": 6.109725685785536e-07,
+      "loss": 2.9973,
+      "step": 603
+    },
+    {
+      "epoch": 0.5009345794392523,
+      "grad_norm": 3.4338088035583496,
+      "learning_rate": 5.552784704904405e-07,
+      "loss": 2.815,
+      "step": 670
+    },
+    {
+      "epoch": 0.5510280373831775,
+      "grad_norm": 3.3768129348754883,
+      "learning_rate": 4.995843724023275e-07,
+      "loss": 2.684,
+      "step": 737
+    },
+    {
+      "epoch": 0.5607476635514018,
+      "eval_loss": 2.6262145042419434,
+      "eval_runtime": 18.4215,
+      "eval_samples_per_second": 27.142,
+      "eval_steps_per_second": 13.571,
+      "step": 750
+    },
+    {
+      "epoch": 0.6011214953271028,
+      "grad_norm": 2.7695705890655518,
+      "learning_rate": 4.438902743142144e-07,
+      "loss": 2.6152,
+      "step": 804
+    },
+    {
+      "epoch": 0.6512149532710281,
+      "grad_norm": 2.307760715484619,
+      "learning_rate": 3.881961762261014e-07,
+      "loss": 2.5592,
+      "step": 871
+    },
+    {
+      "epoch": 0.7013084112149532,
+      "grad_norm": 2.533203125,
+      "learning_rate": 3.3250207813798835e-07,
+      "loss": 2.5099,
+      "step": 938
+    },
+    {
+      "epoch": 0.7476635514018691,
+      "eval_loss": 2.444204807281494,
+      "eval_runtime": 18.3848,
+      "eval_samples_per_second": 27.196,
+      "eval_steps_per_second": 13.598,
+      "step": 1000
+    },
+    {
+      "epoch": 0.7514018691588785,
+      "grad_norm": 1.7434587478637695,
+      "learning_rate": 2.7680798004987534e-07,
+      "loss": 2.4359,
+      "step": 1005
+    },
+    {
+      "epoch": 0.8014953271028037,
+      "grad_norm": 2.9051830768585205,
+      "learning_rate": 2.2111388196176226e-07,
+      "loss": 2.4193,
+      "step": 1072
+    },
+    {
+      "epoch": 0.851588785046729,
+      "grad_norm": 2.5767340660095215,
+      "learning_rate": 1.6541978387364923e-07,
+      "loss": 2.4261,
+      "step": 1139
+    },
+    {
+      "epoch": 0.9016822429906542,
+      "grad_norm": 1.5444096326828003,
+      "learning_rate": 1.0972568578553615e-07,
+      "loss": 2.3706,
+      "step": 1206
+    },
+    {
+      "epoch": 0.9345794392523364,
+      "eval_loss": 2.3879618644714355,
+      "eval_runtime": 18.3821,
+      "eval_samples_per_second": 27.2,
+      "eval_steps_per_second": 13.6,
+      "step": 1250
+    },
+    {
+      "epoch": 0.9517757009345794,
+      "grad_norm": 2.0951781272888184,
+      "learning_rate": 5.403158769742311e-08,
+      "loss": 2.3796,
+      "step": 1273
+    },
+    {
+      "epoch": 0.9996261682242991,
+      "step": 1337,
+      "total_flos": 4.450466167504896e+16,
+      "train_loss": 3.11931433781101,
+      "train_runtime": 1360.775,
+      "train_samples_per_second": 7.863,
+      "train_steps_per_second": 0.983
+    }
+  ],
+  "logging_steps": 67,
+  "max_steps": 1337,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4.450466167504896e+16,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e2164ae028b12e3863c1198001f37bc834491baffa8cf9969a346360bc0112f
+size 5752