SFT DeepSeek-R1-14B ck137

.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

adapter_config.json

@@ -0,0 +1,48 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "deepseek-ai/DeepSeek-R1-Distill-Qwen-14B",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "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": 128,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.19.1",
+  "qalora_group_size": 16,
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "o_proj",
+    "k_proj",
+    "q_proj",
+    "gate_proj",
+    "down_proj",
+    "v_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c784fd133b96b25bea04cb4ade7490771c2591abdf2a1b3393e7d6e04b68760d
+size 1101095848

chat_template.jinja

@@ -0,0 +1 @@
+{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set ns = namespace(is_first=false, is_tool=false, is_output_first=true, system_prompt='') %}{%- for message in messages %}{%- if message['role'] == 'system' %}{% set ns.system_prompt = message['content'] %}{%- endif %}{%- endfor %}{{bos_token}}{{ns.system_prompt}}{%- for message in messages %}{%- if message['role'] == 'user' %}{%- set ns.is_tool = false -%}{{'<｜User｜>' + message['content']}}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is none %}{%- set ns.is_tool = false -%}{%- for tool in message['tool_calls']%}{%- if not ns.is_first %}{{'<｜Assistant｜><｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\n' + '```json' + '\n' + tool['function']['arguments'] + '\n' + '```' + '<｜tool▁call▁end｜>'}}{%- set ns.is_first = true -%}{%- else %}{{'\n' + '<｜tool▁call▁begin｜>' + tool['type'] + '<｜tool▁sep｜>' + tool['function']['name'] + '\n' + '```json' + '\n' + tool['function']['arguments'] + '\n' + '```' + '<｜tool▁call▁end｜>'}}{{'<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}{%- endif %}{%- endfor %}{%- endif %}{%- if message['role'] == 'assistant' and message['content'] is not none %}{%- if ns.is_tool %}{{'<｜tool▁outputs▁end｜>' + message['content'] + '<｜end▁of▁sentence｜>'}}{%- set ns.is_tool = false -%}{%- else %}{% set content = message['content'] %}{% if '</think>' in content %}{% set content = content.split('</think>')[-1] %}{% endif %}{{'<｜Assistant｜>' + content + '<｜end▁of▁sentence｜>'}}{%- endif %}{%- endif %}{%- if message['role'] == 'tool' %}{%- set ns.is_tool = true -%}{%- if ns.is_output_first %}{{'<｜tool▁outputs▁begin｜><｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- set ns.is_output_first = false %}{%- else %}{{'\n<｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}{%- endif %}{%- endif %}{%- endfor -%}{% if ns.is_tool %}{{'<｜tool▁outputs▁end｜>'}}{% endif %}{% if add_generation_prompt and not ns.is_tool %}{{'<｜Assistant｜><think>\n'}}{% endif %}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b926cdcc84559848f4b1587aa16e79b05ef44bf58aaf1063fe0d03853bf2738
+size 559915301

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:548a3f7cdc74203805a9efb1d99382277f41a9555d91fd96f49768eb056c2ea9
+size 14645

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a00e258c784e47e6b17fbdfadf1b3fcab20e1474570f38acbccb4565ef8efa7
+size 1465

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f624f8136bc57382156e7595e8ea404a66fbce12e3181b933ec2459bda3a71be
+size 11421907

tokenizer_config.json

@@ -0,0 +1,15 @@
+{
+  "add_prefix_space": null,
+  "backend": "tokenizers",
+  "bos_token": "<｜begin▁of▁sentence｜>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<｜end▁of▁sentence｜>",
+  "is_local": false,
+  "legacy": true,
+  "local_files_only": true,
+  "model_max_length": 16384,
+  "pad_token": "<｜end▁of▁sentence｜>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_state.json

@@ -0,0 +1,304 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 137,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 1.12497947961092,
+      "epoch": 0.03673094582185491,
+      "grad_norm": 0.8993809819221497,
+      "learning_rate": 3.0769230769230774e-05,
+      "loss": 1.8966182708740233,
+      "mean_token_accuracy": 0.5981592454016209,
+      "num_tokens": 392451.0,
+      "step": 5
+    },
+    {
+      "entropy": 1.3978254437446593,
+      "epoch": 0.07346189164370982,
+      "grad_norm": 0.4200671911239624,
+      "learning_rate": 6.923076923076924e-05,
+      "loss": 1.6123085021972656,
+      "mean_token_accuracy": 0.6334522105753422,
+      "num_tokens": 780460.0,
+      "step": 10
+    },
+    {
+      "entropy": 1.4284753248095512,
+      "epoch": 0.11019283746556474,
+      "grad_norm": 0.5383214354515076,
+      "learning_rate": 9.999844234470782e-05,
+      "loss": 1.1326273918151855,
+      "mean_token_accuracy": 0.7270047955214978,
+      "num_tokens": 1170277.0,
+      "step": 15
+    },
+    {
+      "entropy": 0.5256051793694496,
+      "epoch": 0.14692378328741965,
+      "grad_norm": 0.32786956429481506,
+      "learning_rate": 9.994393459922218e-05,
+      "loss": 0.5460782527923584,
+      "mean_token_accuracy": 0.8675555787980557,
+      "num_tokens": 1562948.0,
+      "step": 20
+    },
+    {
+      "entropy": 0.2676012733951211,
+      "epoch": 0.18365472910927455,
+      "grad_norm": 0.12770651280879974,
+      "learning_rate": 9.981164111355035e-05,
+      "loss": 0.29712226390838625,
+      "mean_token_accuracy": 0.9294811107218266,
+      "num_tokens": 1950156.0,
+      "step": 25
+    },
+    {
+      "entropy": 0.2584058292210102,
+      "epoch": 0.22038567493112948,
+      "grad_norm": 0.0914032906293869,
+      "learning_rate": 9.960176792966289e-05,
+      "loss": 0.25907483100891116,
+      "mean_token_accuracy": 0.9349191218614579,
+      "num_tokens": 2339119.0,
+      "step": 30
+    },
+    {
+      "entropy": 0.25888317823410034,
+      "epoch": 0.2571166207529844,
+      "grad_norm": 0.08953554928302765,
+      "learning_rate": 9.931464191690015e-05,
+      "loss": 0.2529557943344116,
+      "mean_token_accuracy": 0.9351828552782535,
+      "num_tokens": 2734551.0,
+      "step": 35
+    },
+    {
+      "entropy": 0.22340067327022553,
+      "epoch": 0.2938475665748393,
+      "grad_norm": 0.07802692800760269,
+      "learning_rate": 9.895071026288574e-05,
+      "loss": 0.221995210647583,
+      "mean_token_accuracy": 0.9419150903820992,
+      "num_tokens": 3120046.0,
+      "step": 40
+    },
+    {
+      "entropy": 0.21697051208466292,
+      "epoch": 0.3305785123966942,
+      "grad_norm": 0.08155567944049835,
+      "learning_rate": 9.851053977704931e-05,
+      "loss": 0.22191472053527833,
+      "mean_token_accuracy": 0.9412054426968097,
+      "num_tokens": 3508920.0,
+      "step": 45
+    },
+    {
+      "entropy": 0.2017911121249199,
+      "epoch": 0.3673094582185491,
+      "grad_norm": 0.07083539664745331,
+      "learning_rate": 9.799481600784286e-05,
+      "loss": 0.20391447544097902,
+      "mean_token_accuracy": 0.9452535562217236,
+      "num_tokens": 3894334.0,
+      "step": 50
+    },
+    {
+      "entropy": 0.20160430558025838,
+      "epoch": 0.40404040404040403,
+      "grad_norm": 0.06837889552116394,
+      "learning_rate": 9.740434217502547e-05,
+      "loss": 0.20340940952301026,
+      "mean_token_accuracy": 0.9446921683847904,
+      "num_tokens": 4281402.0,
+      "step": 55
+    },
+    {
+      "entropy": 0.20042244642972945,
+      "epoch": 0.44077134986225897,
+      "grad_norm": 0.08252335339784622,
+      "learning_rate": 9.674003791867991e-05,
+      "loss": 0.2018129348754883,
+      "mean_token_accuracy": 0.9447339937090874,
+      "num_tokens": 4663548.0,
+      "step": 60
+    },
+    {
+      "entropy": 0.19784397445619106,
+      "epoch": 0.47750229568411384,
+      "grad_norm": 0.07859351485967636,
+      "learning_rate": 9.600293786690872e-05,
+      "loss": 0.19837383031845093,
+      "mean_token_accuracy": 0.9450356759130955,
+      "num_tokens": 5049145.0,
+      "step": 65
+    },
+    {
+      "entropy": 0.1947242783382535,
+      "epoch": 0.5142332415059688,
+      "grad_norm": 0.07524942606687546,
+      "learning_rate": 9.51941900244412e-05,
+      "loss": 0.19666141271591187,
+      "mean_token_accuracy": 0.9454756386578083,
+      "num_tokens": 5436189.0,
+      "step": 70
+    },
+    {
+      "entropy": 0.19588824408128858,
+      "epoch": 0.5509641873278237,
+      "grad_norm": 0.07221005856990814,
+      "learning_rate": 9.431505398466045e-05,
+      "loss": 0.19920532703399657,
+      "mean_token_accuracy": 0.9449514284729957,
+      "num_tokens": 5829408.0,
+      "step": 75
+    },
+    {
+      "entropy": 0.19220142532140017,
+      "epoch": 0.5876951331496786,
+      "grad_norm": 0.07809904962778091,
+      "learning_rate": 9.336689896783573e-05,
+      "loss": 0.19279507398605347,
+      "mean_token_accuracy": 0.9458583235740662,
+      "num_tokens": 6218941.0,
+      "step": 80
+    },
+    {
+      "entropy": 0.18541973838582634,
+      "epoch": 0.6244260789715336,
+      "grad_norm": 0.07320163398981094,
+      "learning_rate": 9.235120168861496e-05,
+      "loss": 0.1880725622177124,
+      "mean_token_accuracy": 0.9469495385885238,
+      "num_tokens": 6606033.0,
+      "step": 85
+    },
+    {
+      "entropy": 0.1838523769751191,
+      "epoch": 0.6611570247933884,
+      "grad_norm": 0.07499408721923828,
+      "learning_rate": 9.126954405609882e-05,
+      "loss": 0.18436297178268432,
+      "mean_token_accuracy": 0.9477912008762359,
+      "num_tokens": 6993613.0,
+      "step": 90
+    },
+    {
+      "entropy": 0.18930766182020306,
+      "epoch": 0.6978879706152433,
+      "grad_norm": 0.0816631019115448,
+      "learning_rate": 9.012361071007891e-05,
+      "loss": 0.19324288368225098,
+      "mean_token_accuracy": 0.946058064699173,
+      "num_tokens": 7390817.0,
+      "step": 95
+    },
+    {
+      "entropy": 0.18645640034228564,
+      "epoch": 0.7346189164370982,
+      "grad_norm": 0.07840832322835922,
+      "learning_rate": 8.891518639727649e-05,
+      "loss": 0.18845387697219848,
+      "mean_token_accuracy": 0.9464856244623661,
+      "num_tokens": 7784854.0,
+      "step": 100
+    },
+    {
+      "entropy": 0.17504646591842174,
+      "epoch": 0.7713498622589532,
+      "grad_norm": 0.07297156751155853,
+      "learning_rate": 8.764615319166886e-05,
+      "loss": 0.1781143069267273,
+      "mean_token_accuracy": 0.9493056297302246,
+      "num_tokens": 8166437.0,
+      "step": 105
+    },
+    {
+      "entropy": 0.17095539206638932,
+      "epoch": 0.8080808080808081,
+      "grad_norm": 0.0789044052362442,
+      "learning_rate": 8.631848756323197e-05,
+      "loss": 0.17464057207107545,
+      "mean_token_accuracy": 0.9500580169260502,
+      "num_tokens": 8553224.0,
+      "step": 110
+    },
+    {
+      "entropy": 0.17393150376155972,
+      "epoch": 0.8448117539026629,
+      "grad_norm": 0.07846875488758087,
+      "learning_rate": 8.493425729966534e-05,
+      "loss": 0.1741488456726074,
+      "mean_token_accuracy": 0.9500745631754398,
+      "num_tokens": 8941103.0,
+      "step": 115
+    },
+    {
+      "entropy": 0.17150701954960823,
+      "epoch": 0.8815426997245179,
+      "grad_norm": 0.0809190571308136,
+      "learning_rate": 8.349561828589277e-05,
+      "loss": 0.17422133684158325,
+      "mean_token_accuracy": 0.9498188808560372,
+      "num_tokens": 9327685.0,
+      "step": 120
+    },
+    {
+      "entropy": 0.17129514068365098,
+      "epoch": 0.9182736455463728,
+      "grad_norm": 0.07602571696043015,
+      "learning_rate": 8.200481114635536e-05,
+      "loss": 0.17384564876556396,
+      "mean_token_accuracy": 0.9498213849961757,
+      "num_tokens": 9715967.0,
+      "step": 125
+    },
+    {
+      "entropy": 0.17661647107452155,
+      "epoch": 0.9550045913682277,
+      "grad_norm": 0.08382342010736465,
+      "learning_rate": 8.046415775532585e-05,
+      "loss": 0.17854903936386107,
+      "mean_token_accuracy": 0.9487794756889343,
+      "num_tokens": 10103714.0,
+      "step": 130
+    },
+    {
+      "entropy": 0.17341060359030963,
+      "epoch": 0.9917355371900827,
+      "grad_norm": 0.07687266916036606,
+      "learning_rate": 7.887605762067945e-05,
+      "loss": 0.17285407781600953,
+      "mean_token_accuracy": 0.9503463752567768,
+      "num_tokens": 10488946.0,
+      "step": 135
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 411,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 9.054554389471212e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b795cebea5f6e80b75b46706ae2518da1e1898b7315ad9d14b82870321b1358f
+size 5649