Training in progress, step 3000

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:69e75ae7e1f69a41e91706ac778c4176886a39e991e0545bde52d6c1f744f678
+oid sha256:3768dd1339753637e98fb5a78e49089bfc20cfbb2e5d5ab1d79b249f12bd91d6
 size 500897101

checkpoint-2600/adapter_model/adapter_config.json

@@ -1,26 +0,0 @@
-{
-  "auto_mapping": null,
-  "base_model_name_or_path": "/workspace/webui/models/TheBloke_Llama-2-13B-fp16",
-  "bias": "none",
-  "fan_in_fan_out": null,
-  "inference_mode": true,
-  "init_lora_weights": true,
-  "layers_pattern": null,
-  "layers_to_transform": null,
-  "lora_alpha": 16,
-  "lora_dropout": 0.05,
-  "modules_to_save": null,
-  "peft_type": "LORA",
-  "r": 32,
-  "revision": null,
-  "target_modules": [
-    "v_proj",
-    "o_proj",
-    "down_proj",
-    "q_proj",
-    "gate_proj",
-    "up_proj",
-    "k_proj"
-  ],
-  "task_type": "CAUSAL_LM"
-}

checkpoint-2600/adapter_model/adapter_model.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:56dc05e4b75a13b83ba7370f0c76297d690a74a3feda12d5b102e996353b81b9
-size 500897101

checkpoint-2600/rng_state_0.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:0912fca65962b5a2eae5b3a2f02a0781dfce080830156eafc75210ab50cce11f
-size 27772

checkpoint-2600/rng_state_10.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:9bc002d47c306eaf39badd1745ba64746a2454f02d1895e497a0a018c2f55519
-size 27789

checkpoint-2600/rng_state_11.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:6944bfba0db1a3496823e962d67c67720ce60c56929358ec9d6393dbc0392519
-size 27789

checkpoint-2600/rng_state_13.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:520507119187dd3a1ed2573026f48344953fb3370b827f752fa7a48c95b5284e
-size 27789

checkpoint-2600/rng_state_2.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:dee3265539f2932bd9c5e447892f5d9572b40947ff788f317f50efbeaf431e1e
-size 27772

checkpoint-2600/rng_state_3.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:7f3fc5de4443bd4983b99f2bddc59d4f9e40e5317cf99f9d620bdce259405432
-size 27772

checkpoint-2600/trainer_state.json

@@ -1,632 +0,0 @@
-{
-  "best_metric": null,
-  "best_model_checkpoint": null,
-  "epoch": 1.0081426909654905,
-  "global_step": 2600,
-  "is_hyper_param_search": false,
-  "is_local_process_zero": true,
-  "is_world_process_zero": true,
-  "log_history": [
-    {
-      "epoch": 0.02,
-      "learning_rate": 0.0001999867761371633,
-      "loss": 1.0435,
-      "step": 50
-    },
-    {
-      "epoch": 0.04,
-      "learning_rate": 0.00019993306018843102,
-      "loss": 0.8918,
-      "step": 100
-    },
-    {
-      "epoch": 0.06,
-      "learning_rate": 0.00019983804784290833,
-      "loss": 0.8874,
-      "step": 150
-    },
-    {
-      "epoch": 0.08,
-      "learning_rate": 0.00019970177836355307,
-      "loss": 0.8839,
-      "step": 200
-    },
-    {
-      "epoch": 0.09,
-      "learning_rate": 0.00019961818913082012,
-      "loss": 0.8801,
-      "step": 225
-    },
-    {
-      "epoch": 0.1,
-      "learning_rate": 0.00019952430806244534,
-      "loss": 0.8753,
-      "step": 250
-    },
-    {
-      "epoch": 0.11,
-      "learning_rate": 0.00019942014485754635,
-      "loss": 0.8754,
-      "step": 275
-    },
-    {
-      "epoch": 0.12,
-      "learning_rate": 0.00019930571027751713,
-      "loss": 0.8751,
-      "step": 300
-    },
-    {
-      "epoch": 0.13,
-      "learning_rate": 0.0001991810161449164,
-      "loss": 0.8819,
-      "step": 325
-    },
-    {
-      "epoch": 0.14,
-      "learning_rate": 0.00019904607534224612,
-      "loss": 0.8744,
-      "step": 350
-    },
-    {
-      "epoch": 0.15,
-      "learning_rate": 0.00019890090181062063,
-      "loss": 0.8735,
-      "step": 375
-    },
-    {
-      "epoch": 0.16,
-      "learning_rate": 0.00019874551054832625,
-      "loss": 0.8703,
-      "step": 400
-    },
-    {
-      "epoch": 0.16,
-      "learning_rate": 0.00019857991760927193,
-      "loss": 0.8715,
-      "step": 425
-    },
-    {
-      "epoch": 0.17,
-      "learning_rate": 0.00019840414010133045,
-      "loss": 0.8714,
-      "step": 450
-    },
-    {
-      "epoch": 0.18,
-      "learning_rate": 0.00019821819618457114,
-      "loss": 0.8653,
-      "step": 475
-    },
-    {
-      "epoch": 0.19,
-      "learning_rate": 0.0001980221050693837,
-      "loss": 0.8716,
-      "step": 500
-    },
-    {
-      "epoch": 0.2,
-      "learning_rate": 0.00019781588701449338,
-      "loss": 0.8695,
-      "step": 525
-    },
-    {
-      "epoch": 0.21,
-      "learning_rate": 0.0001975995633248682,
-      "loss": 0.8746,
-      "step": 550
-    },
-    {
-      "epoch": 0.22,
-      "learning_rate": 0.00019737315634951762,
-      "loss": 0.8731,
-      "step": 575
-    },
-    {
-      "epoch": 0.23,
-      "learning_rate": 0.00019713668947918386,
-      "loss": 0.867,
-      "step": 600
-    },
-    {
-      "epoch": 0.24,
-      "learning_rate": 0.0001968901871439252,
-      "loss": 0.8706,
-      "step": 625
-    },
-    {
-      "epoch": 0.25,
-      "learning_rate": 0.000196633674810592,
-      "loss": 0.8595,
-      "step": 650
-    },
-    {
-      "epoch": 0.26,
-      "learning_rate": 0.0001963671789801958,
-      "loss": 0.8627,
-      "step": 675
-    },
-    {
-      "epoch": 0.27,
-      "learning_rate": 0.0001960907271851712,
-      "loss": 0.8607,
-      "step": 700
-    },
-    {
-      "epoch": 0.28,
-      "learning_rate": 0.00019580434798653173,
-      "loss": 0.858,
-      "step": 725
-    },
-    {
-      "epoch": 0.29,
-      "learning_rate": 0.00019550807097091876,
-      "loss": 0.8589,
-      "step": 750
-    },
-    {
-      "epoch": 0.3,
-      "learning_rate": 0.00019520192674754515,
-      "loss": 0.8561,
-      "step": 775
-    },
-    {
-      "epoch": 0.31,
-      "learning_rate": 0.00019488594694503264,
-      "loss": 0.8576,
-      "step": 800
-    },
-    {
-      "epoch": 0.32,
-      "learning_rate": 0.00019456016420814446,
-      "loss": 0.8597,
-      "step": 825
-    },
-    {
-      "epoch": 0.33,
-      "learning_rate": 0.00019422461219441254,
-      "loss": 0.862,
-      "step": 850
-    },
-    {
-      "epoch": 0.34,
-      "learning_rate": 0.00019387932557066035,
-      "loss": 0.8577,
-      "step": 875
-    },
-    {
-      "epoch": 0.35,
-      "learning_rate": 0.00019352434000942127,
-      "loss": 0.8632,
-      "step": 900
-    },
-    {
-      "epoch": 0.36,
-      "learning_rate": 0.00019315969218525333,
-      "loss": 0.8567,
-      "step": 925
-    },
-    {
-      "epoch": 0.37,
-      "learning_rate": 0.00019278541977095005,
-      "loss": 0.8501,
-      "step": 950
-    },
-    {
-      "epoch": 0.38,
-      "learning_rate": 0.00019240156143364844,
-      "loss": 0.8596,
-      "step": 975
-    },
-    {
-      "epoch": 0.39,
-      "learning_rate": 0.00019200815683083434,
-      "loss": 0.8556,
-      "step": 1000
-    },
-    {
-      "epoch": 0.39,
-      "eval_loss": 0.8521950244903564,
-      "eval_runtime": 59.8838,
-      "eval_samples_per_second": 12.19,
-      "eval_steps_per_second": 0.885,
-      "step": 1000
-    },
-    {
-      "epoch": 0.4,
-      "learning_rate": 0.00019160524660624505,
-      "loss": 0.8531,
-      "step": 1025
-    },
-    {
-      "epoch": 0.41,
-      "learning_rate": 0.00019119287238567045,
-      "loss": 0.8513,
-      "step": 1050
-    },
-    {
-      "epoch": 0.42,
-      "learning_rate": 0.00019077107677265253,
-      "loss": 0.8502,
-      "step": 1075
-    },
-    {
-      "epoch": 0.43,
-      "learning_rate": 0.00019033990334408384,
-      "loss": 0.8469,
-      "step": 1100
-    },
-    {
-      "epoch": 0.44,
-      "learning_rate": 0.00018989939664570545,
-      "loss": 0.8495,
-      "step": 1125
-    },
-    {
-      "epoch": 0.45,
-      "learning_rate": 0.00018944960218750484,
-      "loss": 0.8485,
-      "step": 1150
-    },
-    {
-      "epoch": 0.46,
-      "learning_rate": 0.00018899056643901404,
-      "loss": 0.8534,
-      "step": 1175
-    },
-    {
-      "epoch": 0.47,
-      "learning_rate": 0.00018852233682450893,
-      "loss": 0.8531,
-      "step": 1200
-    },
-    {
-      "epoch": 0.47,
-      "learning_rate": 0.00018804496171810948,
-      "loss": 0.8509,
-      "step": 1225
-    },
-    {
-      "epoch": 0.48,
-      "learning_rate": 0.00018755849043878222,
-      "loss": 0.8445,
-      "step": 1250
-    },
-    {
-      "epoch": 0.49,
-      "learning_rate": 0.0001870629732452449,
-      "loss": 0.8548,
-      "step": 1275
-    },
-    {
-      "epoch": 0.5,
-      "learning_rate": 0.00018655846133077417,
-      "loss": 0.8441,
-      "step": 1300
-    },
-    {
-      "epoch": 0.51,
-      "learning_rate": 0.00018604500681791656,
-      "loss": 0.8533,
-      "step": 1325
-    },
-    {
-      "epoch": 0.52,
-      "learning_rate": 0.00018552266275310373,
-      "loss": 0.8505,
-      "step": 1350
-    },
-    {
-      "epoch": 0.53,
-      "learning_rate": 0.0001849914831011719,
-      "loss": 0.8544,
-      "step": 1375
-    },
-    {
-      "epoch": 0.54,
-      "learning_rate": 0.00018445152273978668,
-      "loss": 0.845,
-      "step": 1400
-    },
-    {
-      "epoch": 0.55,
-      "learning_rate": 0.00018390283745377354,
-      "loss": 0.8376,
-      "step": 1425
-    },
-    {
-      "epoch": 0.56,
-      "learning_rate": 0.0001833454839293545,
-      "loss": 0.847,
-      "step": 1450
-    },
-    {
-      "epoch": 0.57,
-      "learning_rate": 0.00018277951974829163,
-      "loss": 0.8473,
-      "step": 1475
-    },
-    {
-      "epoch": 0.58,
-      "learning_rate": 0.0001822050033819382,
-      "loss": 0.8438,
-      "step": 1500
-    },
-    {
-      "epoch": 0.59,
-      "learning_rate": 0.00018162199418519785,
-      "loss": 0.8418,
-      "step": 1525
-    },
-    {
-      "epoch": 0.6,
-      "learning_rate": 0.00018103055239039243,
-      "loss": 0.842,
-      "step": 1550
-    },
-    {
-      "epoch": 0.61,
-      "learning_rate": 0.0001804307391010393,
-      "loss": 0.8435,
-      "step": 1575
-    },
-    {
-      "epoch": 0.62,
-      "learning_rate": 0.00017982261628553842,
-      "loss": 0.8349,
-      "step": 1600
-    },
-    {
-      "epoch": 0.63,
-      "learning_rate": 0.0001792062467707703,
-      "loss": 0.8483,
-      "step": 1625
-    },
-    {
-      "epoch": 0.64,
-      "learning_rate": 0.0001785816942356052,
-      "loss": 0.8387,
-      "step": 1650
-    },
-    {
-      "epoch": 0.65,
-      "learning_rate": 0.00017794902320432429,
-      "loss": 0.843,
-      "step": 1675
-    },
-    {
-      "epoch": 0.66,
-      "learning_rate": 0.00017730829903995333,
-      "loss": 0.8424,
-      "step": 1700
-    },
-    {
-      "epoch": 0.67,
-      "learning_rate": 0.00017665958793751006,
-      "loss": 0.8418,
-      "step": 1725
-    },
-    {
-      "epoch": 0.68,
-      "learning_rate": 0.00017600295691716522,
-      "loss": 0.8384,
-      "step": 1750
-    },
-    {
-      "epoch": 0.69,
-      "learning_rate": 0.00017533847381731856,
-      "loss": 0.8445,
-      "step": 1775
-    },
-    {
-      "epoch": 0.7,
-      "learning_rate": 0.00017466620728759033,
-      "loss": 0.8446,
-      "step": 1800
-    },
-    {
-      "epoch": 0.71,
-      "learning_rate": 0.00017398622678172878,
-      "loss": 0.838,
-      "step": 1825
-    },
-    {
-      "epoch": 0.72,
-      "learning_rate": 0.0001732986025504348,
-      "loss": 0.8415,
-      "step": 1850
-    },
-    {
-      "epoch": 0.73,
-      "learning_rate": 0.000172603405634104,
-      "loss": 0.8357,
-      "step": 1875
-    },
-    {
-      "epoch": 0.74,
-      "learning_rate": 0.00017190070785548755,
-      "loss": 0.8311,
-      "step": 1900
-    },
-    {
-      "epoch": 0.75,
-      "learning_rate": 0.0001711905818122717,
-      "loss": 0.8333,
-      "step": 1925
-    },
-    {
-      "epoch": 0.76,
-      "learning_rate": 0.0001704731008695777,
-      "loss": 0.8387,
-      "step": 1950
-    },
-    {
-      "epoch": 0.77,
-      "learning_rate": 0.0001697483391523821,
-      "loss": 0.8442,
-      "step": 1975
-    },
-    {
-      "epoch": 0.78,
-      "learning_rate": 0.00016901637153785885,
-      "loss": 0.8399,
-      "step": 2000
-    },
-    {
-      "epoch": 0.78,
-      "eval_loss": 0.8339959383010864,
-      "eval_runtime": 58.5829,
-      "eval_samples_per_second": 12.461,
-      "eval_steps_per_second": 0.905,
-      "step": 2000
-    },
-    {
-      "epoch": 0.79,
-      "learning_rate": 0.0001682772736476434,
-      "loss": 0.8334,
-      "step": 2025
-    },
-    {
-      "epoch": 0.79,
-      "learning_rate": 0.0001675311218400201,
-      "loss": 0.835,
-      "step": 2050
-    },
-    {
-      "epoch": 0.8,
-      "learning_rate": 0.00016677799320203332,
-      "loss": 0.8368,
-      "step": 2075
-    },
-    {
-      "epoch": 0.81,
-      "learning_rate": 0.00016601796554152344,
-      "loss": 0.8278,
-      "step": 2100
-    },
-    {
-      "epoch": 0.82,
-      "learning_rate": 0.00016525111737908827,
-      "loss": 0.8334,
-      "step": 2125
-    },
-    {
-      "epoch": 0.83,
-      "learning_rate": 0.00016447752793997096,
-      "loss": 0.8416,
-      "step": 2150
-    },
-    {
-      "epoch": 0.84,
-      "learning_rate": 0.00016369727714587483,
-      "loss": 0.8297,
-      "step": 2175
-    },
-    {
-      "epoch": 0.85,
-      "learning_rate": 0.0001629104456067066,
-      "loss": 0.8327,
-      "step": 2200
-    },
-    {
-      "epoch": 0.86,
-      "learning_rate": 0.00016211711461224825,
-      "loss": 0.8324,
-      "step": 2225
-    },
-    {
-      "epoch": 0.87,
-      "learning_rate": 0.0001613173661237589,
-      "loss": 0.8313,
-      "step": 2250
-    },
-    {
-      "epoch": 0.88,
-      "learning_rate": 0.0001605112827655069,
-      "loss": 0.8292,
-      "step": 2275
-    },
-    {
-      "epoch": 0.89,
-      "learning_rate": 0.0001596989478162339,
-      "loss": 0.8334,
-      "step": 2300
-    },
-    {
-      "epoch": 0.9,
-      "learning_rate": 0.00015888044520055106,
-      "loss": 0.8352,
-      "step": 2325
-    },
-    {
-      "epoch": 0.91,
-      "learning_rate": 0.00015805585948026852,
-      "loss": 0.823,
-      "step": 2350
-    },
-    {
-      "epoch": 0.92,
-      "learning_rate": 0.000157225275845659,
-      "loss": 0.8293,
-      "step": 2375
-    },
-    {
-      "epoch": 0.93,
-      "learning_rate": 0.00015638878010665672,
-      "loss": 0.8289,
-      "step": 2400
-    },
-    {
-      "epoch": 0.94,
-      "learning_rate": 0.00015554645868399205,
-      "loss": 0.832,
-      "step": 2425
-    },
-    {
-      "epoch": 0.95,
-      "learning_rate": 0.00015469839860026308,
-      "loss": 0.8294,
-      "step": 2450
-    },
-    {
-      "epoch": 0.96,
-      "learning_rate": 0.0001538446874709452,
-      "loss": 0.8281,
-      "step": 2475
-    },
-    {
-      "epoch": 0.97,
-      "learning_rate": 0.00015298541349533925,
-      "loss": 0.8314,
-      "step": 2500
-    },
-    {
-      "epoch": 0.98,
-      "learning_rate": 0.00015212066544745926,
-      "loss": 0.831,
-      "step": 2525
-    },
-    {
-      "epoch": 0.99,
-      "learning_rate": 0.00015125053266686124,
-      "loss": 0.8319,
-      "step": 2550
-    },
-    {
-      "epoch": 1.0,
-      "learning_rate": 0.00015037510504941303,
-      "loss": 0.8259,
-      "step": 2575
-    },
-    {
-      "epoch": 1.01,
-      "learning_rate": 0.00014949447303800695,
-      "loss": 0.8133,
-      "step": 2600
-    }
-  ],
-  "max_steps": 7737,
-  "num_train_epochs": 3,
-  "total_flos": 1.1197618170380681e+19,
-  "trial_name": null,
-  "trial_params": null
-}

checkpoint-2700/README.md

@@ -1,20 +0,0 @@
----
-library_name: peft
----
-## Training procedure
-
-
-The following `bitsandbytes` quantization config was used during training:
-- load_in_8bit: False
-- load_in_4bit: True
-- llm_int8_threshold: 6.0
-- llm_int8_skip_modules: None
-- llm_int8_enable_fp32_cpu_offload: False
-- llm_int8_has_fp16_weight: False
-- bnb_4bit_quant_type: nf4
-- bnb_4bit_use_double_quant: True
-- bnb_4bit_compute_dtype: bfloat16
-### Framework versions
-
-
-- PEFT 0.5.0.dev0

checkpoint-2700/adapter_model/README.md

@@ -1,20 +0,0 @@
----
-library_name: peft
----
-## Training procedure
-
-
-The following `bitsandbytes` quantization config was used during training:
-- load_in_8bit: False
-- load_in_4bit: True
-- llm_int8_threshold: 6.0
-- llm_int8_skip_modules: None
-- llm_int8_enable_fp32_cpu_offload: False
-- llm_int8_has_fp16_weight: False
-- bnb_4bit_quant_type: nf4
-- bnb_4bit_use_double_quant: True
-- bnb_4bit_compute_dtype: bfloat16
-### Framework versions
-
-
-- PEFT 0.5.0.dev0

checkpoint-2700/adapter_model/adapter_config.json

@@ -1,26 +0,0 @@
-{
-  "auto_mapping": null,
-  "base_model_name_or_path": "/workspace/webui/models/TheBloke_Llama-2-13B-fp16",
-  "bias": "none",
-  "fan_in_fan_out": null,
-  "inference_mode": true,
-  "init_lora_weights": true,
-  "layers_pattern": null,
-  "layers_to_transform": null,
-  "lora_alpha": 16,
-  "lora_dropout": 0.05,
-  "modules_to_save": null,
-  "peft_type": "LORA",
-  "r": 32,
-  "revision": null,
-  "target_modules": [
-    "v_proj",
-    "o_proj",
-    "down_proj",
-    "q_proj",
-    "gate_proj",
-    "up_proj",
-    "k_proj"
-  ],
-  "task_type": "CAUSAL_LM"
-}

checkpoint-2700/adapter_model/adapter_model.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:72857c4351001ef2bdba0e7acda85bdabe013b254c505a3fec540300b8b69221
-size 500897101

checkpoint-2700/optimizer.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:1e6581d1b0c10687bb3a3bc5ccd55dd7742012f93950a83aa87e181175ba0dae
-size 1001752701

checkpoint-2700/rng_state_1.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:22862d05c3516b301c0029fcde0e8d61ec3a7a699c06f10b45b2038d258705bf
-size 27772

checkpoint-2700/rng_state_12.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:d397934e98e2af089f95cd3ebfbb6349d0d5379338b81dcdd71225e616b7d2d4
-size 27789

checkpoint-2700/rng_state_4.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:203e94cac471cc2d7046694caa3b10e20010a25498536913b857d68ce1af2d43
-size 27772

checkpoint-2700/rng_state_5.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:03a357f3ee8bad9901505c5f66d44c603f13d92ab451726200a0ee872b5550ca
-size 27772

checkpoint-2700/rng_state_6.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:632d1189cca460782dd94b618a185a39301197e1ac0644b87bc12e7d639eb0db
-size 27772

checkpoint-2700/rng_state_7.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:6c082c3485e7cf0ad8b46608970b89a1aec712ccf501f38bb2fbacfb0063ff84
-size 27772

checkpoint-2700/rng_state_8.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:f661148a14bf7645d198ffbee78fd27e53207bc2df14b4ac8eaf8cb1ec10b9d2
-size 27772

checkpoint-2700/rng_state_9.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:302a97fe98bf1022f079fb5f4731e03dbd6c8c435be26dfdcac5c3191c75b913
-size 27772

checkpoint-2700/scheduler.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:165954622b82d5ed3c4b0d29e582a52b9368810b632d35b84ef87387e9f95006
-size 627

checkpoint-2700/training_args.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:1240323c6a8f49a8a8b1664a44594fc01574f066beb8bd9d04ff53bb19046038
-size 4027

{checkpoint-2600 → checkpoint-2900/adapter_model}/adapter_config.json

@@ -14,13 +14,13 @@
   "r": 32,
   "revision": null,
   "target_modules": [
+    "down_proj",
+    "k_proj",
+    "gate_proj",
     "v_proj",
     "o_proj",
-    "down_proj",
     "q_proj",
-    "gate_proj",
-    "up_proj",
-    "k_proj"
+    "up_proj"
   ],
   "task_type": "CAUSAL_LM"
 }

{checkpoint-2700 → checkpoint-2900/adapter_model}/adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72857c4351001ef2bdba0e7acda85bdabe013b254c505a3fec540300b8b69221
+oid sha256:69e75ae7e1f69a41e91706ac778c4176886a39e991e0545bde52d6c1f744f678
 size 500897101

{checkpoint-2700 → checkpoint-3000}/adapter_config.json

@@ -14,13 +14,13 @@
   "r": 32,
   "revision": null,
   "target_modules": [
+    "down_proj",
+    "k_proj",
+    "gate_proj",
     "v_proj",
     "o_proj",
-    "down_proj",
     "q_proj",
-    "gate_proj",
-    "up_proj",
-    "k_proj"
+    "up_proj"
   ],
   "task_type": "CAUSAL_LM"
 }

{checkpoint-2600 → checkpoint-3000}/adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:56dc05e4b75a13b83ba7370f0c76297d690a74a3feda12d5b102e996353b81b9
+oid sha256:3768dd1339753637e98fb5a78e49089bfc20cfbb2e5d5ab1d79b249f12bd91d6
 size 500897101

{checkpoint-2600 → checkpoint-3000}/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ba85ea1955fc3a2204b855d6c2c901d39f0b8328d2edfcb27bc07bc00be4595
+oid sha256:43dd2594437f90014ceb24dae35f0caf1408f106ca0640abfdb6f930ec7d1917
 size 1001752701

{checkpoint-2700 → checkpoint-3000}/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f207e68632bac90f957ee4b69848b1b3bf1823589f0084ffda5fe51a062cda66
+oid sha256:372977c5ad5707d01ab93c603a2084e21dcc5bbe3746e25cbd04e791984a40ad
 size 27772

{checkpoint-2600 → checkpoint-3000}/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8feef9c5b326e993ae8e32c169c4ef3993742c124ba0930945980b8e008850e8
+oid sha256:0cf974f69d3a79d20401ab16c60981d40397dff4557e89f3fb4f166a1c2b6988
 size 27772

{checkpoint-2700 → checkpoint-3000}/rng_state_10.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce953efa19f78d1504d60b13e76d782935e5997327dfbb7ccffdc0d67cd8ce63
+oid sha256:f46cf42d5b149dfdabbc17334f090d493267bd9a2a1e982e5a7904ba8ad96c66
 size 27789

{checkpoint-2700 → checkpoint-3000}/rng_state_11.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f1474d4132d013009328b51314e14a4557202e7a03fe1c5dd72c4bee493ebc32
+oid sha256:0d782b19c86bb619094e572c4d5fa6b1b8aff8745fd27fd20d67ad46b26e3500
 size 27789

{checkpoint-2600 → checkpoint-3000}/rng_state_12.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ba756a07b90478b637b9851fa410027ee94e909cb7919cd9d4fcd159a37ef887
+oid sha256:46ed59f9d93f80f01f93314ed6347cd1950aad081d7b1afa92318f622eae07dc
 size 27789

{checkpoint-2700 → checkpoint-3000}/rng_state_13.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c5aad35bbee83cb807b5f372f846229966f29c49d44cb351799da3e78c3739b
+oid sha256:de734c628aa46f0b8f66418bc77802de4cf179c013f3fa6520a4c967c9c44ee9
 size 27789

{checkpoint-2700 → checkpoint-3000}/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:54f1ed3e8d7bf0d86bd6d9acac91b9cfaabc266a2ecb5c2e05b800f5fb314129
+oid sha256:8b3ee02de5d832b0550492ad9197099cc49a1ef39883f9f21d43ee5eb7abbe91
 size 27772

{checkpoint-2700 → checkpoint-3000}/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:01f289536347abba01b49789dfbc3e30589b75cea2b08c3d776318c525f868ad
+oid sha256:f47b89653cf7379ccd6b6642b1cb9305e7b0ff4639356066795aec75e109dcd0
 size 27772

{checkpoint-2600 → checkpoint-3000}/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:85747e94ba08fc4b2acfbd826ef4a638fe780d8ad9fde0b070c76d64712855ae
+oid sha256:896ef18d13ff8a9f7f4850c38ec321a8050c0001f5f2abe7e1f217fabe5940c7
 size 27772

{checkpoint-2600 → checkpoint-3000}/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b6301ecefe14db185cd05ef36f36561cb7a32b66ac5fff6d1a936ba52f55b71
+oid sha256:f03081aff382542ac4332b7380a218da9fc6f3cc8c0e182a596a1aa05e2c4a86
 size 27772

{checkpoint-2600 → checkpoint-3000}/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bec70d8a47c437ca5bbbf7c5ca737d3eaf174b954dc4c7ce62a94528e7393b54
+oid sha256:8ba56e43a346f575d11975e33c17fd24d061dc495ff64f652662b4fe2bd5ba2a
 size 27772

{checkpoint-2600 → checkpoint-3000}/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:882e9a61238408dfaa60a0bc414cc18e3736c719db2871047c47d9c0a454770f
+oid sha256:cd77f76c2f0d692464a663d61dae016bcf5dd8966ed8742d59dea407d2a7048f
 size 27772

{checkpoint-2600 → checkpoint-3000}/rng_state_8.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:69a5c17e76a49d87f983fe9d36b8583b4966de729e3282bd49f56ea218d26ae9
+oid sha256:20c5b17ace5a48bc38935d68f2ceef000b52c248bec852ba042e42f55d1fdcec
 size 27772

{checkpoint-2600 → checkpoint-3000}/rng_state_9.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1673f90f732ddcdd764acb2dc0929a8fc940506800aac55e9f472611bc30b40d
+oid sha256:2362bce85dfe8a924fd3e27761bcd0046ea4d1f8b878596ba3abccb85ffaaa3d
 size 27772

{checkpoint-2600 → checkpoint-3000}/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8b72189e37755fe2f84814c3b2381641ff6ac501218069d38d84c5403ae9995
+oid sha256:f5eb3f4a2e8a234b77c028b4206015afec84f155c6d5bcb4ec7cd2c9f89b304b
 size 627

{checkpoint-2700 → checkpoint-3000}/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.0469174098487786,
-  "global_step": 2700,
+  "epoch": 1.1632415664986429,
+  "global_step": 3000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -646,11 +646,91 @@
       "learning_rate": 0.00014592172853170193,
       "loss": 0.8037,
       "step": 2700
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 0.00014501644968259212,
+      "loss": 0.8063,
+      "step": 2725
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 0.00014410652005730025,
+      "loss": 0.8155,
+      "step": 2750
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 0.00014319203366321826,
+      "loss": 0.8066,
+      "step": 2775
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 0.0001422730849785107,
+      "loss": 0.8091,
+      "step": 2800
+    },
+    {
+      "epoch": 1.1,
+      "learning_rate": 0.0001413497689423539,
+      "loss": 0.8067,
+      "step": 2825
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 0.00014042218094512755,
+      "loss": 0.8046,
+      "step": 2850
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 0.00013949041681855985,
+      "loss": 0.8053,
+      "step": 2875
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 0.0001385545728258264,
+      "loss": 0.8075,
+      "step": 2900
+    },
+    {
+      "epoch": 1.13,
+      "learning_rate": 0.0001376147456516055,
+      "loss": 0.8015,
+      "step": 2925
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 0.00013667103239208903,
+      "loss": 0.8016,
+      "step": 2950
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 0.00013572353054495126,
+      "loss": 0.8029,
+      "step": 2975
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 0.0001347723379992762,
+      "loss": 0.8017,
+      "step": 3000
+    },
+    {
+      "epoch": 1.16,
+      "eval_loss": 0.8229297995567322,
+      "eval_runtime": 59.3398,
+      "eval_samples_per_second": 12.302,
+      "eval_steps_per_second": 0.893,
+      "step": 3000
     }
   ],
   "max_steps": 7737,
   "num_train_epochs": 3,
-  "total_flos": 1.1628331844604264e+19,
+  "total_flos": 1.2918900565647294e+19,
   "trial_name": null,
   "trial_params": null
 }

{checkpoint-2600 → checkpoint-3000}/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1240323c6a8f49a8a8b1664a44594fc01574f066beb8bd9d04ff53bb19046038
+oid sha256:7292138fecd854f5f17371c439bbd450ee3c48e738b75818b778a55f4e26ef57
 size 4027