Training in progress, step 25, checkpoint

last-checkpoint/README.md

@@ -4,18 +4,6 @@ library_name: peft
 ## Training procedure
 
 
-The following `bitsandbytes` quantization config was used during training:
-- quant_method: bitsandbytes
-- 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: float16
-
 The following `bitsandbytes` quantization config was used during training:
 - quant_method: bitsandbytes
 - load_in_8bit: False
@@ -29,6 +17,5 @@ The following `bitsandbytes` quantization config was used during training:
 - bnb_4bit_compute_dtype: float16
 ### Framework versions
 
-- PEFT 0.5.0
 
 - PEFT 0.5.0

last-checkpoint/adapter_config.json

@@ -8,7 +8,7 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "lora_alpha": 8,
-  "lora_dropout": 0.2,
+  "lora_dropout": 0.05,
   "modules_to_save": null,
   "peft_type": "LORA",
   "r": 4,

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6614ad059f21b421670cd5e428c91ab88f769eb2a2492105cc8a6983fe3edfa0
+oid sha256:1a97e01168bb7705aceb33e32e0e4e3d587f3e1163b2c422a18c4e5807a1ccdc
 size 40036040

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:901c5fd7af5774f7e3e7f030e0200f5e17298e36cd8fcec8511b2c3751bd4dec
+oid sha256:8851a73de47dbfcfe31de86bb6192dfb9990a4ac4a46f2f7ab1302c1c78989d2
 size 20523679

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:30b6b81c68bccbea71620607bbde917982ac0e318eae54d911e6a4cadfae0a72
+oid sha256:3029f8fdae5b5a1515326241e0c15afad3612dc0f653bb9b6b93ae183483db93
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a164590e485ad70f68d6dc5c9f98d12a7490944c208738b6125bd2b698b648a9
+oid sha256:01bd1906bbea59f9e9fca9d2fcebc7d848ace4b2b715eed5519ef909ccf2df1c
 size 627

last-checkpoint/trainer_state.json

@@ -1,32 +1,32 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.2,
-  "eval_steps": 100,
-  "global_step": 100,
+  "epoch": 0.25,
+  "eval_steps": 25,
+  "global_step": 25,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.2,
-      "learning_rate": 0.04,
-      "loss": 10997.5238,
-      "step": 100
+      "epoch": 0.25,
+      "learning_rate": 0.0001,
+      "loss": 1.6153,
+      "step": 25
     },
     {
-      "epoch": 0.2,
-      "eval_runtime": 2114.359,
-      "eval_samples_per_second": 1.892,
-      "eval_steps_per_second": 0.236,
-      "step": 100
+      "epoch": 0.25,
+      "eval_runtime": 216.6929,
+      "eval_samples_per_second": 1.846,
+      "eval_steps_per_second": 0.157,
+      "step": 25
     }
   ],
-  "logging_steps": 100,
-  "max_steps": 1000,
+  "logging_steps": 25,
+  "max_steps": 200,
   "num_train_epochs": 2,
-  "save_steps": 100,
-  "total_flos": 3.32202164355072e+16,
+  "save_steps": 25,
+  "total_flos": 4152527054438400.0,
   "trial_name": null,
   "trial_params": null
 }

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed3fc0fab185d4e779aef22afa57b457c6d7621ef7637b0afb63fb96731ca99e
+oid sha256:9c8c27537b3f48a590e7245cfc358a5c006cb5add7444724e14c4fd4a1f89680
 size 4091