Training in progress, step 100, 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_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef41f8521e50bf504d99781460bd3460e64607713ee863c3a8562b76421fac45
+oid sha256:42c44b90ff1a08964fc953e9f694b1575dd62637b20903ba06f2273289ac56a4
 size 40036040

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fbc28aff6c1f0519ffb9cd7a501dc311b1aa599b81b95e0587dc2546c3ac6680
+oid sha256:425d1bc0c0c8b750363a2739a2c79a82e0cd9c38c04ebfe97f799ad7b2dc00b6
 size 20523679

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90f803b28408be4400865e7afc43e8d783a7dbb70d4236447fec88b54e3956a2
+oid sha256:a059a19a2996dab3b6d4818dae12c8bf997be18ff1e9dfcbb8a7af4070b27755
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:24d86c276b7647b8353d4643979580f8916c0427c3136aa6cb63bd500555f215
+oid sha256:e5f7790259e29eb5b24d667bdfc452be2dffd1fc55eea23973e34ba06c4748b9
 size 627

last-checkpoint/trainer_state.json

@@ -1,45 +1,32 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.05,
-  "eval_steps": 2,
-  "global_step": 4,
+  "epoch": 0.31347962382445144,
+  "eval_steps": 100,
+  "global_step": 100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.03,
-      "learning_rate": 0.001,
-      "loss": 3.1823,
-      "step": 2
+      "epoch": 0.31,
+      "learning_rate": 0.0002,
+      "loss": 0.7896,
+      "step": 100
     },
     {
-      "epoch": 0.03,
-      "eval_runtime": 127.9324,
-      "eval_samples_per_second": 1.759,
-      "eval_steps_per_second": 0.227,
-      "step": 2
-    },
-    {
-      "epoch": 0.05,
-      "learning_rate": 0.001,
-      "loss": 1.5289,
-      "step": 4
-    },
-    {
-      "epoch": 0.05,
-      "eval_runtime": 128.0886,
-      "eval_samples_per_second": 1.757,
-      "eval_steps_per_second": 0.226,
-      "step": 4
+      "epoch": 0.31,
+      "eval_runtime": 511.2401,
+      "eval_samples_per_second": 1.76,
+      "eval_steps_per_second": 0.221,
+      "step": 100
     }
   ],
-  "logging_steps": 2,
-  "max_steps": 240,
+  "logging_steps": 100,
+  "max_steps": 957,
   "num_train_epochs": 3,
-  "save_steps": 2,
-  "total_flos": 664404328710144.0,
+  "save_steps": 100,
+  "total_flos": 1.66101082177536e+16,
   "trial_name": null,
   "trial_params": null
 }

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:887525ecb45e22150885f827b7fded85dffa90a11a9d2671d3af44cae52f9aff
+oid sha256:f3c40a0e487f195e0bcdca0bd80b08de3505f73bfc6a8c9eb501acf966d1c6ad
 size 4027