Training in progress, step 4, checkpoint

last-checkpoint/README.md

@@ -4,30 +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
-- 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
@@ -53,8 +29,6 @@ The following `bitsandbytes` quantization config was used during training:
 - bnb_4bit_compute_dtype: float16
 ### Framework versions
 
-- PEFT 0.5.0
-- PEFT 0.5.0
 - PEFT 0.5.0
 
 - PEFT 0.5.0

last-checkpoint/adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:894902fc83ce981ce902d325f92c66c93f068f601ec88ba81ca2818c4f4ea82c
+oid sha256:4b2afaa2d90767d6e6b3122609a0b28522b7c540e55fffa6cece521823863a13
 size 40137613

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f41804539ce4dbc951729526a56d2696d7d2042884d136c4e448563b20767c9c
+oid sha256:ef41f8521e50bf504d99781460bd3460e64607713ee863c3a8562b76421fac45
 size 40036040

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b5f1842a91acf8bc3388db088cf49775e50c5c216645f7d35ef69df393c50c91
+oid sha256:fbc28aff6c1f0519ffb9cd7a501dc311b1aa599b81b95e0587dc2546c3ac6680
 size 20523679

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:18aff74b667dba3ffb21fc4e30c6282bcfa51148f5f176894821bf027611df3f
+oid sha256:90f803b28408be4400865e7afc43e8d783a7dbb70d4236447fec88b54e3956a2
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:359ea6d423af08e8e9047ba958e9726b4e403615b5c587f71a606d0689d2621a
+oid sha256:24d86c276b7647b8353d4643979580f8916c0427c3136aa6cb63bd500555f215
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.025,
+  "epoch": 0.05,
   "eval_steps": 2,
-  "global_step": 2,
+  "global_step": 4,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -20,13 +20,26 @@
       "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
     }
   ],
   "logging_steps": 2,
   "max_steps": 240,
   "num_train_epochs": 3,
   "save_steps": 2,
-  "total_flos": 332202164355072.0,
+  "total_flos": 664404328710144.0,
   "trial_name": null,
   "trial_params": null
 }