Training in progress, step 1500, checkpoint

last-checkpoint/README.md

@@ -216,23 +216,4 @@ The following `bitsandbytes` quantization config was used during training:
 ### Framework versions
 
 
-- PEFT 0.7.0.dev0
-## Training procedure
-
-
-The following `bitsandbytes` quantization config was used during training:
-- quant_method: bitsandbytes
-- load_in_8bit: True
-- load_in_4bit: False
-- 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: fp4
-- bnb_4bit_use_double_quant: False
-- bnb_4bit_compute_dtype: float32
-
-### Framework versions
-
-
 - PEFT 0.7.0.dev0

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bda8507d5c5066f31513bff07c4d9f0892568afb4024128f972ec1b6da9b2ac2
+oid sha256:421be7fd313381b65da454dc231e57674859d47159fc30c9c8b08ee7b9712517
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e53295bee557fed0dcdde3db2f871a7b3f220fc88e63c4cb7d6788ecdf83f57
+oid sha256:fe8555c4ba45765dbeb36358ba1d94c94f9ff9649b9c2f01dc17adab00b5102b
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e4490c26af2695a2b327922ff3f2cc285daad2f6354ff581e32798a9b8e42b8
+oid sha256:84c42f02805f05255b8fcfb4fa3b8e8ef15f6edcb5701c96a5484d4d1911b2fc
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d1351871b6e069a7a4437616d40b913152ecc2cd046e996fcfeb300a3cf60638
+oid sha256:d397c26ac1ddd7670b9ddd8b909580a771b707ad5b586b657ad627e8bc4e787f
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.3074026107788086,
-  "best_model_checkpoint": "./outputs/checkpoint-1400",
-  "epoch": 1.0200364298724955,
+  "best_metric": 2.2931342124938965,
+  "best_model_checkpoint": "./outputs/checkpoint-1500",
+  "epoch": 1.092896174863388,
   "eval_steps": 100,
-  "global_step": 1400,
+  "global_step": 1500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -203,13 +203,27 @@
       "eval_samples_per_second": 30.619,
       "eval_steps_per_second": 3.831,
       "step": 1400
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 0.0002,
+      "loss": 2.2609,
+      "step": 1500
+    },
+    {
+      "epoch": 1.09,
+      "eval_loss": 2.2931342124938965,
+      "eval_runtime": 205.4253,
+      "eval_samples_per_second": 30.542,
+      "eval_steps_per_second": 3.821,
+      "step": 1500
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 4.091805541361664e+16,
+  "total_flos": 4.384226881972224e+16,
   "trial_name": null,
   "trial_params": null
 }