Training in progress, step 800, 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 sha256:00350a6c30389aa6ee77391842a05a3e2deafca8f0ac607d9ad785288ca8246b
+oid sha256:c039dd5fba64dffdd9569ab975b4d98763ec1e9be229cc02f7cb5f394fec626b
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9699140d765a756700671694919acf18339996dbeb4dbc4783dbf1c9e7136e77
+oid sha256:d49daa2cecf7a1e1fecb4b247861334e91f819b0c3bea660845acfb4d8907831
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db6358da13f324834878bd2b4485e5667664a0d92ed16a7f6a761dd9dea8cc65
+oid sha256:4cf66005e5e6a4f3553669f4e9894b69e1bc5f9207c5bf2c3d2ce3aab9394607
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:30423cc69a1c7d18caef4643847588d5884db012263cbe7b7224fa4719ca4156
+oid sha256:de7840bcb72f2f480fd301578d289cdfa174589e831b0d33e5772f3956b6beae
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.4490628242492676,
-  "best_model_checkpoint": "./outputs/checkpoint-700",
-  "epoch": 0.5100182149362478,
+  "best_metric": 2.4292285442352295,
+  "best_model_checkpoint": "./outputs/checkpoint-800",
+  "epoch": 0.5828779599271403,
   "eval_steps": 100,
-  "global_step": 700,
+  "global_step": 800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -105,13 +105,27 @@
       "eval_samples_per_second": 30.434,
       "eval_steps_per_second": 3.808,
       "step": 700
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.0002,
+      "loss": 2.428,
+      "step": 800
+    },
+    {
+      "epoch": 0.58,
+      "eval_loss": 2.4292285442352295,
+      "eval_runtime": 206.472,
+      "eval_samples_per_second": 30.387,
+      "eval_steps_per_second": 3.802,
+      "step": 800
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 2.042513200078848e+16,
+  "total_flos": 2.333865205776384e+16,
   "trial_name": null,
   "trial_params": null
 }