Training in progress, step 100, checkpoint

last-checkpoint/README.md

@@ -217,4 +217,23 @@ The following `bitsandbytes` quantization config was used during training:
 ### Framework versions
 
 
+- PEFT 0.6.3.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 0.6.3.dev0

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:065d6cdfd25a3592de63b9ea57d49cc10abe0782a56656abb658855f78661c42
+oid sha256:a8f074ee0142264d42ff6ac14277529268f6ceb94c56d620fbaa623f9e5cfd77
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6ab06dac26f59d076051a357403d2a8514e3f20a26dcde2e2c380d7e94ee1a84
+oid sha256:9f610b9589325d7175171087c87fcde851d9e63322240c2f555b520195b099b0
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c1ec0da87f5671851cc04bcc5ea52b139af3d8380509986e058dbd0a4f2510f2
+oid sha256:41f270cc5b1e61ed3af1f62839766416b6f4a38dc682e2def2352932fbe9d6d9
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c1a2ac1c11599601eeac95feb1dbfd49ec5c625e61dcce18b3f094491f9cf2d
+oid sha256:216f76b8039f833c337db298c81f13b12082d5fd4f9d866cecd34b2ca7550b37
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.0246661901474,
-  "best_model_checkpoint": "./outputs/checkpoint-600",
-  "epoch": 0.8522727272727273,
+  "best_metric": 1.0926024913787842,
+  "best_model_checkpoint": "./outputs/checkpoint-100",
+  "epoch": 0.14204545454545456,
   "eval_steps": 100,
-  "global_step": 600,
+  "global_step": 100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -11,86 +11,16 @@
     {
       "epoch": 0.14,
       "learning_rate": 0.0002,
-      "loss": 1.5807,
+      "loss": 1.5836,
       "step": 100
     },
     {
       "epoch": 0.14,
-      "eval_loss": 1.0911378860473633,
-      "eval_runtime": 126.8708,
-      "eval_samples_per_second": 11.76,
-      "eval_steps_per_second": 1.474,
+      "eval_loss": 1.0926024913787842,
+      "eval_runtime": 92.4288,
+      "eval_samples_per_second": 16.142,
+      "eval_steps_per_second": 2.023,
       "step": 100
-    },
-    {
-      "epoch": 0.28,
-      "learning_rate": 0.0002,
-      "loss": 1.2278,
-      "step": 200
-    },
-    {
-      "epoch": 0.28,
-      "eval_loss": 1.0710176229476929,
-      "eval_runtime": 123.7755,
-      "eval_samples_per_second": 12.054,
-      "eval_steps_per_second": 1.511,
-      "step": 200
-    },
-    {
-      "epoch": 0.43,
-      "learning_rate": 0.0002,
-      "loss": 1.2143,
-      "step": 300
-    },
-    {
-      "epoch": 0.43,
-      "eval_loss": 1.0573608875274658,
-      "eval_runtime": 123.8307,
-      "eval_samples_per_second": 12.049,
-      "eval_steps_per_second": 1.51,
-      "step": 300
-    },
-    {
-      "epoch": 0.57,
-      "learning_rate": 0.0002,
-      "loss": 1.1968,
-      "step": 400
-    },
-    {
-      "epoch": 0.57,
-      "eval_loss": 1.0461841821670532,
-      "eval_runtime": 123.7514,
-      "eval_samples_per_second": 12.056,
-      "eval_steps_per_second": 1.511,
-      "step": 400
-    },
-    {
-      "epoch": 0.71,
-      "learning_rate": 0.0002,
-      "loss": 1.1868,
-      "step": 500
-    },
-    {
-      "epoch": 0.71,
-      "eval_loss": 1.035237431526184,
-      "eval_runtime": 123.8134,
-      "eval_samples_per_second": 12.05,
-      "eval_steps_per_second": 1.51,
-      "step": 500
-    },
-    {
-      "epoch": 0.85,
-      "learning_rate": 0.0002,
-      "loss": 1.1746,
-      "step": 600
-    },
-    {
-      "epoch": 0.85,
-      "eval_loss": 1.0246661901474,
-      "eval_runtime": 123.5637,
-      "eval_samples_per_second": 12.075,
-      "eval_steps_per_second": 1.513,
-      "step": 600
     }
   ],
   "logging_steps": 100,
@@ -98,7 +28,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 3.333198802526208e+16,
+  "total_flos": 5530295581655040.0,
   "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:fea25dd0b62f2743404b9270b914baaf658731e1acbc936ce8fd0c2017ee8535
+oid sha256:773fc843ab8e8578c19dea3b7f4669d81e0fdb743a2d8dc54ea40860d6fb2fab
 size 4283