Training in progress, step 50, checkpoint

last-checkpoint/README.md

@@ -217,23 +217,4 @@ The following `bitsandbytes` quantization config was used during training:
 ### Framework versions
 
 
-- PEFT 0.6.2
-## 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: True
-- bnb_4bit_quant_type: nf4
-- bnb_4bit_use_double_quant: True
-- bnb_4bit_compute_dtype: float16
-
-### Framework versions
-
-
 - PEFT 0.6.2

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:97cba999fb720c4d176ef8a8d3c8d6809705b6f07a15dc41a16e639cba3a4151
+oid sha256:269e02dc931865a4d7c1981eca33d2486373d043dd99da5f05186ac7501a7648
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:346e9b48608e1d59b317e52559a01620207035d8ff8260d0025b99fef9d3a988
+oid sha256:1b219215a0cdf22b74e690dedd537471ed5ec27d5a848a0c00dd9462c08dea9c
 size 42545748

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:377540a51df182761cc61ba1eb907a8a946aa1a4db87591c9078f8e011fe7b38
+oid sha256:58973b63eb41c8b34c51f7eb73abffa4ae0d2af806c0e342de338e3f48596cb0
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cba506068924f81fe6223c30197a8cb6d84cb2904e97497dc664ebe8dc4a033f
+oid sha256:02173fc97b82f2e000f1d5084934ed87f720106f5dddb2874a3633a6c2964dab
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 25.0,
+  "epoch": 50.0,
   "eval_steps": 1000,
-  "global_step": 25,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -157,13 +157,163 @@
       "learning_rate": 0.00016631578947368423,
       "loss": 0.0127,
       "step": 25
+    },
+    {
+      "epoch": 26.0,
+      "learning_rate": 0.00016421052631578948,
+      "loss": 0.0049,
+      "step": 26
+    },
+    {
+      "epoch": 27.0,
+      "learning_rate": 0.00016210526315789473,
+      "loss": 0.0042,
+      "step": 27
+    },
+    {
+      "epoch": 28.0,
+      "learning_rate": 0.00016,
+      "loss": 0.0052,
+      "step": 28
+    },
+    {
+      "epoch": 29.0,
+      "learning_rate": 0.00015789473684210527,
+      "loss": 0.0041,
+      "step": 29
+    },
+    {
+      "epoch": 30.0,
+      "learning_rate": 0.00015578947368421052,
+      "loss": 0.0044,
+      "step": 30
+    },
+    {
+      "epoch": 31.0,
+      "learning_rate": 0.0001536842105263158,
+      "loss": 0.0044,
+      "step": 31
+    },
+    {
+      "epoch": 32.0,
+      "learning_rate": 0.00015157894736842108,
+      "loss": 0.0043,
+      "step": 32
+    },
+    {
+      "epoch": 33.0,
+      "learning_rate": 0.00014947368421052633,
+      "loss": 0.0043,
+      "step": 33
+    },
+    {
+      "epoch": 34.0,
+      "learning_rate": 0.00014736842105263158,
+      "loss": 0.0043,
+      "step": 34
+    },
+    {
+      "epoch": 35.0,
+      "learning_rate": 0.00014526315789473686,
+      "loss": 0.0044,
+      "step": 35
+    },
+    {
+      "epoch": 36.0,
+      "learning_rate": 0.0001431578947368421,
+      "loss": 0.0035,
+      "step": 36
+    },
+    {
+      "epoch": 37.0,
+      "learning_rate": 0.00014105263157894736,
+      "loss": 0.004,
+      "step": 37
+    },
+    {
+      "epoch": 38.0,
+      "learning_rate": 0.00013894736842105264,
+      "loss": 0.0044,
+      "step": 38
+    },
+    {
+      "epoch": 39.0,
+      "learning_rate": 0.0001368421052631579,
+      "loss": 0.0041,
+      "step": 39
+    },
+    {
+      "epoch": 40.0,
+      "learning_rate": 0.00013473684210526317,
+      "loss": 0.0043,
+      "step": 40
+    },
+    {
+      "epoch": 41.0,
+      "learning_rate": 0.00013263157894736842,
+      "loss": 0.0041,
+      "step": 41
+    },
+    {
+      "epoch": 42.0,
+      "learning_rate": 0.0001305263157894737,
+      "loss": 0.0042,
+      "step": 42
+    },
+    {
+      "epoch": 43.0,
+      "learning_rate": 0.00012842105263157895,
+      "loss": 0.0036,
+      "step": 43
+    },
+    {
+      "epoch": 44.0,
+      "learning_rate": 0.0001263157894736842,
+      "loss": 0.0038,
+      "step": 44
+    },
+    {
+      "epoch": 45.0,
+      "learning_rate": 0.00012421052631578949,
+      "loss": 0.0039,
+      "step": 45
+    },
+    {
+      "epoch": 46.0,
+      "learning_rate": 0.00012210526315789474,
+      "loss": 0.0045,
+      "step": 46
+    },
+    {
+      "epoch": 47.0,
+      "learning_rate": 0.00012,
+      "loss": 0.0053,
+      "step": 47
+    },
+    {
+      "epoch": 48.0,
+      "learning_rate": 0.00011789473684210525,
+      "loss": 0.0042,
+      "step": 48
+    },
+    {
+      "epoch": 49.0,
+      "learning_rate": 0.00011578947368421053,
+      "loss": 0.0029,
+      "step": 49
+    },
+    {
+      "epoch": 50.0,
+      "learning_rate": 0.0001136842105263158,
+      "loss": 0.004,
+      "step": 50
     }
   ],
   "logging_steps": 1,
   "max_steps": 100,
   "num_train_epochs": 100,
   "save_steps": 25,
-  "total_flos": 267436185600000.0,
+  "total_flos": 534872371200000.0,
   "trial_name": null,
   "trial_params": null
 }