Training in progress, step 500

README.md

@@ -20,15 +20,15 @@ should probably proofread and complete it, then remove this comment. -->
 
 This model is a fine-tuned version of [data/ap-gpt-j-6b-sft-qlora-04-08](https://huggingface.co/data/ap-gpt-j-6b-sft-qlora-04-08) on the hugodk-sch/aftonposten_title_prefs dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.4763
-- Rewards/chosen: 0.2774
-- Rewards/rejected: 0.1670
-- Rewards/accuracies: 0.5685
-- Rewards/margins: 0.1104
-- Logps/rejected: -37.2781
-- Logps/chosen: -33.6382
-- Logits/rejected: -2.1561
-- Logits/chosen: -2.1608
+- Loss: 0.5837
+- Rewards/chosen: -0.0077
+- Rewards/rejected: -0.0206
+- Rewards/accuracies: 0.5428
+- Rewards/margins: 0.0128
+- Logps/rejected: -37.5460
+- Logps/chosen: -34.0456
+- Logits/rejected: -2.2319
+- Logits/chosen: -2.2368
 
 ## Model description
 
@@ -57,33 +57,21 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: cosine
 - lr_scheduler_warmup_ratio: 0.1
-- num_epochs: 4
+- num_epochs: 1
 
 ### Training results
 
-| Training Loss | Epoch | Step | Logits/chosen | Logits/rejected | Logps/chosen | Logps/rejected | Validation Loss | Rewards/accuracies | Rewards/chosen | Rewards/margins | Rewards/rejected |
-|:-------------:|:-----:|:----:|:-------------:|:---------------:|:------------:|:--------------:|:---------------:|:------------------:|:--------------:|:---------------:|:----------------:|
-| 0.4799        | 0.26  | 100  | -2.2381       | -2.2333         | -33.8607     | -37.3570       | 0.4978          | 0.5341             | 0.1217         | 0.0100          | 0.1117           |
-| 0.4453        | 0.52  | 200  | -2.2347       | -2.2299         | -33.7685     | -37.2937       | 0.4928          | 0.5370             | 0.1862         | 0.0302          | 0.1561           |
-| 0.3947        | 0.78  | 300  | -2.2322       | -2.2274         | -33.7551     | -37.2894       | 0.4910          | 0.5565             | 0.1956         | 0.0365          | 0.1591           |
-| 0.3136        | 1.04  | 400  | 0.4857        | 0.2846          | 0.2244       | 0.5797         | 0.0602          | -37.1961           | -33.6280       | -2.2032         | -2.2080          |
-| 0.2784        | 1.3   | 500  | 0.4891        | 0.2959          | 0.2519       | 0.5220         | 0.0439          | -37.1567           | -33.6119       | -2.2050         | -2.2098          |
-| 0.2593        | 1.56  | 600  | 0.4795        | 0.3345          | 0.2439       | 0.5743         | 0.0906          | -37.1682           | -33.5567       | -2.1866         | -2.1914          |
-| 0.2606        | 1.82  | 700  | 0.4764        | 0.3188          | 0.2158       | 0.6063         | 0.1031          | -37.2084           | -33.5791       | -2.1788         | -2.1836          |
-| 0.1758        | 2.08  | 800  | 0.4767        | 0.2840          | 0.1749       | 0.5860         | 0.1091          | -37.2668           | -33.6289       | -2.1680         | -2.1727          |
-| 0.1687        | 2.34  | 900  | 0.4770        | 0.2898          | 0.1833       | 0.5486         | 0.1065          | -37.2547           | -33.6205       | -2.1626         | -2.1674          |
-| 0.1826        | 2.6   | 1000 | 0.4764        | 0.2700          | 0.1574       | 0.5831         | 0.1126          | -37.2917           | -33.6489       | -2.1578         | -2.1625          |
-| 0.1541        | 2.86  | 1100 | 0.4751        | 0.2864          | 0.1692       | 0.5777         | 0.1171          | -37.2748           | -33.6254       | -2.1561         | -2.1608          |
-| 0.194         | 3.12  | 1200 | 0.4748        | 0.2856          | 0.1654       | 0.5801         | 0.1202          | -37.2803           | -33.6265       | -2.1565         | -2.1612          |
-| 0.1414        | 3.38  | 1300 | 0.4753        | 0.2859          | 0.1690       | 0.5831         | 0.1169          | -37.2751           | -33.6261       | -2.1558         | -2.1605          |
-| 0.1492        | 3.64  | 1400 | 0.4744        | 0.2846          | 0.1627       | 0.5918         | 0.1220          | -37.2842           | -33.6279       | -2.1556         | -2.1603          |
-| 0.1694        | 3.9   | 1500 | 0.4747        | 0.2822          | 0.1614       | 0.5569         | 0.1208          | -37.2860           | -33.6314       | -2.1560         | -2.1607          |
+| Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
+|:-------------:|:-----:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
+| 0.4711        | 0.26  | 100  | 0.5755          | 0.0163         | 0.0131           | 0.5195             | 0.0032          | -37.4979       | -34.0113     | -2.2352         | -2.2401       |
+| 0.5061        | 0.52  | 200  | 0.5877          | -0.0108        | -0.0202          | 0.4992             | 0.0094          | -37.5455       | -34.0500     | -2.2337         | -2.2385       |
+| 0.3371        | 0.78  | 300  | 0.5843          | 0.0001         | -0.0131          | 0.5278             | 0.0132          | -37.5353       | -34.0344     | -2.2322         | -2.2371       |
 
 
 ### Framework versions
 
-- PEFT 0.10.0
-- Transformers 4.39.0.dev0
+- PEFT 0.8.2
+- Transformers 4.37.2
 - Pytorch 2.1.2+cu121
-- Datasets 2.14.6
+- Datasets 2.17.0
 - Tokenizers 0.15.1

adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "k_proj",
-    "o_proj",
     "gate_proj",
     "up_proj",
+    "o_proj",
+    "down_proj",
     "q_proj",
     "v_proj",
-    "down_proj"
+    "k_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e4f8e306a73a999a41c8de964894eaa93994481de6722767ddb43b3c17557965
+oid sha256:65a417ec51ff0410fddcaee4741abe927bf937a91102d2c02f81ad7f949d370d
 size 176183216

all_results.json

@@ -1,21 +1,21 @@
 {
-    "epoch": 4.0,
-    "eval_logits/chosen": -2.1607675552368164,
-    "eval_logits/rejected": -2.156055450439453,
-    "eval_logps/chosen": -33.63822555541992,
-    "eval_logps/rejected": -37.278076171875,
-    "eval_loss": 0.4762561619281769,
-    "eval_rewards/accuracies": 0.5685215592384338,
-    "eval_rewards/chosen": 0.27742961049079895,
-    "eval_rewards/margins": 0.11044850200414658,
-    "eval_rewards/rejected": 0.16698110103607178,
-    "eval_runtime": 145.2249,
+    "epoch": 1.0,
+    "eval_logits/chosen": -2.236751079559326,
+    "eval_logits/rejected": -2.2318832874298096,
+    "eval_logps/chosen": -34.04561233520508,
+    "eval_logps/rejected": -37.546016693115234,
+    "eval_loss": 0.5836836099624634,
+    "eval_rewards/accuracies": 0.5427741408348083,
+    "eval_rewards/chosen": -0.007742464076727629,
+    "eval_rewards/margins": 0.01283606793731451,
+    "eval_rewards/rejected": -0.02057853527367115,
+    "eval_runtime": 145.5744,
     "eval_samples": 343,
-    "eval_samples_per_second": 2.362,
-    "eval_steps_per_second": 0.296,
-    "train_loss": 0.17319794591371115,
-    "train_runtime": 10768.0107,
+    "eval_samples_per_second": 2.356,
+    "eval_steps_per_second": 0.295,
+    "train_loss": 0.46899499707407766,
+    "train_runtime": 3249.86,
     "train_samples": 3079,
-    "train_samples_per_second": 1.144,
-    "train_steps_per_second": 0.143
+    "train_samples_per_second": 0.947,
+    "train_steps_per_second": 0.118
 }

config.json

@@ -18,8 +18,6 @@
   "n_layer": 28,
   "n_positions": 2048,
   "quantization_config": {
-    "_load_in_4bit": true,
-    "_load_in_8bit": false,
     "bnb_4bit_compute_dtype": "float16",
     "bnb_4bit_quant_type": "nf4",
     "bnb_4bit_use_double_quant": false,
@@ -47,7 +45,7 @@
   },
   "tie_word_embeddings": false,
   "tokenizer_class": "GPT2Tokenizer",
-  "transformers_version": "4.39.0.dev0",
+  "transformers_version": "4.37.2",
   "use_cache": true,
   "vocab_size": 50400
 }

eval_results.json

@@ -1,16 +1,16 @@
 {
-    "epoch": 4.0,
-    "eval_logits/chosen": -2.1607675552368164,
-    "eval_logits/rejected": -2.156055450439453,
-    "eval_logps/chosen": -33.63822555541992,
-    "eval_logps/rejected": -37.278076171875,
-    "eval_loss": 0.4762561619281769,
-    "eval_rewards/accuracies": 0.5685215592384338,
-    "eval_rewards/chosen": 0.27742961049079895,
-    "eval_rewards/margins": 0.11044850200414658,
-    "eval_rewards/rejected": 0.16698110103607178,
-    "eval_runtime": 145.2249,
+    "epoch": 1.0,
+    "eval_logits/chosen": -2.236751079559326,
+    "eval_logits/rejected": -2.2318832874298096,
+    "eval_logps/chosen": -34.04561233520508,
+    "eval_logps/rejected": -37.546016693115234,
+    "eval_loss": 0.5836836099624634,
+    "eval_rewards/accuracies": 0.5427741408348083,
+    "eval_rewards/chosen": -0.007742464076727629,
+    "eval_rewards/margins": 0.01283606793731451,
+    "eval_rewards/rejected": -0.02057853527367115,
+    "eval_runtime": 145.5744,
     "eval_samples": 343,
-    "eval_samples_per_second": 2.362,
-    "eval_steps_per_second": 0.296
+    "eval_samples_per_second": 2.356,
+    "eval_steps_per_second": 0.295
 }

train_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 4.0,
-    "train_loss": 0.17319794591371115,
-    "train_runtime": 10768.0107,
+    "epoch": 1.0,
+    "train_loss": 0.46899499707407766,
+    "train_runtime": 3249.86,
     "train_samples": 3079,
-    "train_samples_per_second": 1.144,
-    "train_steps_per_second": 0.143
+    "train_samples_per_second": 0.947,
+    "train_steps_per_second": 0.118
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8e2af54b22e0c705b7be129d81b530e212ba6e920cf50f5a6b51678e37ee371e
+oid sha256:42bcfdc2f497fa88a496c41b8d8bbebd3c7aa9e6b2566ebda67c8fed3e34f63b
 size 5176