Training in progress, step 700

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: 0.6747
-- Rewards/chosen: -0.2693
-- Rewards/rejected: -0.4359
-- Rewards/accuracies: 0.6009
-- Rewards/margins: 0.1666
-- Logps/rejected: -38.1393
-- Logps/chosen: -34.4192
-- Logits/rejected: -2.1170
-- Logits/chosen: -2.1217
+- Loss: 0.4913
+- Rewards/chosen: 0.1914
+- Rewards/rejected: 0.1556
+- Rewards/accuracies: 0.5453
+- Rewards/margins: 0.0358
+- Logps/rejected: -37.2944
+- Logps/chosen: -33.7611
+- Logits/rejected: -2.2272
+- Logits/chosen: -2.2320
 
 ## 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 |
-|:-------------:|:-----:|:----:|:-------------:|:---------------:|:------------:|:--------------:|:---------------:|:------------------:|:--------------:|:---------------:|:----------------:|
-| 0.6577        | 0.26  | 100  | -2.2338       | -2.2289         | -34.0400     | -37.5357       | 0.6949          | 0.5316             | -0.0038        | 0.0095          | -0.0133          |
-| 0.6156        | 0.52  | 200  | -2.2317       | -2.2268         | -34.0535     | -37.5578       | 0.6943          | 0.5191             | -0.0132        | 0.0156          | -0.0288          |
-| 0.5468        | 0.78  | 300  | -2.2277       | -2.2229         | -34.0684     | -37.5860       | 0.6903          | 0.5191             | -0.0237        | 0.0249          | -0.0486          |
-| 0.4243        | 1.04  | 400  | 0.6886        | -0.0963         | -0.1489      | 0.5540         | 0.0526          | -37.7293           | -34.1721       | -2.1933         | -2.1981          |
-| 0.353         | 1.3   | 500  | 0.6901        | -0.1994         | -0.2743      | 0.5569         | 0.0749          | -37.9085           | -34.3194       | -2.1884         | -2.1932          |
-| 0.3554        | 1.56  | 600  | 0.6763        | -0.1468         | -0.2572      | 0.5806         | 0.1103          | -37.8840           | -34.2443       | -2.1701         | -2.1749          |
-| 0.3333        | 1.82  | 700  | 0.6813        | -0.1817         | -0.2946      | 0.5743         | 0.1129          | -37.9375           | -34.2941       | -2.1549         | -2.1596          |
-| 0.2025        | 2.08  | 800  | 0.6800        | -0.2316         | -0.3667      | 0.5660         | 0.1351          | -38.0405           | -34.3655       | -2.1413         | -2.1461          |
-| 0.2153        | 2.34  | 900  | 0.6866        | -0.2482         | -0.3826      | 0.5835         | 0.1344          | -38.0632           | -34.3891       | -2.1292         | -2.1340          |
-| 0.2381        | 2.6   | 1000 | 0.6821        | -0.2624         | -0.4162      | 0.5864         | 0.1538          | -38.1112           | -34.4094       | -2.1207         | -2.1255          |
-| 0.1898        | 2.86  | 1100 | 0.6858        | -0.2673         | -0.4161      | 0.5831         | 0.1487          | -38.1110           | -34.4164       | -2.1188         | -2.1235          |
-| 0.2231        | 3.12  | 1200 | 0.6780        | -0.2626         | -0.4264      | 0.5889         | 0.1637          | -38.1257           | -34.4097       | -2.1175         | -2.1223          |
-| 0.164         | 3.38  | 1300 | 0.6834        | -0.2678         | -0.4194      | 0.5947         | 0.1516          | -38.1158           | -34.4172       | -2.1174         | -2.1221          |
-| 0.1562        | 3.64  | 1400 | 0.6753        | -0.2666         | -0.4361      | 0.5922         | 0.1696          | -38.1396           | -34.4154       | -2.1172         | -2.1219          |
-| 0.2163        | 3.9   | 1500 | 0.6831        | -0.2684         | -0.4218      | 0.5801         | 0.1534          | -38.1192           | -34.4180       | -2.1173         | -2.1220          |
+| Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
+|:-------------:|:-----:|:----:|:---------------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
+| 0.4799        | 0.26  | 100  | 0.4978          | 0.1217         | 0.1117           | 0.5341             | 0.0100          | -37.3570       | -33.8607     | -2.2333         | -2.2381       |
+| 0.4453        | 0.52  | 200  | 0.4928          | 0.1862         | 0.1561           | 0.5370             | 0.0302          | -37.2937       | -33.7685     | -2.2299         | -2.2347       |
+| 0.3947        | 0.78  | 300  | 0.4910          | 0.1956         | 0.1591           | 0.5565             | 0.0365          | -37.2894       | -33.7551     | -2.2274         | -2.2322       |
 
 
 ### 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

@@ -21,12 +21,12 @@
   "revision": null,
   "target_modules": [
     "k_proj",
-    "v_proj",
-    "q_proj",
-    "up_proj",
-    "down_proj",
+    "o_proj",
     "gate_proj",
-    "o_proj"
+    "up_proj",
+    "q_proj",
+    "v_proj",
+    "down_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:026a6415f2106bbe9c74c61bfa08dae685e1f6c824a2d2e66189c50a8330cb3f
+oid sha256:30d462aa3dfb9338c49917319859d4440a70aea4fafbe93d299c226a2a22aaf4
 size 176183216

all_results.json

@@ -1,21 +1,21 @@
 {
-    "epoch": 4.0,
-    "eval_logits/chosen": -2.1216881275177,
-    "eval_logits/rejected": -2.1169610023498535,
-    "eval_logps/chosen": -34.41923522949219,
-    "eval_logps/rejected": -38.13933563232422,
-    "eval_loss": 0.6746898293495178,
-    "eval_rewards/accuracies": 0.6009136438369751,
-    "eval_rewards/chosen": -0.2692793905735016,
-    "eval_rewards/margins": 0.16662099957466125,
-    "eval_rewards/rejected": -0.43590039014816284,
-    "eval_runtime": 145.1817,
+    "epoch": 1.0,
+    "eval_logits/chosen": -2.2319846153259277,
+    "eval_logits/rejected": -2.227167844772339,
+    "eval_logps/chosen": -33.76113510131836,
+    "eval_logps/rejected": -37.29436492919922,
+    "eval_loss": 0.49125906825065613,
+    "eval_rewards/accuracies": 0.545265793800354,
+    "eval_rewards/chosen": 0.19139321148395538,
+    "eval_rewards/margins": 0.03581271693110466,
+    "eval_rewards/rejected": 0.15558050572872162,
+    "eval_runtime": 145.6689,
     "eval_samples": 343,
-    "eval_samples_per_second": 2.363,
-    "eval_steps_per_second": 0.296,
-    "train_loss": 0.2216110908365869,
-    "train_runtime": 10768.4727,
+    "eval_samples_per_second": 2.355,
+    "eval_steps_per_second": 0.295,
+    "train_loss": 0.45851393303313814,
+    "train_runtime": 3252.0771,
     "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": -2.1216881275177,
-    "eval_logits/rejected": -2.1169610023498535,
-    "eval_logps/chosen": -34.41923522949219,
-    "eval_logps/rejected": -38.13933563232422,
-    "eval_loss": 0.6746898293495178,
-    "eval_rewards/accuracies": 0.6009136438369751,
-    "eval_rewards/chosen": -0.2692793905735016,
-    "eval_rewards/margins": 0.16662099957466125,
-    "eval_rewards/rejected": -0.43590039014816284,
-    "eval_runtime": 145.1817,
+    "epoch": 1.0,
+    "eval_logits/chosen": -2.2319846153259277,
+    "eval_logits/rejected": -2.227167844772339,
+    "eval_logps/chosen": -33.76113510131836,
+    "eval_logps/rejected": -37.29436492919922,
+    "eval_loss": 0.49125906825065613,
+    "eval_rewards/accuracies": 0.545265793800354,
+    "eval_rewards/chosen": 0.19139321148395538,
+    "eval_rewards/margins": 0.03581271693110466,
+    "eval_rewards/rejected": 0.15558050572872162,
+    "eval_runtime": 145.6689,
     "eval_samples": 343,
-    "eval_samples_per_second": 2.363,
-    "eval_steps_per_second": 0.296
+    "eval_samples_per_second": 2.355,
+    "eval_steps_per_second": 0.295
 }

train_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 4.0,
-    "train_loss": 0.2216110908365869,
-    "train_runtime": 10768.4727,
+    "epoch": 1.0,
+    "train_loss": 0.45851393303313814,
+    "train_runtime": 3252.0771,
     "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 sha256:6a7873256b464917bacb6f47f59f51881713a7cee62cb71ff848461a2de6635e
+oid sha256:8e2af54b22e0c705b7be129d81b530e212ba6e920cf50f5a6b51678e37ee371e
 size 5176