Model save

README.md

@@ -2,29 +2,24 @@
 license: gemma
 base_model: google/gemma-2-2b
 tags:
-- easylm
-- trl
-- sft
-- generated_from_trainer
 - trl
 - sft
 - generated_from_trainer
 datasets:
 - alpaca_farm
 model-index:
-- name: easylm-sft-gemma-2-2b-v2.7
+- name: easylm-sft-gemma-2-2b
   results: []
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 should probably proofread and complete it, then remove this comment. -->
 
-[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/lklab_kaist/grm/runs/b2v74p40)
-# easylm-sft-gemma-2-2b-v2.7
+# easylm-sft-gemma-2-2b
 
 This model is a fine-tuned version of [google/gemma-2-2b](https://huggingface.co/google/gemma-2-2b) on the alpaca_farm dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.9037
+- Loss: 0.9477
 
 ## Model description
 
@@ -59,14 +54,14 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch | Step | Validation Loss |
 |:-------------:|:-----:|:----:|:---------------:|
-| No log        | 1.0   | 13   | 0.7269          |
-| No log        | 2.0   | 26   | 0.8854          |
-| No log        | 3.0   | 39   | 0.9037          |
+| No log        | 1.0   | 13   | 0.7365          |
+| No log        | 2.0   | 26   | 0.9138          |
+| No log        | 3.0   | 39   | 0.9477          |
 
 
 ### Framework versions
 
-- Transformers 4.42.4
+- Transformers 4.43.3
 - Pytorch 2.3.0+cu121
 - Datasets 2.20.0
 - Tokenizers 0.19.1

all_results.json

@@ -1,14 +1,9 @@
 {
     "epoch": 3.0,
-    "eval_loss": 0.9036551117897034,
-    "eval_runtime": 0.7104,
-    "eval_samples": 100,
-    "eval_samples_per_second": 140.76,
-    "eval_steps_per_second": 18.299,
-    "total_flos": 648728419500032.0,
-    "train_loss": 0.4328929705497546,
-    "train_runtime": 169.1685,
+    "total_flos": 648728369168384.0,
+    "train_loss": 0.4277030749198718,
+    "train_runtime": 188.9615,
     "train_samples": 100,
-    "train_samples_per_second": 1.773,
-    "train_steps_per_second": 0.231
+    "train_samples_per_second": 1.588,
+    "train_steps_per_second": 0.206
 }

config.json

@@ -27,7 +27,7 @@
   "rope_theta": 10000.0,
   "sliding_window": 4096,
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.42.4",
+  "transformers_version": "4.43.3",
   "use_cache": true,
   "vocab_size": 256000
 }

generation_config.json

@@ -4,5 +4,5 @@
   "cache_implementation": "hybrid",
   "eos_token_id": 1,
   "pad_token_id": 0,
-  "transformers_version": "4.42.4"
+  "transformers_version": "4.43.3"
 }

model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:59180a822295d04eb5c6863e139dc12de1bd3dfc6aee4fa61f80893dad528527
+oid sha256:5f939cd2fc3072d9610787f59518cfa616d9a4e4574d91879c09278b25c235f4
 size 4988025760

model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:af88f933649ef95b91ff5c5f51035c54d42b413f5157e96fd3f5554b50f76d01
+oid sha256:39deb869e669d42dcaaa5dd503f2130a86ee9f294a1f1c6fcac4152fe9ee7ead
 size 1420339880

train_results.json

@@ -1,9 +1,9 @@
 {
     "epoch": 3.0,
-    "total_flos": 648728419500032.0,
-    "train_loss": 0.4328929705497546,
-    "train_runtime": 169.1685,
+    "total_flos": 648728369168384.0,
+    "train_loss": 0.4277030749198718,
+    "train_runtime": 188.9615,
     "train_samples": 100,
-    "train_samples_per_second": 1.773,
-    "train_steps_per_second": 0.231
+    "train_samples_per_second": 1.588,
+    "train_steps_per_second": 0.206
 }

trainer_state.json

@@ -10,36 +10,36 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_loss": 0.7268993854522705,
-      "eval_runtime": 0.6996,
-      "eval_samples_per_second": 142.933,
-      "eval_steps_per_second": 18.581,
+      "eval_loss": 0.7365190982818604,
+      "eval_runtime": 0.6967,
+      "eval_samples_per_second": 143.541,
+      "eval_steps_per_second": 18.66,
       "step": 13
     },
     {
       "epoch": 2.0,
-      "eval_loss": 0.8854426741600037,
-      "eval_runtime": 0.6985,
-      "eval_samples_per_second": 143.164,
-      "eval_steps_per_second": 18.611,
+      "eval_loss": 0.9137925505638123,
+      "eval_runtime": 0.6958,
+      "eval_samples_per_second": 143.712,
+      "eval_steps_per_second": 18.683,
       "step": 26
     },
     {
       "epoch": 3.0,
-      "eval_loss": 0.9036551117897034,
-      "eval_runtime": 0.7207,
-      "eval_samples_per_second": 138.758,
-      "eval_steps_per_second": 18.038,
+      "eval_loss": 0.9477354288101196,
+      "eval_runtime": 0.6964,
+      "eval_samples_per_second": 143.59,
+      "eval_steps_per_second": 18.667,
       "step": 39
     },
     {
       "epoch": 3.0,
       "step": 39,
-      "total_flos": 648728419500032.0,
-      "train_loss": 0.4328929705497546,
-      "train_runtime": 169.1685,
-      "train_samples_per_second": 1.773,
-      "train_steps_per_second": 0.231
+      "total_flos": 648728369168384.0,
+      "train_loss": 0.4277030749198718,
+      "train_runtime": 188.9615,
+      "train_samples_per_second": 1.588,
+      "train_steps_per_second": 0.206
     }
   ],
   "logging_steps": 500,
@@ -53,13 +53,13 @@
         "should_epoch_stop": false,
         "should_evaluate": false,
         "should_log": false,
-        "should_save": true,
-        "should_training_stop": true
+        "should_save": false,
+        "should_training_stop": false
       },
       "attributes": {}
     }
   },
-  "total_flos": 648728419500032.0,
+  "total_flos": 648728369168384.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:42d4f29ac9e6eaf36b0ee766ca2cb229d13bdc5d266a511742ca57b231a9b54d
-size 6392
+oid sha256:8bf45f26a4483f612d42291b1a443c8820a43ab24b747fd86c26449dada505f9
+size 6520