Upload folder using huggingface_hub

all_results.json

@@ -1,9 +1,9 @@
 {
-    "epoch": 3.0,
-    "total_flos": 684863013568512.0,
-    "train_loss": 0.023829213575364362,
-    "train_runtime": 16963.4869,
+    "epoch": 2.0,
+    "total_flos": 452559651471360.0,
+    "train_loss": 0.022131871465586973,
+    "train_runtime": 16494.942,
     "train_samples": 8460,
-    "train_samples_per_second": 1.496,
-    "train_steps_per_second": 0.094
+    "train_samples_per_second": 1.026,
+    "train_steps_per_second": 0.085
 }

args.json

@@ -70,14 +70,14 @@
   "kl_coeff": 0.0,
   "label_names": null,
   "label_smoothing_factor": 0.0,
-  "learning_rate": 1e-06,
+  "learning_rate": 9e-07,
   "length_column_name": "length",
   "load_best_model_at_end": false,
   "local_rank": 0,
   "log_level": "passive",
   "log_level_replica": "warning",
   "log_on_each_node": true,
-  "logging_dir": "/scratch/gpfs/jg9904/saved_models/Qwen2.5-14B-Instruct-RL/runs/Apr24_14-16-12_della-k11g2",
+  "logging_dir": "/scratch/gpfs/jg9904/saved_models/Qwen2.5-14B-Instruct-RL-2.1/runs/Apr27_14-34-38_della-j16g2",
   "logging_first_step": false,
   "logging_nan_inf_filter": true,
   "logging_steps": 1.0,
@@ -89,15 +89,15 @@
   "max_steps": -1,
   "max_train_samples": null,
   "metric_for_best_model": null,
-  "model_name_or_path": "/scratch/gpfs/jg9904/saved_models/Qwen2.5-14B-Instruct-SFT",
+  "model_name_or_path": "/scratch/gpfs/jg9904/saved_models/Qwen2.5-14B-Instruct-RL",
   "mp_parameters": "",
   "neftune_noise_alpha": null,
   "no_cuda": false,
-  "num_train_epochs": 3.0,
+  "num_train_epochs": 2.0,
   "optim": "adamw_torch",
   "optim_args": null,
   "optim_target_modules": null,
-  "output_dir": "/scratch/gpfs/jg9904/saved_models/Qwen2.5-14B-Instruct-RL",
+  "output_dir": "/scratch/gpfs/jg9904/saved_models/Qwen2.5-14B-Instruct-RL-2.1",
   "overwrite_cache": false,
   "overwrite_output_dir": true,
   "past_index": -1,
@@ -117,14 +117,14 @@
   ],
   "restore_callback_states_from_checkpoint": false,
   "resume_from_checkpoint": null,
-  "run_name": "/scratch/gpfs/jg9904/saved_models/Qwen2.5-14B-Instruct-RL",
+  "run_name": "/scratch/gpfs/jg9904/saved_models/Qwen2.5-14B-Instruct-RL-2.1",
   "save_on_each_node": false,
   "save_only_model": true,
   "save_safetensors": true,
   "save_steps": 500,
   "save_strategy": "no",
   "save_total_limit": null,
-  "seed": 42,
+  "seed": 26,
   "skip_memory_metrics": true,
   "split_batches": null,
   "tf32": null,
@@ -136,7 +136,7 @@
   "tp_size": 0,
   "tpu_metrics_debug": false,
   "tpu_num_cores": null,
-  "train_tokenized_file": "/scratch/gpfs/jg9904/cogbehaveRL/RL/offline_rl_v2/data/14K_reward.jsonl",
+  "train_tokenized_file": "/scratch/gpfs/jg9904/cogbehaveRL/RL/offline_rl_v2/data/14K_reward-r2.jsonl",
   "use_cpu": false,
   "use_flash_attn": true,
   "use_ipex": false,

model-00001-of-00006.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f18f6592df3a3802936a42bbe707273fa833f75f023970db5938538c5827c04
+oid sha256:59689bf092b786e692f1353c24bedf498061684513464b7a73a7510467bdddf3
 size 4986211280

model-00002-of-00006.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab61ee1441c650203c387244c225fb1aed7f323a7ed948c1893dbf809397cc8f
+oid sha256:85a1620514c230c48bfb1aba8750847a213de948d3a0e8d2d855d60d9ae9ad94
 size 4954847344

model-00003-of-00006.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f62d595693b6fbd47cb7c22c13b57a20a1cc33fd960485b680318852a0ae5dc
+oid sha256:51cecf40de633b7c2e92622fbe91b6cb401d5b57da64c53c2704e2b512eaf9a8
 size 4954847392

model-00004-of-00006.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e10f48bd178f34c4b43b27d39ba28c2287762bea10f17c67050577144551da8
+oid sha256:eb8f7f572db0875c8b2bd1c11b6a627c32ae1205cf1380071260d3878a03f2a3
 size 4954847392

model-00005-of-00006.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c76c97e126c7218861307c02f09784b66acb906eb151ef0f46e3f5b86a3bb92b
+oid sha256:391045fc5562f499cd5ced91de26b3cd25da8094ded5c7350d9446b72590c804
 size 4954847392

model-00006-of-00006.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ace25ba75838b279919e80863544cbb71bc0e18daebd7f317d2ce6e5bb4652bf
+oid sha256:4c24750ce1b70304e6cdcd7f13f716ba999105e1d2ab22166b13961a1c2689ff
 size 4734533160

runs/Apr27_14-34-38_della-j16g2/events.out.tfevents.1745778947.della-j16g2.2201280.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3192051163af29dd14cc1cdcbf4c9776ac4444141d1a2249c73f662e53cbcf16
+size 515149

train_results.json

@@ -1,9 +1,9 @@
 {
-    "epoch": 3.0,
-    "total_flos": 684863013568512.0,
-    "train_loss": 0.023829213575364362,
-    "train_runtime": 16963.4869,
+    "epoch": 2.0,
+    "total_flos": 452559651471360.0,
+    "train_loss": 0.022131871465586973,
+    "train_runtime": 16494.942,
     "train_samples": 8460,
-    "train_samples_per_second": 1.496,
-    "train_steps_per_second": 0.094
+    "train_samples_per_second": 1.026,
+    "train_steps_per_second": 0.085
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f8a572573859a793cde5a6cf88ab0baee35cfabcb572759b18c90d158c2e2d3
+oid sha256:d17d30d7ac9e972934bf62062e8a2b07b263c0053803f3234d294d7b4a13ce17
 size 7160