Upload folder using huggingface_hub

adapter_config.json

@@ -29,12 +29,12 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "gate_proj",
     "down_proj",
-    "q_proj",
     "up_proj",
+    "gate_proj",
     "v_proj",
     "o_proj",
+    "q_proj",
     "k_proj"
   ],
   "task_type": "CAUSAL_LM",

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc030f8ea10c352e5747a54fd6bd60b5d61c279d752fe38e1d75aff90472319b
+oid sha256:c5fe9cd11eab35635b3e40afb66399670464aeb435423f4a450cca4a4ac3626a
 size 264308896

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d85ab20dfbad778fc5a15fb52e139c37b62533714841cd3769c9b18976e264a9
-size 134777605
+oid sha256:c19907c05be97657db095ba64e710f3f3f486bd1ed0860b1bbd6662d2b1e5b1e
+size 136089395

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ebac56874dd3cee39433ddfeb334df4a599430bfff17402cb47ea22a559fee9f
+oid sha256:b144eceedfa2101476447173dfe3d346a36b7516fd4322dfd02b73b27d9b2310
 size 14645

scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f573b9f7149922ed73a27c9028f6f2cbdca1c0ef23c998ef777ef3be95e566d
+oid sha256:4fee0874fa9afae54661807fadac685c3d3f843473b6af99cc43d812ec6e1b36
 size 1383

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:078542fd99723b70b4d1288e198aa1c9b9788cf33584a5b08ffba1fd602d7f84
+oid sha256:6c1b3d3a192c565272886289c8e8ac137d3c10918ed8d56d761a18da40f9c741
 size 1465

trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0006876633200385092,
+  "epoch": 0.0013753266400770184,
   "eval_steps": 500,
-  "global_step": 10,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -36,11 +36,39 @@
       "rewards/match_format_exactly/mean": 1.0,
       "rewards/match_format_exactly/std": 0.0,
       "step": 10
+    },
+    {
+      "completion_length": 334.6,
+      "completions/clipped_ratio": 0.025,
+      "completions/max_length": 824.9,
+      "completions/max_terminated_length": 713.2,
+      "completions/mean_length": 334.6,
+      "completions/mean_terminated_length": 299.05833435058594,
+      "completions/min_length": 50.2,
+      "completions/min_terminated_length": 50.2,
+      "epoch": 0.0013753266400770184,
+      "frac_reward_zero_std": 0.1,
+      "grad_norm": 5.82886266708374,
+      "kl": 1.5751606613397597,
+      "learning_rate": 2.3750000000000003e-07,
+      "loss": 0.0016,
+      "num_tokens": 51474.0,
+      "reward": 4.4375,
+      "reward_std": 0.4622055947780609,
+      "rewards/check_coherence/mean": 0.4875,
+      "rewards/check_coherence/std": 0.33231321573257444,
+      "rewards/check_response_quality/mean": 2.2125,
+      "rewards/check_response_quality/std": 0.2633414089679718,
+      "rewards/match_format_approximately/mean": 0.7375,
+      "rewards/match_format_approximately/std": 0.21933756470680238,
+      "rewards/match_format_exactly/mean": 1.0,
+      "rewards/match_format_exactly/std": 0.0,
+      "step": 20
     }
   ],
   "logging_steps": 10,
-  "max_steps": 60,
-  "num_input_tokens_seen": 26778,
+  "max_steps": 4000,
+  "num_input_tokens_seen": 51474,
   "num_train_epochs": 1,
   "save_steps": 10,
   "stateful_callbacks": {

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a6e31b6545879cafd72186cf6ce7bab37b7f1b65d30aec6986b01692da80961c
+oid sha256:89640938646618221e1b1ed739226e1b8be20971bb4a902cd531ba9b4399d32e
 size 7313