model_checkpoint_test

model_checkpoint_test/metadata.json

@@ -0,0 +1,4 @@
+{
+  "score": 0.0,
+  "step_index": 0
+}

model_checkpoint_test/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:65705bd2a8af3869b16af29bb33330b53303d946b96e94318390cba97cc81b2e
-size 3952509771
+oid sha256:426c65fe6efafe9122c6f867160776c5ab9ca0fabf89c01b69ee9de1eb034124
+size 2297

model_checkpoint_test/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d4b2d0e7e32c57f217bda640702c9a866cc251489bef3ccf66647c47e2f0ee6b
+oid sha256:098b29492211804ab324a36f37466821d948280bb74fce4ba895c03f13ecd878
 size 14645

model_checkpoint_test/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce1df6aa405639e3557888fcfe2436bb9a52be8517ae5231728aa34d0c5e37aa
+oid sha256:24ea0cb7b47f612954454da2a06d80c327ff664c0beff3af56cbb5de08d2b6ab
 size 1465

model_checkpoint_test/trainer_state.json

@@ -1,41 +1,17 @@
 {
   "best_global_step": null,
   "best_metric": null,
-  "best_model_checkpoint": "/home/paperspace/.arbor/storage/grpo:qwen2-0.5b-instruct:masked-penguin:20251027/checkpoints/model_checkpoint_best",
-  "epoch": 0.20634920634920634,
+  "best_model_checkpoint": null,
+  "epoch": 0,
   "eval_steps": 500,
-  "global_step": 13,
+  "global_step": 0,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
-  "log_history": [
-    {
-      "clip_ratio/high_max": 0.0,
-      "clip_ratio/high_mean": 0.0,
-      "clip_ratio/low_mean": 0.0,
-      "clip_ratio/low_min": 0.0,
-      "clip_ratio/region_mean": 0.0,
-      "completions/clipped_ratio": 0.0,
-      "completions/max_length": 4.0,
-      "completions/max_terminated_length": 4.0,
-      "completions/mean_length": 4.0,
-      "completions/mean_terminated_length": 4.0,
-      "completions/min_length": 4.0,
-      "completions/min_terminated_length": 4.0,
-      "epoch": 0.15873015873015872,
-      "grad_norm": 0.0,
-      "kl": 0.0,
-      "learning_rate": 9e-07,
-      "loss": 0.0,
-      "num_tokens": 4960.0,
-      "reward": -1.0,
-      "reward_std": 0.0,
-      "step": 10
-    }
-  ],
+  "log_history": [],
   "logging_steps": 10,
   "max_steps": 500,
-  "num_input_tokens_seen": 6448,
+  "num_input_tokens_seen": 0,
   "num_train_epochs": 8,
   "save_steps": 500,
   "stateful_callbacks": {
@@ -50,7 +26,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 0.0,
+  "total_flos": 0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null

model_checkpoint_test/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37311d79cdb8b23fae81f9e99e135d4bd44ca29b020b3838b33e13d534c37262
-size 7633
+oid sha256:1358766191dc7baee28883479e004089c478ffe01eb8a1acb403a49ca49b1358
+size 7697

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37311d79cdb8b23fae81f9e99e135d4bd44ca29b020b3838b33e13d534c37262
-size 7633
+oid sha256:1358766191dc7baee28883479e004089c478ffe01eb8a1acb403a49ca49b1358
+size 7697