Dummy model upload

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d1881eca1d5c57b04779f2c2755b1992d4064877f0f76ffaa79fe805b11808b9
+oid sha256:8ec677e84828e3e44618ffea3b9afd17422cc9efc8d43c96c75273b7bcdfb3cd
 size 2384234968

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a614c17d4f0b07c748d204868330d7233a273c2f47316b389846d3f6753a130
+size 4768663315

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:250560ab3d528161ab3659b120def6e4a9ab4b457e3399603bbcfa40db3efc90
+size 14645

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48b0173ad77d395de0dcb80c9ad1ed4c0f3496d7e872f3137f2ff0d41d8e55e6
+size 1465

special_tokens_map.json

@@ -21,11 +21,5 @@
     "rstrip": false,
     "single_word": false
   },
-  "pad_token": {
-    "content": "<|endoftext|>",
-    "lstrip": false,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  }
+  "pad_token": "<|endoftext|>"
 }

trainer_state.json

@@ -0,0 +1,94 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 4,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.25,
+      "grad_norm": 237.14096069335938,
+      "learning_rate": 1e-06,
+      "logits/chosen": -0.6401658654212952,
+      "logits/rejected": -0.6565139889717102,
+      "logps/chosen": -239.0843048095703,
+      "logps/rejected": -251.87965393066406,
+      "loss": 0.6931,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": 0.0,
+      "rewards/margins": 0.0,
+      "rewards/rejected": 0.0,
+      "step": 1
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 205.25946044921875,
+      "learning_rate": 7.5e-07,
+      "logits/chosen": -0.8173736333847046,
+      "logits/rejected": NaN,
+      "logps/chosen": -230.25527954101562,
+      "logps/rejected": 0.0,
+      "loss": 0.6875,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 0.01139068603515625,
+      "rewards/margins": 0.01139068603515625,
+      "rewards/rejected": 0.0,
+      "step": 2
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 203.58648681640625,
+      "learning_rate": 5e-07,
+      "logits/chosen": -0.06951718032360077,
+      "logits/rejected": NaN,
+      "logps/chosen": -273.0633850097656,
+      "logps/rejected": 0.0,
+      "loss": 0.6691,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 0.04867248609662056,
+      "rewards/margins": 0.04867248609662056,
+      "rewards/rejected": 0.0,
+      "step": 3
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 251.11907958984375,
+      "learning_rate": 2.5e-07,
+      "logits/chosen": NaN,
+      "logits/rejected": -0.36895808577537537,
+      "logps/chosen": 0.0,
+      "logps/rejected": -262.998779296875,
+      "loss": 0.6926,
+      "rewards/accuracies": 1.0,
+      "rewards/chosen": 0.0,
+      "rewards/margins": 0.0010742187732830644,
+      "rewards/rejected": -0.0010742187732830644,
+      "step": 4
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 4,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65a8db7cce37df096f010008355f68266c4332946dee45fe5a1a2102e147147c
+size 6545