Upload task output 1

config.json

@@ -26,6 +26,6 @@
   "torch_dtype": "bfloat16",
   "transformers_version": "4.51.3",
   "unsloth_version": "2024.9",
-  "use_cache": true,
+  "use_cache": false,
   "vocab_size": 32000
 }

generation_config.json

@@ -1,5 +1,7 @@
 {
-  "temperature": null,
-  "top_p": null,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "max_length": 2048,
+  "pad_token_id": 0,
   "transformers_version": "4.51.3"
 }

loss.txt

@@ -0,0 +1 @@
+12,0.0034910915419459343

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dac4eaa2a8031e87705616aa1c38605e779849fa8620a0c8a803ee3ea841c963
+oid sha256:74f46edd6e8fbe8e563351ac05d833b5efcba7c3642831238281f6f95a198533
 size 2200119864

trainer_state.json

@@ -0,0 +1,72 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.4,
+  "eval_steps": 500,
+  "global_step": 12,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.8,
+      "eval_loss": 0.23455508053302765,
+      "eval_runtime": 0.847,
+      "eval_samples_per_second": 30.695,
+      "eval_steps_per_second": 30.695,
+      "step": 4
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 18.0,
+      "learning_rate": 1.034398775510204e-05,
+      "loss": 0.6029,
+      "step": 5
+    },
+    {
+      "epoch": 1.6,
+      "eval_loss": 0.0045469822362065315,
+      "eval_runtime": 0.7331,
+      "eval_samples_per_second": 35.466,
+      "eval_steps_per_second": 35.466,
+      "step": 8
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.7890625,
+      "learning_rate": 2.3273972448979586e-05,
+      "loss": 0.0268,
+      "step": 10
+    },
+    {
+      "epoch": 2.4,
+      "eval_loss": 0.0034910915419459343,
+      "eval_runtime": 0.7336,
+      "eval_samples_per_second": 35.439,
+      "eval_steps_per_second": 35.439,
+      "step": 12
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 15,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.3703631052210176e+16,
+  "train_batch_size": 100,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e1363607d5d5f7831874dd9a68730d09683d72d7edda472e7407c295ecc65e7
+size 5560