Upload fine-tuned model

config.json

@@ -0,0 +1,35 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": 128001,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 16,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 32.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
+  },
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.51.3",
+  "use_cache": true,
+  "vocab_size": 128256
+}

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 128000,
+  "do_sample": true,
+  "eos_token_id": 128001,
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.51.3"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4e7083f46f247845da972853910d8680ca649ab8c902c99ae0aef8b98f13b94
+size 4943274328

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d79a6afb2552fb1cf64796402d4e175b61bc5b99be45450ff790ca57d1cdf3c8
+size 2510808826

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c062f7f375beded48b5337f5a3f3a5cb38807fa3e85dbf3e294c0ab6b627bfc2
+size 14244

scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7ab928fb6fc03d23ed0a52a122112f8e7b9f1b5afe619387db540b707cec3ec
+size 988

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b81ef4084acb220d4aa4aaf816f556a4e6f57487225003cd5fc278dd5e90c942
+size 1064

trainer_state.json

@@ -0,0 +1,129 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.191904047976012,
+  "eval_steps": 25,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.13193403298350825,
+      "grad_norm": 119.62747955322266,
+      "learning_rate": 1.6000000000000003e-05,
+      "loss": 60.0685,
+      "step": 11
+    },
+    {
+      "epoch": 0.2638680659670165,
+      "grad_norm": 76.251220703125,
+      "learning_rate": 1.983619906947144e-05,
+      "loss": 53.8545,
+      "step": 22
+    },
+    {
+      "epoch": 0.29985007496251875,
+      "eval_loss": 3.3249454498291016,
+      "eval_runtime": 89.9708,
+      "eval_samples_per_second": 5.557,
+      "eval_steps_per_second": 1.856,
+      "step": 25
+    },
+    {
+      "epoch": 0.39580209895052476,
+      "grad_norm": 67.91344451904297,
+      "learning_rate": 1.9199794436588244e-05,
+      "loss": 52.8293,
+      "step": 33
+    },
+    {
+      "epoch": 0.527736131934033,
+      "grad_norm": 75.1031265258789,
+      "learning_rate": 1.811377838556573e-05,
+      "loss": 52.3377,
+      "step": 44
+    },
+    {
+      "epoch": 0.5997001499250375,
+      "eval_loss": 3.2520751953125,
+      "eval_runtime": 89.7398,
+      "eval_samples_per_second": 5.572,
+      "eval_steps_per_second": 1.861,
+      "step": 50
+    },
+    {
+      "epoch": 0.6596701649175413,
+      "grad_norm": 70.66634368896484,
+      "learning_rate": 1.6631226582407954e-05,
+      "loss": 52.2969,
+      "step": 55
+    },
+    {
+      "epoch": 0.7916041979010495,
+      "grad_norm": 74.07559204101562,
+      "learning_rate": 1.4824594148071936e-05,
+      "loss": 51.8169,
+      "step": 66
+    },
+    {
+      "epoch": 0.8995502248875562,
+      "eval_loss": 3.2324743270874023,
+      "eval_runtime": 90.1521,
+      "eval_samples_per_second": 5.546,
+      "eval_steps_per_second": 1.852,
+      "step": 75
+    },
+    {
+      "epoch": 0.9235382308845578,
+      "grad_norm": 72.83753967285156,
+      "learning_rate": 1.2782174639164528e-05,
+      "loss": 51.5118,
+      "step": 77
+    },
+    {
+      "epoch": 1.047976011994003,
+      "grad_norm": 79.93111419677734,
+      "learning_rate": 1.0603784974222862e-05,
+      "loss": 48.0834,
+      "step": 88
+    },
+    {
+      "epoch": 1.1799100449775113,
+      "grad_norm": 89.3459243774414,
+      "learning_rate": 8.395887191422397e-06,
+      "loss": 50.378,
+      "step": 99
+    },
+    {
+      "epoch": 1.191904047976012,
+      "eval_loss": 3.2021567821502686,
+      "eval_runtime": 90.5661,
+      "eval_samples_per_second": 5.521,
+      "eval_steps_per_second": 1.844,
+      "step": 100
+    }
+  ],
+  "logging_steps": 11,
+  "max_steps": 166,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 50,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.4253959153713152e+17,
+  "train_batch_size": 3,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:16d296347945cb67bfa6c7229aa45967a046d5ff07369d05446b90a909c9721c
+size 5368