Upload folder using huggingface_hub

generation_config.json

@@ -1,6 +0,0 @@
-{
-  "bos_token_id": 151643,
-  "eos_token_id": 151643,
-  "max_new_tokens": 2048,
-  "transformers_version": "4.51.3"
-}

optimizer.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:ae1869aea5467ffc88a428bc881a5e8da420e5b315f456962050117e347f9441
-size 2384459962

rng_state.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:69f50a692634404f2eebb2eab9f456865957578d752987bc52d843ac2a774366
-size 14244

scheduler.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:9197244c5ee8fd84c23cb5387dd7cd4b0d34bb7720142963e9ea404ddb17646d
-size 1064

trainer_state.json

@@ -1,166 +0,0 @@
-{
-  "best_global_step": null,
-  "best_metric": null,
-  "best_model_checkpoint": null,
-  "epoch": 1.0,
-  "eval_steps": 200,
-  "global_step": 1250,
-  "is_hyper_param_search": false,
-  "is_local_process_zero": true,
-  "is_world_process_zero": true,
-  "log_history": [
-    {
-      "epoch": 0.08,
-      "grad_norm": 7.40625,
-      "learning_rate": 4.604e-05,
-      "loss": 1.1267,
-      "step": 100
-    },
-    {
-      "epoch": 0.16,
-      "grad_norm": 5.71875,
-      "learning_rate": 4.2040000000000004e-05,
-      "loss": 1.1115,
-      "step": 200
-    },
-    {
-      "epoch": 0.16,
-      "eval_loss": 1.4295576810836792,
-      "eval_runtime": 81.4705,
-      "eval_samples_per_second": 44.728,
-      "eval_steps_per_second": 5.597,
-      "step": 200
-    },
-    {
-      "epoch": 0.24,
-      "grad_norm": 5.8125,
-      "learning_rate": 3.804e-05,
-      "loss": 1.0758,
-      "step": 300
-    },
-    {
-      "epoch": 0.32,
-      "grad_norm": 4.875,
-      "learning_rate": 3.404e-05,
-      "loss": 1.0637,
-      "step": 400
-    },
-    {
-      "epoch": 0.32,
-      "eval_loss": 1.4099386930465698,
-      "eval_runtime": 81.8405,
-      "eval_samples_per_second": 44.526,
-      "eval_steps_per_second": 5.572,
-      "step": 400
-    },
-    {
-      "epoch": 0.4,
-      "grad_norm": 5.90625,
-      "learning_rate": 3.004e-05,
-      "loss": 1.0337,
-      "step": 500
-    },
-    {
-      "epoch": 0.48,
-      "grad_norm": 5.125,
-      "learning_rate": 2.6040000000000005e-05,
-      "loss": 1.025,
-      "step": 600
-    },
-    {
-      "epoch": 0.48,
-      "eval_loss": 1.3943334817886353,
-      "eval_runtime": 81.4207,
-      "eval_samples_per_second": 44.755,
-      "eval_steps_per_second": 5.601,
-      "step": 600
-    },
-    {
-      "epoch": 0.56,
-      "grad_norm": 5.125,
-      "learning_rate": 2.2040000000000002e-05,
-      "loss": 1.0328,
-      "step": 700
-    },
-    {
-      "epoch": 0.64,
-      "grad_norm": 5.84375,
-      "learning_rate": 1.804e-05,
-      "loss": 1.0097,
-      "step": 800
-    },
-    {
-      "epoch": 0.64,
-      "eval_loss": 1.3861989974975586,
-      "eval_runtime": 81.4518,
-      "eval_samples_per_second": 44.738,
-      "eval_steps_per_second": 5.598,
-      "step": 800
-    },
-    {
-      "epoch": 0.72,
-      "grad_norm": 5.0625,
-      "learning_rate": 1.4040000000000001e-05,
-      "loss": 1.0091,
-      "step": 900
-    },
-    {
-      "epoch": 0.8,
-      "grad_norm": 5.8125,
-      "learning_rate": 1.004e-05,
-      "loss": 0.9927,
-      "step": 1000
-    },
-    {
-      "epoch": 0.8,
-      "eval_loss": 1.3814911842346191,
-      "eval_runtime": 81.426,
-      "eval_samples_per_second": 44.752,
-      "eval_steps_per_second": 5.6,
-      "step": 1000
-    },
-    {
-      "epoch": 0.88,
-      "grad_norm": 6.5625,
-      "learning_rate": 6.040000000000001e-06,
-      "loss": 1.0129,
-      "step": 1100
-    },
-    {
-      "epoch": 0.96,
-      "grad_norm": 4.8125,
-      "learning_rate": 2.0400000000000004e-06,
-      "loss": 0.988,
-      "step": 1200
-    },
-    {
-      "epoch": 0.96,
-      "eval_loss": 1.3815840482711792,
-      "eval_runtime": 81.4118,
-      "eval_samples_per_second": 44.76,
-      "eval_steps_per_second": 5.601,
-      "step": 1200
-    }
-  ],
-  "logging_steps": 100,
-  "max_steps": 1250,
-  "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": 2.706232049664e+16,
-  "train_batch_size": 8,
-  "trial_name": null,
-  "trial_params": null
-}

training_args.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:f5891e3b928ad2808f900a2b53aa256fe6c83df2b1853b1d06afa110235dcafb
-size 5304