Upload folder using huggingface_hub

tiny-aya-base/condition-2-zh-5k-seed42/adapter_config.json

@@ -0,0 +1,50 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": {
+    "base_model_class": "Cohere2ForCausalLM",
+    "parent_library": "transformers.models.cohere2.modeling_cohere2",
+    "unsloth_fixed": true
+  },
+  "base_model_name_or_path": "CohereLabs/tiny-aya-base",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "gate_proj",
+    "down_proj",
+    "q_proj",
+    "up_proj",
+    "o_proj",
+    "v_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

tiny-aya-base/condition-2-zh-5k-seed42/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd0bda14e83c8f6abb9b93cb65bcf8657c627a7253ec408efe757c66b2e516b6
+size 120981200

tiny-aya-base/condition-2-zh-5k-seed42/training_metrics.json

@@ -0,0 +1,221 @@
+{
+  "model_config_name": "tiny-aya-base",
+  "condition_name": "condition-2-zh-5k",
+  "seed": 42,
+  "output_name": "condition-2-zh-5k-seed42",
+  "train_result": {
+    "train_runtime": 3189.045,
+    "train_samples_per_second": 1.411,
+    "train_steps_per_second": 0.088,
+    "total_flos": 7.874966217293824e+16,
+    "train_loss": 1.0931839418749438,
+    "epoch": 1.0
+  },
+  "log_history": [
+    {
+      "loss": 1.3802,
+      "grad_norm": 0.18310873210430145,
+      "learning_rate": 0.00012,
+      "epoch": 0.03546099290780142,
+      "step": 10
+    },
+    {
+      "loss": 1.2231,
+      "grad_norm": 0.20137809216976166,
+      "learning_rate": 0.00019988926445681492,
+      "epoch": 0.07092198581560284,
+      "step": 20
+    },
+    {
+      "loss": 1.1538,
+      "grad_norm": 0.13060247898101807,
+      "learning_rate": 0.0001986463043917528,
+      "epoch": 0.10638297872340426,
+      "step": 30
+    },
+    {
+      "loss": 1.0858,
+      "grad_norm": 0.13724569976329803,
+      "learning_rate": 0.00019603921063437793,
+      "epoch": 0.14184397163120568,
+      "step": 40
+    },
+    {
+      "loss": 1.0876,
+      "grad_norm": 0.13389232754707336,
+      "learning_rate": 0.0001921040354671897,
+      "epoch": 0.1773049645390071,
+      "step": 50
+    },
+    {
+      "loss": 1.1002,
+      "grad_norm": 0.13278646767139435,
+      "learning_rate": 0.00018689519659051467,
+      "epoch": 0.2127659574468085,
+      "step": 60
+    },
+    {
+      "loss": 1.125,
+      "grad_norm": 0.12825895845890045,
+      "learning_rate": 0.00018048472460553257,
+      "epoch": 0.24822695035460993,
+      "step": 70
+    },
+    {
+      "loss": 1.0989,
+      "grad_norm": 0.11768730729818344,
+      "learning_rate": 0.00017296126693671884,
+      "epoch": 0.28368794326241137,
+      "step": 80
+    },
+    {
+      "loss": 1.0723,
+      "grad_norm": 0.1311381310224533,
+      "learning_rate": 0.00016442886196799464,
+      "epoch": 0.3191489361702128,
+      "step": 90
+    },
+    {
+      "loss": 1.1375,
+      "grad_norm": 0.11994785070419312,
+      "learning_rate": 0.00015500550034448413,
+      "epoch": 0.3546099290780142,
+      "step": 100
+    },
+    {
+      "loss": 1.051,
+      "grad_norm": 0.14449964463710785,
+      "learning_rate": 0.00014482149333496454,
+      "epoch": 0.3900709219858156,
+      "step": 110
+    },
+    {
+      "loss": 1.0801,
+      "grad_norm": 0.11190137267112732,
+      "learning_rate": 0.0001340176708181637,
+      "epoch": 0.425531914893617,
+      "step": 120
+    },
+    {
+      "loss": 1.082,
+      "grad_norm": 0.13787060976028442,
+      "learning_rate": 0.00012274343381211066,
+      "epoch": 0.46099290780141844,
+      "step": 130
+    },
+    {
+      "loss": 1.0855,
+      "grad_norm": 0.11431122571229935,
+      "learning_rate": 0.00011115468847720245,
+      "epoch": 0.49645390070921985,
+      "step": 140
+    },
+    {
+      "loss": 1.0947,
+      "grad_norm": 0.1287315934896469,
+      "learning_rate": 9.941169016269379e-05,
+      "epoch": 0.5319148936170213,
+      "step": 150
+    },
+    {
+      "loss": 1.0105,
+      "grad_norm": 0.10841815918684006,
+      "learning_rate": 8.767682731028415e-05,
+      "epoch": 0.5673758865248227,
+      "step": 160
+    },
+    {
+      "loss": 1.0387,
+      "grad_norm": 0.14366087317466736,
+      "learning_rate": 7.611237586016557e-05,
+      "epoch": 0.6028368794326241,
+      "step": 170
+    },
+    {
+      "loss": 1.0646,
+      "grad_norm": 0.11654563248157501,
+      "learning_rate": 6.487825521280109e-05,
+      "epoch": 0.6382978723404256,
+      "step": 180
+    },
+    {
+      "loss": 1.0768,
+      "grad_norm": 0.11926326900720596,
+      "learning_rate": 5.4129816778190936e-05,
+      "epoch": 0.6737588652482269,
+      "step": 190
+    },
+    {
+      "loss": 1.0763,
+      "grad_norm": 0.1296761929988861,
+      "learning_rate": 4.401569569374668e-05,
+      "epoch": 0.7092198581560284,
+      "step": 200
+    },
+    {
+      "loss": 1.0745,
+      "grad_norm": 0.12935227155685425,
+      "learning_rate": 3.467575541836305e-05,
+      "epoch": 0.7446808510638298,
+      "step": 210
+    },
+    {
+      "loss": 1.0821,
+      "grad_norm": 0.131064772605896,
+      "learning_rate": 2.6239153625937784e-05,
+      "epoch": 0.7801418439716312,
+      "step": 220
+    },
+    {
+      "loss": 1.0247,
+      "grad_norm": 0.13105124235153198,
+      "learning_rate": 1.882255614419376e-05,
+      "epoch": 0.8156028368794326,
+      "step": 230
+    },
+    {
+      "loss": 1.0794,
+      "grad_norm": 0.10978998243808746,
+      "learning_rate": 1.2528523637410838e-05,
+      "epoch": 0.851063829787234,
+      "step": 240
+    },
+    {
+      "loss": 1.0668,
+      "grad_norm": 0.12805533409118652,
+      "learning_rate": 7.4440933428779e-06,
+      "epoch": 0.8865248226950354,
+      "step": 250
+    },
+    {
+      "loss": 1.0593,
+      "grad_norm": 0.12139143794775009,
+      "learning_rate": 3.6395754735699894e-06,
+      "epoch": 0.9219858156028369,
+      "step": 260
+    },
+    {
+      "loss": 1.0517,
+      "grad_norm": 0.10230202227830887,
+      "learning_rate": 1.1675809310361497e-06,
+      "epoch": 0.9574468085106383,
+      "step": 270
+    },
+    {
+      "loss": 1.0584,
+      "grad_norm": 0.12069207429885864,
+      "learning_rate": 6.229377380218005e-08,
+      "epoch": 0.9929078014184397,
+      "step": 280
+    },
+    {
+      "train_runtime": 3189.045,
+      "train_samples_per_second": 1.411,
+      "train_steps_per_second": 0.088,
+      "total_flos": 7.874966217293824e+16,
+      "train_loss": 1.0931839418749438,
+      "epoch": 1.0,
+      "step": 282
+    }
+  ]
+}