End of training

README.md

@@ -3,6 +3,8 @@ license: mit
 base_model: BAAI/bge-base-en-v1.5
 tags:
 - generated_from_trainer
+metrics:
+- f1
 model-index:
 - name: opus-em-bge-base
   results: []
@@ -14,6 +16,9 @@ should probably proofread and complete it, then remove this comment. -->
 # opus-em-bge-base
 
 This model is a fine-tuned version of [BAAI/bge-base-en-v1.5](https://huggingface.co/BAAI/bge-base-en-v1.5) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0054
+- F1: 0.9995
 
 ## Model description
 

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 3.0,
+    "eval_f1": 0.9994789524201289,
+    "eval_loss": 0.005438507534563541,
+    "eval_runtime": 162.2941,
+    "eval_samples": 36000,
+    "eval_samples_per_second": 221.819,
+    "eval_steps_per_second": 6.932,
+    "train_loss": 0.004904600699804723,
+    "train_runtime": 10571.3602,
+    "train_samples": 160000,
+    "train_samples_per_second": 45.406,
+    "train_steps_per_second": 0.709
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 3.0,
+    "eval_f1": 0.9994789524201289,
+    "eval_loss": 0.005438507534563541,
+    "eval_runtime": 162.2941,
+    "eval_samples": 36000,
+    "eval_samples_per_second": 221.819,
+    "eval_steps_per_second": 6.932
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "train_loss": 0.004904600699804723,
+    "train_runtime": 10571.3602,
+    "train_samples": 160000,
+    "train_samples_per_second": 45.406,
+    "train_steps_per_second": 0.709
+}

trainer_state.json

@@ -0,0 +1,250 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 7500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.08,
+      "learning_rate": 2e-05,
+      "loss": 0.1014,
+      "step": 200
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 2e-05,
+      "loss": 0.0067,
+      "step": 400
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 2e-05,
+      "loss": 0.0054,
+      "step": 600
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 2e-05,
+      "loss": 0.0072,
+      "step": 800
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 2e-05,
+      "loss": 0.0082,
+      "step": 1000
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 2e-05,
+      "loss": 0.0017,
+      "step": 1200
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 2e-05,
+      "loss": 0.0044,
+      "step": 1400
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 2e-05,
+      "loss": 0.0019,
+      "step": 1600
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 2e-05,
+      "loss": 0.0027,
+      "step": 1800
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 2e-05,
+      "loss": 0.0012,
+      "step": 2000
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 2e-05,
+      "loss": 0.0031,
+      "step": 2200
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 2e-05,
+      "loss": 0.0005,
+      "step": 2400
+    },
+    {
+      "epoch": 1.04,
+      "learning_rate": 2e-05,
+      "loss": 0.0026,
+      "step": 2600
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 2e-05,
+      "loss": 0.0006,
+      "step": 2800
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 2e-05,
+      "loss": 0.0027,
+      "step": 3000
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 2e-05,
+      "loss": 0.0027,
+      "step": 3200
+    },
+    {
+      "epoch": 1.36,
+      "learning_rate": 2e-05,
+      "loss": 0.0025,
+      "step": 3400
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 2e-05,
+      "loss": 0.0028,
+      "step": 3600
+    },
+    {
+      "epoch": 1.52,
+      "learning_rate": 2e-05,
+      "loss": 0.0006,
+      "step": 3800
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 2e-05,
+      "loss": 0.0019,
+      "step": 4000
+    },
+    {
+      "epoch": 1.68,
+      "learning_rate": 2e-05,
+      "loss": 0.0005,
+      "step": 4200
+    },
+    {
+      "epoch": 1.76,
+      "learning_rate": 2e-05,
+      "loss": 0.0004,
+      "step": 4400
+    },
+    {
+      "epoch": 1.84,
+      "learning_rate": 2e-05,
+      "loss": 0.0009,
+      "step": 4600
+    },
+    {
+      "epoch": 1.92,
+      "learning_rate": 2e-05,
+      "loss": 0.0025,
+      "step": 4800
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 2e-05,
+      "loss": 0.0016,
+      "step": 5000
+    },
+    {
+      "epoch": 2.08,
+      "learning_rate": 2e-05,
+      "loss": 0.0007,
+      "step": 5200
+    },
+    {
+      "epoch": 2.16,
+      "learning_rate": 2e-05,
+      "loss": 0.0022,
+      "step": 5400
+    },
+    {
+      "epoch": 2.24,
+      "learning_rate": 2e-05,
+      "loss": 0.0043,
+      "step": 5600
+    },
+    {
+      "epoch": 2.32,
+      "learning_rate": 2e-05,
+      "loss": 0.0017,
+      "step": 5800
+    },
+    {
+      "epoch": 2.4,
+      "learning_rate": 2e-05,
+      "loss": 0.0015,
+      "step": 6000
+    },
+    {
+      "epoch": 2.48,
+      "learning_rate": 2e-05,
+      "loss": 0.0003,
+      "step": 6200
+    },
+    {
+      "epoch": 2.56,
+      "learning_rate": 2e-05,
+      "loss": 0.0013,
+      "step": 6400
+    },
+    {
+      "epoch": 2.64,
+      "learning_rate": 2e-05,
+      "loss": 0.0019,
+      "step": 6600
+    },
+    {
+      "epoch": 2.72,
+      "learning_rate": 2e-05,
+      "loss": 0.0009,
+      "step": 6800
+    },
+    {
+      "epoch": 2.8,
+      "learning_rate": 2e-05,
+      "loss": 0.0,
+      "step": 7000
+    },
+    {
+      "epoch": 2.88,
+      "learning_rate": 2e-05,
+      "loss": 0.0011,
+      "step": 7200
+    },
+    {
+      "epoch": 2.96,
+      "learning_rate": 2e-05,
+      "loss": 0.0011,
+      "step": 7400
+    },
+    {
+      "epoch": 3.0,
+      "step": 7500,
+      "total_flos": 182323266453504.0,
+      "train_loss": 0.004904600699804723,
+      "train_runtime": 10571.3602,
+      "train_samples_per_second": 45.406,
+      "train_steps_per_second": 0.709
+    }
+  ],
+  "logging_steps": 200,
+  "max_steps": 7500,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 182323266453504.0,
+  "trial_name": null,
+  "trial_params": null
+}